2025
Matey-Sanz, Miguel; Claver, José M.; Dura, Esther; Felici-Castell, Santiago; Montoliu, Raúl; Pérez-Navarro, Antoni; Perez-Solano, Juan J.; Soriano, Antonio; Trilles-Oliver, Sergio; Torres-Sospedra, Joaquín
Fingerprinting with Fine Time Measurements: from RSS to RTT Proceedings Article
In: 2025 17th International Congress on Ultra Modern Telecommunications and Control Systems and Workshops (ICUMT), pp. 193-198, IEEE, 2025, ISBN: 979-8-3315-7675-2, (2015-19).
Abstract | Links | BibTeX | Tags: Indoor positioning, Wi-Fi fingerprint
@inproceedings{Matey2025c,
title = {Fingerprinting with Fine Time Measurements: from RSS to RTT},
author = {Miguel Matey-Sanz and José M. Claver and Esther Dura and Santiago Felici-Castell and Raúl Montoliu and Antoni Pérez-Navarro and Juan J. Perez-Solano and Antonio Soriano and Sergio Trilles-Oliver and Joaquín Torres-Sospedra},
doi = {https://doi.org/10.1109/ICUMT67815.2025.11268646},
isbn = {979-8-3315-7675-2},
year = {2025},
date = {2025-12-01},
urldate = {2025-12-01},
booktitle = {2025 17th International Congress on Ultra Modern Telecommunications and Control Systems and Workshops (ICUMT)},
pages = {193-198},
publisher = {IEEE},
abstract = {This work investigates the feasibility of Wi-Fi RTT-based fingerprinting using Android smartphones under different conditions. We analyze key factors affecting positioning accuracy based on k-Nearest Neighbors, including the distance metric, value of k, centroid computation strategy and data representation. Moreover, we also focused on fingerprint aggregation strategies. We show that common distance functions like Euclidean are suboptimal under device diversity. Our proposed differences to the closest AP (DtC) representation significantly reduces positioning errors, especially in cross-device scenarios, by mitigating device-specific measurement offsets. Additionally, aggregating RTT measurements into 1 s non-overlapping windows at both training and testing stages improves robustness and reduces computational load. Experiments across four datasets demonstrate sub-meter accuracy with the proposed approach, outperforming traditional methods. These results highlight the importance of distance metric, data representation, and aggregation in RTT-based positioning systems.},
note = {2015-19},
keywords = {Indoor positioning, Wi-Fi fingerprint},
pubstate = {published},
tppubtype = {inproceedings}
}
This work investigates the feasibility of Wi-Fi RTT-based fingerprinting using Android smartphones under different conditions. We analyze key factors affecting positioning accuracy based on k-Nearest Neighbors, including the distance metric, value of k, centroid computation strategy and data representation. Moreover, we also focused on fingerprint aggregation strategies. We show that common distance functions like Euclidean are suboptimal under device diversity. Our proposed differences to the closest AP (DtC) representation significantly reduces positioning errors, especially in cross-device scenarios, by mitigating device-specific measurement offsets. Additionally, aggregating RTT measurements into 1 s non-overlapping windows at both training and testing stages improves robustness and reduces computational load. Experiments across four datasets demonstrate sub-meter accuracy with the proposed approach, outperforming traditional methods. These results highlight the importance of distance metric, data representation, and aggregation in RTT-based positioning systems.
Ramos-Romero, Francisco; Trilles-Oliver, Sergio
IMPROVING CREATIVITY AND DIGITAL COMPETENCE THROUGH 3D DESIGN WITH BRICKLINK STUDIO Proceedings Article
In: ICERI25 Proceedings, pp. 8455-8458, IATED, 2025, ISSN: 978-84-09-78706-7, (2025-15).
Abstract | Links | BibTeX | Tags: data visualization, storytelling
@inproceedings{Ramos2025c,
title = {IMPROVING CREATIVITY AND DIGITAL COMPETENCE THROUGH 3D DESIGN WITH BRICKLINK STUDIO},
author = {Francisco Ramos-Romero and Sergio Trilles-Oliver},
doi = {https://doi.org/10.21125/iceri.2025.2393},
issn = {978-84-09-78706-7},
year = {2025},
date = {2025-11-01},
urldate = {2025-11-01},
booktitle = {ICERI25 Proceedings},
pages = {8455-8458},
publisher = {IATED},
abstract = {This paper presents a pedagogical experience designed for students of the Bachelor's Degree in Industrial Design Engineering and Product Development, aimed at enhancing both digital competence and creative thinking through the use of LEGO Studio, a virtual tool for 3D modeling and animation of LEGO constructions.
The primary objective of the course was to foster the students’ ability to conceptualize, model, and communicate three-dimensional ideas in a digital environment. The learning process was centered on an active and playful methodology, using LEGO bricks as a design language that is simultaneously accessible, familiar, and flexible. The course challenged students to develop their own models using three approaches: building entirely new creations from scratch, digitally reconstructing existing LEGO sets to understand their internal logic and structure, and finally, modifying those pre-built models to adapt them to new functional or aesthetic goals.
This combination of creative freedom and structured replication proved to be particularly effective. By first analyzing existing models, students learned key design strategies related to balance, proportion, modularity, and mechanical articulation. Then, through modification and original creation, they applied those strategies in new contexts—experimenting with visual storytelling, product aesthetics, and spatial composition. These processes are closely aligned with real-world tasks in industrial design, such as reengineering, redesign, and prototyping.
The students produced a diverse range of digital models, including architectural compositions, abstract objects, and character-based scenes. Notably, many of the projects were inspired by well-known cultural universes such as Star Wars, Minecraft, and The Lord of the Rings. Students recreated iconic ships, environments, and characters from these franchises, and then reinterpreted or modified them according to their own creative vision and design goals. These themed models not only enhanced engagement but also allowed students to explore storytelling, fan-based design culture, and the visual translation of fictional concepts into 3D forms.
These outputs served not only as evidence of their digital skills, but also as a portfolio of applied creativity. The project-based assessment allowed students to reflect critically on their decisions, document their workflows, and justify modifications from a design perspective.
Throughout the course, students demonstrated a notable improvement in their technological fluency—especially in using 3D environments, managing parts and assemblies, applying materials and lighting, and producing high-quality visualizations. At the same time, they strengthened key transversal skills such as planning, spatial reasoning, and visual communication. The learning environment also encouraged autonomy, curiosity, and play, which contributed to increased engagement and motivation.
In conclusion, this experience confirms the value of integrating accessible, game-based platforms like LEGO Studio into design education. It promotes a type of digital literacy that is both applied and creative, and it allows future professionals in industrial design to explore the intersections between virtual prototyping, expressive modeling, and user-centered innovation. By bridging technical competence and imaginative exploration, this approach prepares students to face complex design challenges with confidence and flexibility.},
note = {2025-15},
keywords = {data visualization, storytelling},
pubstate = {published},
tppubtype = {inproceedings}
}
This paper presents a pedagogical experience designed for students of the Bachelor's Degree in Industrial Design Engineering and Product Development, aimed at enhancing both digital competence and creative thinking through the use of LEGO Studio, a virtual tool for 3D modeling and animation of LEGO constructions.
The primary objective of the course was to foster the students’ ability to conceptualize, model, and communicate three-dimensional ideas in a digital environment. The learning process was centered on an active and playful methodology, using LEGO bricks as a design language that is simultaneously accessible, familiar, and flexible. The course challenged students to develop their own models using three approaches: building entirely new creations from scratch, digitally reconstructing existing LEGO sets to understand their internal logic and structure, and finally, modifying those pre-built models to adapt them to new functional or aesthetic goals.
This combination of creative freedom and structured replication proved to be particularly effective. By first analyzing existing models, students learned key design strategies related to balance, proportion, modularity, and mechanical articulation. Then, through modification and original creation, they applied those strategies in new contexts—experimenting with visual storytelling, product aesthetics, and spatial composition. These processes are closely aligned with real-world tasks in industrial design, such as reengineering, redesign, and prototyping.
The students produced a diverse range of digital models, including architectural compositions, abstract objects, and character-based scenes. Notably, many of the projects were inspired by well-known cultural universes such as Star Wars, Minecraft, and The Lord of the Rings. Students recreated iconic ships, environments, and characters from these franchises, and then reinterpreted or modified them according to their own creative vision and design goals. These themed models not only enhanced engagement but also allowed students to explore storytelling, fan-based design culture, and the visual translation of fictional concepts into 3D forms.
These outputs served not only as evidence of their digital skills, but also as a portfolio of applied creativity. The project-based assessment allowed students to reflect critically on their decisions, document their workflows, and justify modifications from a design perspective.
Throughout the course, students demonstrated a notable improvement in their technological fluency—especially in using 3D environments, managing parts and assemblies, applying materials and lighting, and producing high-quality visualizations. At the same time, they strengthened key transversal skills such as planning, spatial reasoning, and visual communication. The learning environment also encouraged autonomy, curiosity, and play, which contributed to increased engagement and motivation.
In conclusion, this experience confirms the value of integrating accessible, game-based platforms like LEGO Studio into design education. It promotes a type of digital literacy that is both applied and creative, and it allows future professionals in industrial design to explore the intersections between virtual prototyping, expressive modeling, and user-centered innovation. By bridging technical competence and imaginative exploration, this approach prepares students to face complex design challenges with confidence and flexibility.
The primary objective of the course was to foster the students’ ability to conceptualize, model, and communicate three-dimensional ideas in a digital environment. The learning process was centered on an active and playful methodology, using LEGO bricks as a design language that is simultaneously accessible, familiar, and flexible. The course challenged students to develop their own models using three approaches: building entirely new creations from scratch, digitally reconstructing existing LEGO sets to understand their internal logic and structure, and finally, modifying those pre-built models to adapt them to new functional or aesthetic goals.
This combination of creative freedom and structured replication proved to be particularly effective. By first analyzing existing models, students learned key design strategies related to balance, proportion, modularity, and mechanical articulation. Then, through modification and original creation, they applied those strategies in new contexts—experimenting with visual storytelling, product aesthetics, and spatial composition. These processes are closely aligned with real-world tasks in industrial design, such as reengineering, redesign, and prototyping.
The students produced a diverse range of digital models, including architectural compositions, abstract objects, and character-based scenes. Notably, many of the projects were inspired by well-known cultural universes such as Star Wars, Minecraft, and The Lord of the Rings. Students recreated iconic ships, environments, and characters from these franchises, and then reinterpreted or modified them according to their own creative vision and design goals. These themed models not only enhanced engagement but also allowed students to explore storytelling, fan-based design culture, and the visual translation of fictional concepts into 3D forms.
These outputs served not only as evidence of their digital skills, but also as a portfolio of applied creativity. The project-based assessment allowed students to reflect critically on their decisions, document their workflows, and justify modifications from a design perspective.
Throughout the course, students demonstrated a notable improvement in their technological fluency—especially in using 3D environments, managing parts and assemblies, applying materials and lighting, and producing high-quality visualizations. At the same time, they strengthened key transversal skills such as planning, spatial reasoning, and visual communication. The learning environment also encouraged autonomy, curiosity, and play, which contributed to increased engagement and motivation.
In conclusion, this experience confirms the value of integrating accessible, game-based platforms like LEGO Studio into design education. It promotes a type of digital literacy that is both applied and creative, and it allows future professionals in industrial design to explore the intersections between virtual prototyping, expressive modeling, and user-centered innovation. By bridging technical competence and imaginative exploration, this approach prepares students to face complex design challenges with confidence and flexibility.
Trilles-Oliver, Sergio; Juan-Verdoy, Pablo; Villanueva, María Santagueda; Granell-Canut, Carlos; Ramos-Romero, Francisco
SUCRE4KIDS: A TANGIBLE PROGRAMMING APPROACH FOR INTRODUCING COMPUTATIONAL THINKING IN EARLY EDUCATION Proceedings Article
In: ICERI25 Proceedings, pp. 8779-8784, IATED, 2025, ISBN: 978-84-09-78706-7, (2025-14).
Abstract | Links | BibTeX | Tags: Computational thinking, SUCRE, sucre4kids
@inproceedings{Trilles2025a,
title = {SUCRE4KIDS: A TANGIBLE PROGRAMMING APPROACH FOR INTRODUCING COMPUTATIONAL THINKING IN EARLY EDUCATION},
author = {Sergio Trilles-Oliver and Pablo Juan-Verdoy and María Santagueda Villanueva and Carlos Granell-Canut and Francisco Ramos-Romero},
doi = {https://doi.org/10.21125/iceri.2025.2476},
isbn = {978-84-09-78706-7},
year = {2025},
date = {2025-11-01},
urldate = {2025-11-01},
booktitle = {ICERI25 Proceedings},
pages = {8779-8784},
publisher = {IATED},
abstract = {Sucre4Kids is a sub-initiative of the broader Sucre programme, which aims to foster computational thinking throughout the entire pre-university educational stage. Specifically designed for children aged 5 to 8 years, Sucre4Kids introduces core programming concepts—such as conditionals, sequences, and loops—through a tangible approach tailored to early childhood and lower primary education. Its pedagogical framework prioritises sensory engagement, physical manipulation, and age-appropriate abstraction. Rather than relying on traditional digital devices, the system uses programmable NFC cards and a dedicated hardware platform to create intuitive, hands-on learning experiences.
At the heart of the system lies the SucreCore, a microcontroller-based device equipped with Wi-Fi, an NFC reader, a rechargeable battery, and a small display. Children use SucreCards—durable cards featuring pictograms and embedded NFC tags—to build their programmes. These cards are arranged in sequence and scanned with the SucreCore. A special “Run” card initiates execution, offering immediate feedback.
The design is aligned with the developmental characteristics and educational context of the target age group. Classrooms typically involve collaborative work, hands-on activities, and early literacy development. Sucre4Kids uses geometric shapes to label hardware connectors instead of technical terms, lowering cognitive barriers and encouraging exploration.
The programming model includes three interaction modes. In the basic mode, compound condition-action cards represent simple if–then–else logic. The advanced mode introduces discrete IF, THEN, and ELSE elements and Boolean operators such as AND and OR, allowing for more sophisticated conditional structures. A third mode supports musical composition: children sequence note and rhythm cards and apply loops to repeat patterns.
All modes include control cards for clearing, resetting, and replaying sequences, promoting procedural thinking and iterative refinement. This encourages children to grasp fundamental programming logic and develop structured reasoning.
Sucre4Kids is currently undergoing validation through teacher training and pilot classroom activities. Initial feedback highlights strong pupil engagement, ease of integration into routines, and alignment with pedagogical goals. Teachers report that children understand basic logic structures and cause-effect relationships using the tangible interface, even without prior coding experience.
Future development will extend the programming vocabulary with constructs such as variables and functions, and introduce interdisciplinary learning scenarios involving storytelling, music, and science. By embedding logic in familiar and playful contexts, Sucre4Kids offers a solid foundation for digital competence and scientific curiosity from the start of formal education.},
note = {2025-14},
keywords = {Computational thinking, SUCRE, sucre4kids},
pubstate = {published},
tppubtype = {inproceedings}
}
Sucre4Kids is a sub-initiative of the broader Sucre programme, which aims to foster computational thinking throughout the entire pre-university educational stage. Specifically designed for children aged 5 to 8 years, Sucre4Kids introduces core programming concepts—such as conditionals, sequences, and loops—through a tangible approach tailored to early childhood and lower primary education. Its pedagogical framework prioritises sensory engagement, physical manipulation, and age-appropriate abstraction. Rather than relying on traditional digital devices, the system uses programmable NFC cards and a dedicated hardware platform to create intuitive, hands-on learning experiences.
At the heart of the system lies the SucreCore, a microcontroller-based device equipped with Wi-Fi, an NFC reader, a rechargeable battery, and a small display. Children use SucreCards—durable cards featuring pictograms and embedded NFC tags—to build their programmes. These cards are arranged in sequence and scanned with the SucreCore. A special “Run” card initiates execution, offering immediate feedback.
The design is aligned with the developmental characteristics and educational context of the target age group. Classrooms typically involve collaborative work, hands-on activities, and early literacy development. Sucre4Kids uses geometric shapes to label hardware connectors instead of technical terms, lowering cognitive barriers and encouraging exploration.
The programming model includes three interaction modes. In the basic mode, compound condition-action cards represent simple if–then–else logic. The advanced mode introduces discrete IF, THEN, and ELSE elements and Boolean operators such as AND and OR, allowing for more sophisticated conditional structures. A third mode supports musical composition: children sequence note and rhythm cards and apply loops to repeat patterns.
All modes include control cards for clearing, resetting, and replaying sequences, promoting procedural thinking and iterative refinement. This encourages children to grasp fundamental programming logic and develop structured reasoning.
Sucre4Kids is currently undergoing validation through teacher training and pilot classroom activities. Initial feedback highlights strong pupil engagement, ease of integration into routines, and alignment with pedagogical goals. Teachers report that children understand basic logic structures and cause-effect relationships using the tangible interface, even without prior coding experience.
Future development will extend the programming vocabulary with constructs such as variables and functions, and introduce interdisciplinary learning scenarios involving storytelling, music, and science. By embedding logic in familiar and playful contexts, Sucre4Kids offers a solid foundation for digital competence and scientific curiosity from the start of formal education.
At the heart of the system lies the SucreCore, a microcontroller-based device equipped with Wi-Fi, an NFC reader, a rechargeable battery, and a small display. Children use SucreCards—durable cards featuring pictograms and embedded NFC tags—to build their programmes. These cards are arranged in sequence and scanned with the SucreCore. A special “Run” card initiates execution, offering immediate feedback.
The design is aligned with the developmental characteristics and educational context of the target age group. Classrooms typically involve collaborative work, hands-on activities, and early literacy development. Sucre4Kids uses geometric shapes to label hardware connectors instead of technical terms, lowering cognitive barriers and encouraging exploration.
The programming model includes three interaction modes. In the basic mode, compound condition-action cards represent simple if–then–else logic. The advanced mode introduces discrete IF, THEN, and ELSE elements and Boolean operators such as AND and OR, allowing for more sophisticated conditional structures. A third mode supports musical composition: children sequence note and rhythm cards and apply loops to repeat patterns.
All modes include control cards for clearing, resetting, and replaying sequences, promoting procedural thinking and iterative refinement. This encourages children to grasp fundamental programming logic and develop structured reasoning.
Sucre4Kids is currently undergoing validation through teacher training and pilot classroom activities. Initial feedback highlights strong pupil engagement, ease of integration into routines, and alignment with pedagogical goals. Teachers report that children understand basic logic structures and cause-effect relationships using the tangible interface, even without prior coding experience.
Future development will extend the programming vocabulary with constructs such as variables and functions, and introduce interdisciplinary learning scenarios involving storytelling, music, and science. By embedding logic in familiar and playful contexts, Sucre4Kids offers a solid foundation for digital competence and scientific curiosity from the start of formal education.
Gutiérrez, Aaron; Monteiro-Fialho, Leonardo; Trilles-Oliver, Sergio; Zaragozí, Benito; Granell-Canut, Carlos; Miravet, Daniel
Tourists' local buses ridership and pandemic resilience: A smart card data analysis in Southern Catalonia Journal Article
In: Transport, vol. 45, iss. 2, pp. 173–196, 2025, ISSN: 1648-4142, (2025-03).
Abstract | Links | BibTeX | Tags: public transport, smart data card, tourism, traveller profile
@article{Gutierrez2025a,
title = {Tourists' local buses ridership and pandemic resilience: A smart card data analysis in Southern Catalonia},
author = {Aaron Gutiérrez and Leonardo Monteiro-Fialho and Sergio Trilles-Oliver and Benito Zaragozí and Carlos Granell-Canut and Daniel Miravet},
url = {https://geotec.uji.es/2025/11/06/new-geotec-paper-on-public-transport-ridership-disruption-during-the-covid-pandemic/},
doi = {https://doi.org/10.3846/transport.2025.24650},
issn = {1648-4142},
year = {2025},
date = {2025-11-01},
urldate = {2025-11-01},
journal = {Transport},
volume = {45},
issue = {2},
pages = {173–196},
publisher = {Vilnius Gediminas Technical University},
abstract = {The COVID-19 pandemic′s harmful effects have varied across economic sectors and been particularly adverse for the transport and tourism sectors. This article analyses the pandemic′s impact on tourists′ use of public
transport since 2020, including its patterns of change and general decline, using data from more than 40000 smart card holders considered to be summertime users during the peak tourist season in Camp de Tarragona (Catalonia, Spain). 3 model-based clustering analyses of pre-pandemic data from 2019 were performed and used to classify data generated since the pandemic began in 2020. The 1st model included variables of each smart card′s volume of activity, the 2nd model analysed the concentration or spatial dispersion of validated uses of each card, and the 3rd model examined the temporal dimension of the use of smart cards depending on the defined objective. Among the major findings, the number of journeys plunged by 92% in summer 2020 – that is, by far more than throughout the year (64%), which suggests a higher loss of travellers linked with tourism activities (e.g., tourists, 2nd-residence owners, and workers in the tourism sector). Regarding the spatial dimension, patterns with minor reductions related to trips taken within cities (45%) or between major cities (78%). By contrast, travellers with sprawled patterns fell the use by 93%. Last, profiles obtained from variables of a temporary nature presented similar percentages of losses; the most significant losses were for use distributed throughout the day (91.81%) and throughout the night (90.12%). This article provides valuable insights into the pandemic′s varied effects on the use of public transport during peak season at a tourist destination, insights that could inform policies and actions to ensure a more robust response to future crises.},
note = {2025-03},
keywords = {public transport, smart data card, tourism, traveller profile},
pubstate = {published},
tppubtype = {article}
}
The COVID-19 pandemic′s harmful effects have varied across economic sectors and been particularly adverse for the transport and tourism sectors. This article analyses the pandemic′s impact on tourists′ use of public
transport since 2020, including its patterns of change and general decline, using data from more than 40000 smart card holders considered to be summertime users during the peak tourist season in Camp de Tarragona (Catalonia, Spain). 3 model-based clustering analyses of pre-pandemic data from 2019 were performed and used to classify data generated since the pandemic began in 2020. The 1st model included variables of each smart card′s volume of activity, the 2nd model analysed the concentration or spatial dispersion of validated uses of each card, and the 3rd model examined the temporal dimension of the use of smart cards depending on the defined objective. Among the major findings, the number of journeys plunged by 92% in summer 2020 – that is, by far more than throughout the year (64%), which suggests a higher loss of travellers linked with tourism activities (e.g., tourists, 2nd-residence owners, and workers in the tourism sector). Regarding the spatial dimension, patterns with minor reductions related to trips taken within cities (45%) or between major cities (78%). By contrast, travellers with sprawled patterns fell the use by 93%. Last, profiles obtained from variables of a temporary nature presented similar percentages of losses; the most significant losses were for use distributed throughout the day (91.81%) and throughout the night (90.12%). This article provides valuable insights into the pandemic′s varied effects on the use of public transport during peak season at a tourist destination, insights that could inform policies and actions to ensure a more robust response to future crises.
transport since 2020, including its patterns of change and general decline, using data from more than 40000 smart card holders considered to be summertime users during the peak tourist season in Camp de Tarragona (Catalonia, Spain). 3 model-based clustering analyses of pre-pandemic data from 2019 were performed and used to classify data generated since the pandemic began in 2020. The 1st model included variables of each smart card′s volume of activity, the 2nd model analysed the concentration or spatial dispersion of validated uses of each card, and the 3rd model examined the temporal dimension of the use of smart cards depending on the defined objective. Among the major findings, the number of journeys plunged by 92% in summer 2020 – that is, by far more than throughout the year (64%), which suggests a higher loss of travellers linked with tourism activities (e.g., tourists, 2nd-residence owners, and workers in the tourism sector). Regarding the spatial dimension, patterns with minor reductions related to trips taken within cities (45%) or between major cities (78%). By contrast, travellers with sprawled patterns fell the use by 93%. Last, profiles obtained from variables of a temporary nature presented similar percentages of losses; the most significant losses were for use distributed throughout the day (91.81%) and throughout the night (90.12%). This article provides valuable insights into the pandemic′s varied effects on the use of public transport during peak season at a tourist destination, insights that could inform policies and actions to ensure a more robust response to future crises.
Matey-Sanz, Miguel; Torres-Sospedra, Joaquín
Comparative Analysis of Indoor Positioning Approaches with Wi-Fi RTT from Android Devices Best Paper Proceedings Article
In: 2025 IEEE 15th International Conference on Indoor Positioning and Indoor Navigation (IPIN), pp. 1-6, IEEE, 2025, ISBN: 979-8-3315-5680-8, (2025-16).
Abstract | Links | BibTeX | Tags: Indoor localization, Wi-Fi
@inproceedings{Matey2025b,
title = {Comparative Analysis of Indoor Positioning Approaches with Wi-Fi RTT from Android Devices},
author = {Miguel Matey-Sanz and Joaquín Torres-Sospedra},
doi = {https://doi.org/10.1109/IPIN66788.2025.11212914},
isbn = {979-8-3315-5680-8},
year = {2025},
date = {2025-09-15},
urldate = {2025-09-15},
booktitle = {2025 IEEE 15th International Conference on Indoor Positioning and Indoor Navigation (IPIN)},
pages = {1-6},
publisher = {IEEE},
abstract = {Wi-Fi-based indoor positioning applications usually employ methods based on the Received Signal Strength Indicator (RSSI), an indicator of the signal attenuation. However, relying on this indicator has accuracy and stability limitations, hampering the performance of indoor positioning systems. This work studied the indoor positioning based on Wi-Fi Round Trip Time, which employs the signal’s time-of-flight to accurately measure the distance between compatible devices. We deployed four RTT-compatible access points in a research laboratory and collected RTT measurements from two compatible Android smartphones on 20 reference locations. Then, we compared the centroid, Euclidean-based k-Nearest Neighbours (KNN) and a KNN with an adapted Euclidean distance for RTT data for position estimation using the collected dataset. We also explored the effect of using individual and time-aggregated RTT measurements. The results of the study show that a 1s time aggregation improves the mean errors of the KNN-based methods and that the adapted Euclidean distance provides the best mean positioning errors (0.4−0.6m).},
note = {2025-16},
keywords = {Indoor localization, Wi-Fi},
pubstate = {published},
tppubtype = {inproceedings}
}
Wi-Fi-based indoor positioning applications usually employ methods based on the Received Signal Strength Indicator (RSSI), an indicator of the signal attenuation. However, relying on this indicator has accuracy and stability limitations, hampering the performance of indoor positioning systems. This work studied the indoor positioning based on Wi-Fi Round Trip Time, which employs the signal’s time-of-flight to accurately measure the distance between compatible devices. We deployed four RTT-compatible access points in a research laboratory and collected RTT measurements from two compatible Android smartphones on 20 reference locations. Then, we compared the centroid, Euclidean-based k-Nearest Neighbours (KNN) and a KNN with an adapted Euclidean distance for RTT data for position estimation using the collected dataset. We also explored the effect of using individual and time-aggregated RTT measurements. The results of the study show that a 1s time aggregation improves the mean errors of the KNN-based methods and that the adapted Euclidean distance provides the best mean positioning errors (0.4−0.6m).
Pérez-Senosiain, David; Matey-Sanz, Miguel; Torres-Sospedra, Joaquín
Evaluating Wi-Fi Round Trip Time for Accurate Indoor Positioning with Android Smartphones Proceedings Article
In: 2025 IEEE 15th International Conference on Indoor Positioning; Tampere Indoor Navigation (IPIN), pp. 1-6, IEEE, 2025, ISBN: 979-8-3315-5680-8, (2025-17).
Abstract | Links | BibTeX | Tags: Indoor positioning, Wi-Fi
@inproceedings{Perez-Senosiain2025a,
title = {Evaluating Wi-Fi Round Trip Time for Accurate Indoor Positioning with Android Smartphones},
author = {David Pérez-Senosiain and Miguel Matey-Sanz and Joaquín Torres-Sospedra},
doi = {https://doi.org/10.1109/IPIN66788.2025.11212978},
isbn = {979-8-3315-5680-8},
year = {2025},
date = {2025-09-15},
urldate = {2025-09-15},
booktitle = {2025 IEEE 15th International Conference on Indoor Positioning; Tampere Indoor Navigation (IPIN)},
pages = {1-6},
publisher = {IEEE},
abstract = {Estimating the distance between a device and an access point is fundamental for many Wi-Fi-based positioning applications. Methods based on the Received Signal Strength Indicator (RSSI) have limitations in terms of accuracy and stability. This work presents a study on the Wi-Fi Round Trip Time (RTT) technique, which enables more precise distance measurements between a device and a compatible access point by using signal time-of-flight instead of signal attenuation. To achieve this, a native Android application was developed to obtain distances from RTT and facilitate the collection and analysis of experimental data. Additionally, the developed application includes a collaborative and up-to-date database of compatible devices. For testing, two different smartphone models and a Wi-Fi access point capable of responding to RTT requests were used. The results highlight the temporal evolution of the measurements, the limitations of this technology for positioning. Also, we found that Wi-Fi RTT is more reliable in terms of measurements and sampling frequency than Wi-Fi RSSI fingerprinting.},
note = {2025-17},
keywords = {Indoor positioning, Wi-Fi},
pubstate = {published},
tppubtype = {inproceedings}
}
Estimating the distance between a device and an access point is fundamental for many Wi-Fi-based positioning applications. Methods based on the Received Signal Strength Indicator (RSSI) have limitations in terms of accuracy and stability. This work presents a study on the Wi-Fi Round Trip Time (RTT) technique, which enables more precise distance measurements between a device and a compatible access point by using signal time-of-flight instead of signal attenuation. To achieve this, a native Android application was developed to obtain distances from RTT and facilitate the collection and analysis of experimental data. Additionally, the developed application includes a collaborative and up-to-date database of compatible devices. For testing, two different smartphone models and a Wi-Fi access point capable of responding to RTT requests were used. The results highlight the temporal evolution of the measurements, the limitations of this technology for positioning. Also, we found that Wi-Fi RTT is more reliable in terms of measurements and sampling frequency than Wi-Fi RSSI fingerprinting.
Quezada-Gaibor, Darwin; Matey-Sanz, Miguel; Huerta-Guijarro, Joaquín; Torres-Sospedra, Joaquín
Modular Fingerprinting and Deep Learning: A New Training Approach Proceedings Article
In: 2025 IEEE Applied Sensing Conference (APSCON), pp. 1-4, IEEE, 2025, ISBN: 979-8-3503-7933-4, (2025-18).
Abstract | Links | BibTeX | Tags: deep learning, Wi-Fi fingerprint
@inproceedings{Quezada2025a,
title = {Modular Fingerprinting and Deep Learning: A New Training Approach},
author = {Darwin Quezada-Gaibor and Miguel Matey-Sanz and Joaquín Huerta-Guijarro and Joaquín Torres-Sospedra},
doi = {https://doi.org/10.1109/APSCON63569.2025.11144084},
isbn = {979-8-3503-7933-4},
year = {2025},
date = {2025-09-04},
urldate = {2025-09-04},
booktitle = {2025 IEEE Applied Sensing Conference (APSCON)},
pages = {1-4},
publisher = {IEEE},
abstract = {Machine learning models are increasingly used for indoor positioning, often in conjunction with fingerprinting to estimate device location. However, accurately estimating position remains challenging due to complex radio maps. This research proposes a novel approach where the dataset is divided based on Access Points (APs) and maximum Received Signal Strength (RSS) values in fingerprints. By training separate models for each subgroup, we achieved a reduction of over 33% in mean 2D positioning error across two out of three public datasets, despite a slight decrease in floor hit rate.},
note = {2025-18},
keywords = {deep learning, Wi-Fi fingerprint},
pubstate = {published},
tppubtype = {inproceedings}
}
Machine learning models are increasingly used for indoor positioning, often in conjunction with fingerprinting to estimate device location. However, accurately estimating position remains challenging due to complex radio maps. This research proposes a novel approach where the dataset is divided based on Access Points (APs) and maximum Received Signal Strength (RSS) values in fingerprints. By training separate models for each subgroup, we achieved a reduction of over 33% in mean 2D positioning error across two out of three public datasets, despite a slight decrease in floor hit rate.
Hammad, Sahibzada Saadoon; Trilles-Oliver, Sergio
Context-Aware Multi-Step Imputation for Univariate Temperature Time Series Using BiLSTM Proceedings Article
In: 2025 IEEE International Conference on Omni-layer Intelligent Systems (COINS), pp. 1-6, IEEE, 2025, ISBN: 979-8-3315-2037-3, (2025-13).
Abstract | Links | BibTeX | Tags: Anomaly detection, machine learning
@inproceedings{Saadoon2025b,
title = {Context-Aware Multi-Step Imputation for Univariate Temperature Time Series Using BiLSTM},
author = {Sahibzada Saadoon Hammad and Sergio Trilles-Oliver},
doi = {https://doi.ieeecomputersociety.org/10.1109/COINS65080.2025.11125756},
isbn = {979-8-3315-2037-3},
year = {2025},
date = {2025-08-01},
urldate = {2025-08-01},
booktitle = {2025 IEEE International Conference on Omni-layer Intelligent Systems (COINS)},
pages = {1-6},
publisher = {IEEE},
abstract = {Missing data imputation remains a persistent challenge in Internet of Things and sensor-based environments, particularly for applications related to smart cities and urban data analysis. In this study, we compare imputation methods for univariate urban temperature time series collected from three distinct weather stations with significant missing segments. To evaluate the performance of each method, artificial gaps of varying lengths are systematically introduced into the data. We assess the accuracy of eXtreme Gradient Boosting (XGBoost) regression in comparison with more conventional techniques such as spline interpolation. While XGBoost performs well for short and medium gaps, its effectiveness diminishes for longer gaps due to its limited capacity to capture the cyclic patterns inherent in temperature data. To address this, we propose a context-aware Bidirectional Long Short-Term Memory network that captures both past and future temporal dependencies. The model performs multi-step predictions using a one-day context window, avoiding the cumulative error typically propagated in recursive single-step approaches. We also compared the performance of our proposed model with Multi-layer Perceptron. Our results show that the Bidirectional Long Short-Term Memory model performs better than MLP overall and significantly outperforms XGBoost, especially for long missing blocks. These findings demonstrate the effectiveness of context-aware deep learning—particularly Bidirectional Long Short-Term Memory model for robust imputation of cyclic temperature time series in sensor networks.},
note = {2025-13},
keywords = {Anomaly detection, machine learning},
pubstate = {published},
tppubtype = {inproceedings}
}
Missing data imputation remains a persistent challenge in Internet of Things and sensor-based environments, particularly for applications related to smart cities and urban data analysis. In this study, we compare imputation methods for univariate urban temperature time series collected from three distinct weather stations with significant missing segments. To evaluate the performance of each method, artificial gaps of varying lengths are systematically introduced into the data. We assess the accuracy of eXtreme Gradient Boosting (XGBoost) regression in comparison with more conventional techniques such as spline interpolation. While XGBoost performs well for short and medium gaps, its effectiveness diminishes for longer gaps due to its limited capacity to capture the cyclic patterns inherent in temperature data. To address this, we propose a context-aware Bidirectional Long Short-Term Memory network that captures both past and future temporal dependencies. The model performs multi-step predictions using a one-day context window, avoiding the cumulative error typically propagated in recursive single-step approaches. We also compared the performance of our proposed model with Multi-layer Perceptron. Our results show that the Bidirectional Long Short-Term Memory model performs better than MLP overall and significantly outperforms XGBoost, especially for long missing blocks. These findings demonstrate the effectiveness of context-aware deep learning—particularly Bidirectional Long Short-Term Memory model for robust imputation of cyclic temperature time series in sensor networks.
Matey-Sanz, Miguel; Granell-Canut, Carlos; Cárdenas, Ramón A. Mollineda
La IA generativa como acompañante en el ciclo de vida del software Proceedings Article
In: Actas de las Jornadas sobre Enseñanza Universitaria de la Informática (JENUI), pp. 45-53, AENUI, 2025, ISSN: 2531-0607, (2025-06).
Abstract | Links | BibTeX | Tags: docente
@inproceedings{Matey2025a,
title = {La IA generativa como acompañante en el ciclo de vida del software},
author = {Miguel Matey-Sanz and Carlos Granell-Canut and Ramón A. Mollineda Cárdenas},
url = {https://aenui.org/actas/fichas/JENUI_2025_005.html},
issn = {2531-0607},
year = {2025},
date = {2025-07-15},
urldate = {2025-07-15},
booktitle = {Actas de las Jornadas sobre Enseñanza Universitaria de la Informática (JENUI)},
volume = {10},
pages = {45-53},
publisher = {AENUI},
abstract = {Experiencias recientes han mostrado el valor de la inteligencia artificial generativa (IAG) como recurso formativo en la educación universitaria. Sin embargo, su integración en actividades docentes requiere supervision para garantizar un uso crítico, transparente, ético y alineado con los objetivos formativos. Ante la dificultad, y quizás la inoportunidad, de limitar el uso de estas herramientas, este trabajo presenta una propuesta de uso sistemático de la IAG en todas las etapas y tareas de un proyecto de desarrollo de software dirigido por pruebas de aceptación ejecutables, diseño evolutivo, y objetivos de integración continua y despliegue multiplataforma. La metodología docente y el sistema de evaluación fueron adaptados para considerar análisis críticos de las interacciones con la IAG. Al finalizar la asignatura, el alumnado realizo una encuesta en la que se pidió medir el grado de utilidad de distintas herramientas IAG en diferentes ámbitos. Los resultados de la encuesta, la evaluación del proyecto, y las valoraciones del profesorado sobre las experiencias documentadas pretenden contribuir a entender el potencial que ofrecen estas herramientas en distintos ámbitos del desarrollo de software, así como expectativas, patrones de interacción y limitaciones del alumnado para lograr el máximo rendimiento de estas tecnologías.},
note = {2025-06},
keywords = {docente},
pubstate = {published},
tppubtype = {inproceedings}
}
Experiencias recientes han mostrado el valor de la inteligencia artificial generativa (IAG) como recurso formativo en la educación universitaria. Sin embargo, su integración en actividades docentes requiere supervision para garantizar un uso crítico, transparente, ético y alineado con los objetivos formativos. Ante la dificultad, y quizás la inoportunidad, de limitar el uso de estas herramientas, este trabajo presenta una propuesta de uso sistemático de la IAG en todas las etapas y tareas de un proyecto de desarrollo de software dirigido por pruebas de aceptación ejecutables, diseño evolutivo, y objetivos de integración continua y despliegue multiplataforma. La metodología docente y el sistema de evaluación fueron adaptados para considerar análisis críticos de las interacciones con la IAG. Al finalizar la asignatura, el alumnado realizo una encuesta en la que se pidió medir el grado de utilidad de distintas herramientas IAG en diferentes ámbitos. Los resultados de la encuesta, la evaluación del proyecto, y las valoraciones del profesorado sobre las experiencias documentadas pretenden contribuir a entender el potencial que ofrecen estas herramientas en distintos ámbitos del desarrollo de software, así como expectativas, patrones de interacción y limitaciones del alumnado para lograr el máximo rendimiento de estas tecnologías.
Ramos-Romero, Francisco; Trilles-Oliver, Sergio
DATA VISUALIZATION WITH LEGO: A HANDS-ON APPROACH Proceedings Article
In: EDULEARN25 Proceedings, pp. 9628-9631, IATED, 2025, ISBN: 978-84-09-74218-9, (2025-07).
Abstract | Links | BibTeX | Tags: data visualization, storytelling
@inproceedings{Ramos2025a,
title = {DATA VISUALIZATION WITH LEGO: A HANDS-ON APPROACH},
author = {Francisco Ramos-Romero and Sergio Trilles-Oliver},
doi = {https://doi.org/10.21125/edulearn.2025.2493},
isbn = {978-84-09-74218-9},
year = {2025},
date = {2025-07-01},
urldate = {2025-07-01},
booktitle = {EDULEARN25 Proceedings},
pages = {9628-9631},
publisher = {IATED},
abstract = {Complex datasets must be communicated clearly, and data visualization helps achieve this. Bar charts and line graphs are effective but often fail to illustrate deeper relationships, such as the “why” and “how.” This paper explores the use of LEGO bricks to enhance students data visualization skills. By constructing three-dimensional models, students develop a deeper understanding of complex structures and relationships in data while applying creativity. LEGO’s modularity enables students to build, modify, and explore patterns dynamically, fostering a hands-on learning experience.
Each LEGO brick can represent different data points, categories, or variables, with colors, sizes, and arrangements conveying specific metrics. This approach helps students grasp how data interrelates and how visualizations represent complex patterns. Traditional visualizations often oversimplify relationships, whereas LEGO-based models allow for interactive exploration.
For example, consider a dataset displaying monthly sales performance across regions. Typically, students would create bar charts or line graphs, which condense data effectively but fail to reveal underlying connections. Instead, using LEGO bricks, students assign colors to regions and stack bricks to indicate sales volume per month. Tall red bricks could signify high sales, while shorter green bricks represent lower sales. As they adjust the model, students observe how sales evolve over time and across regions, making the data more tangible and engaging than static charts.
LEGO-based visualizations provide a dynamic method for modeling data. Students can add or remove bricks to reflect changes in sales, testing different scenarios. This interactivity helps learners explore how datasets shift and how different factors influence outcomes. Unlike static charts, which can be abstract, LEGO models enable students to physically manipulate data, reinforcing comprehension.
Additionally, LEGO's three-dimensional nature enhances students’ understanding of relationships within datasets. By arranging bricks spatially, they can highlight trends, value comparisons, and anomalies that might be harder to identify in two-dimensional graphs. Stacking bricks over time reveals trends, while spatial positioning shows regional correlations. This encourages deeper analytical thinking and effective communication of complex ideas.
Indeed, because LEGOs are accessible, students from different contexts are able to collaborate and participate in discussions. Collaboration among students assists them in improving their visualizations and analyzing the data from different angles.
Furthermore, LEGO-based exercises allow students to simulate different scenarios. For instance, to analyze the impact of a marketing campaign, students can modify the LEGO model to reflect sales growth, visually testing hypotheses in real-time. This hands-on experimentation reinforces understanding of data dynamics and relationships.
Thus, with the use of LEGO bricks in teaching data visualization, learners participate in the improvement of the interpretation of data sets. Building and changing LEGO models strengthens the learners’ visualization skills and fosters creativity, collaboration, and critical thinking. Students are prepared to deal with real-life data analysis challenges. It makes the learning process in the classroom more engaging and purposeful in terms of students learning about data visualization.},
note = {2025-07},
keywords = {data visualization, storytelling},
pubstate = {published},
tppubtype = {inproceedings}
}
Complex datasets must be communicated clearly, and data visualization helps achieve this. Bar charts and line graphs are effective but often fail to illustrate deeper relationships, such as the “why” and “how.” This paper explores the use of LEGO bricks to enhance students data visualization skills. By constructing three-dimensional models, students develop a deeper understanding of complex structures and relationships in data while applying creativity. LEGO’s modularity enables students to build, modify, and explore patterns dynamically, fostering a hands-on learning experience.
Each LEGO brick can represent different data points, categories, or variables, with colors, sizes, and arrangements conveying specific metrics. This approach helps students grasp how data interrelates and how visualizations represent complex patterns. Traditional visualizations often oversimplify relationships, whereas LEGO-based models allow for interactive exploration.
For example, consider a dataset displaying monthly sales performance across regions. Typically, students would create bar charts or line graphs, which condense data effectively but fail to reveal underlying connections. Instead, using LEGO bricks, students assign colors to regions and stack bricks to indicate sales volume per month. Tall red bricks could signify high sales, while shorter green bricks represent lower sales. As they adjust the model, students observe how sales evolve over time and across regions, making the data more tangible and engaging than static charts.
LEGO-based visualizations provide a dynamic method for modeling data. Students can add or remove bricks to reflect changes in sales, testing different scenarios. This interactivity helps learners explore how datasets shift and how different factors influence outcomes. Unlike static charts, which can be abstract, LEGO models enable students to physically manipulate data, reinforcing comprehension.
Additionally, LEGO's three-dimensional nature enhances students’ understanding of relationships within datasets. By arranging bricks spatially, they can highlight trends, value comparisons, and anomalies that might be harder to identify in two-dimensional graphs. Stacking bricks over time reveals trends, while spatial positioning shows regional correlations. This encourages deeper analytical thinking and effective communication of complex ideas.
Indeed, because LEGOs are accessible, students from different contexts are able to collaborate and participate in discussions. Collaboration among students assists them in improving their visualizations and analyzing the data from different angles.
Furthermore, LEGO-based exercises allow students to simulate different scenarios. For instance, to analyze the impact of a marketing campaign, students can modify the LEGO model to reflect sales growth, visually testing hypotheses in real-time. This hands-on experimentation reinforces understanding of data dynamics and relationships.
Thus, with the use of LEGO bricks in teaching data visualization, learners participate in the improvement of the interpretation of data sets. Building and changing LEGO models strengthens the learners’ visualization skills and fosters creativity, collaboration, and critical thinking. Students are prepared to deal with real-life data analysis challenges. It makes the learning process in the classroom more engaging and purposeful in terms of students learning about data visualization.
Each LEGO brick can represent different data points, categories, or variables, with colors, sizes, and arrangements conveying specific metrics. This approach helps students grasp how data interrelates and how visualizations represent complex patterns. Traditional visualizations often oversimplify relationships, whereas LEGO-based models allow for interactive exploration.
For example, consider a dataset displaying monthly sales performance across regions. Typically, students would create bar charts or line graphs, which condense data effectively but fail to reveal underlying connections. Instead, using LEGO bricks, students assign colors to regions and stack bricks to indicate sales volume per month. Tall red bricks could signify high sales, while shorter green bricks represent lower sales. As they adjust the model, students observe how sales evolve over time and across regions, making the data more tangible and engaging than static charts.
LEGO-based visualizations provide a dynamic method for modeling data. Students can add or remove bricks to reflect changes in sales, testing different scenarios. This interactivity helps learners explore how datasets shift and how different factors influence outcomes. Unlike static charts, which can be abstract, LEGO models enable students to physically manipulate data, reinforcing comprehension.
Additionally, LEGO's three-dimensional nature enhances students’ understanding of relationships within datasets. By arranging bricks spatially, they can highlight trends, value comparisons, and anomalies that might be harder to identify in two-dimensional graphs. Stacking bricks over time reveals trends, while spatial positioning shows regional correlations. This encourages deeper analytical thinking and effective communication of complex ideas.
Indeed, because LEGOs are accessible, students from different contexts are able to collaborate and participate in discussions. Collaboration among students assists them in improving their visualizations and analyzing the data from different angles.
Furthermore, LEGO-based exercises allow students to simulate different scenarios. For instance, to analyze the impact of a marketing campaign, students can modify the LEGO model to reflect sales growth, visually testing hypotheses in real-time. This hands-on experimentation reinforces understanding of data dynamics and relationships.
Thus, with the use of LEGO bricks in teaching data visualization, learners participate in the improvement of the interpretation of data sets. Building and changing LEGO models strengthens the learners’ visualization skills and fosters creativity, collaboration, and critical thinking. Students are prepared to deal with real-life data analysis challenges. It makes the learning process in the classroom more engaging and purposeful in terms of students learning about data visualization.
Ramos-Romero, Francisco; Trilles-Oliver, Sergio
ENHANCE STUDENTS DATA VISUALIZATION SKILLS IN THE CLASSROOM WITH LEGO BRICKLINK Proceedings Article
In: EDULEARN25 Proceedings, pp. 9878, IATED, 2025, ISBN: 978-84-09-74218-9, (2025-08).
Abstract | Links | BibTeX | Tags: data visualization, storytelling
@inproceedings{Ramos2025b,
title = {ENHANCE STUDENTS DATA VISUALIZATION SKILLS IN THE CLASSROOM WITH LEGO BRICKLINK},
author = {Francisco Ramos-Romero and Sergio Trilles-Oliver},
doi = {https://doi.org/10.21125/edulearn.2025.2568},
isbn = {978-84-09-74218-9},
year = {2025},
date = {2025-07-01},
urldate = {2025-07-01},
booktitle = {EDULEARN25 Proceedings},
pages = {9878},
publisher = {IATED},
abstract = {In general, effective data visualization is a critical skill at any level, traditional methods such as bar charts and line graphs can sometimes fall short in helping us to understand complex relationships within data. This study explores the use of LEGO bricks, specifically through LEGO BrickLink Studio, as an innovative tool to address this challenge and enhance students data visualization skills.
In this work, we are focused on the improvement of students data visualization skills by using LEGO bricks with LEGO BrickLink Studio. The activity is centered on students visualizing sales performance in various product categories over three years: 2018, 2019, 2020. Students analyze the sales data by creating interactive 3D models on LEGO BrickLink digital platform. For example, students are accustomed to viewing sales data in fully visualized static formats such as bar and line graphs. Though these formats are effective, they tend to hide the more intricate interrelationships between data points. The use of a collaborative digital environment such as LEGO BrickLink helps students to interactively transform the data into a tangible form.
In our experiment, students portray different product categories, which include electronics, clothing, home appliances, and beauty, each for three years. Students create digital models using LEGO BrickLink Studio wherein the dimensions and color of the model represent the sales volume for each category during a particular year. With this, students are able to actively participate and interact with the data as they modify the quantitative proportions visually over time, which is significantly more engaging than working with the 2D graphs.
The LEGO BrickLink shared environment enables the students to work together, exchange models, and test different hypotheses while interpreting data. Collaboration is facilitated through the online platform where students can create complex visualizations, compare their own understanding of the data, and collaborate in creating dynamic visual models. Through collaboration, besides learning how to interpret trends, outliers, and patterns in the dataset, students also develop critical thinking and problem-solving skills through collaborative interaction.
Also, while designing with LEGO BrickLink, learners can experiment with means of portraying and communicating information in creative ways. Because the platform is very flexible, learners can experiment with different modes of representation, such as changing brick size and ordering to represent patterns of sales, predict sales, or graph anomalies by product type. This hands-on method fosters a closer relationship with information and its actual business application, and also with the technical, analytical, and teamwork skills of the students.
Lastly, using LEGO BrickLink Studio in the classroom allows students to improve their data visualization ability, their understanding of complex data sets, and their working ability in a team-based online platform. Using this tool, there is a playfully fun and easy manner through which students are able to interact with data that traditional 2D graphs and charts are not capable of competing with.},
note = {2025-08},
keywords = {data visualization, storytelling},
pubstate = {published},
tppubtype = {inproceedings}
}
In general, effective data visualization is a critical skill at any level, traditional methods such as bar charts and line graphs can sometimes fall short in helping us to understand complex relationships within data. This study explores the use of LEGO bricks, specifically through LEGO BrickLink Studio, as an innovative tool to address this challenge and enhance students data visualization skills.
In this work, we are focused on the improvement of students data visualization skills by using LEGO bricks with LEGO BrickLink Studio. The activity is centered on students visualizing sales performance in various product categories over three years: 2018, 2019, 2020. Students analyze the sales data by creating interactive 3D models on LEGO BrickLink digital platform. For example, students are accustomed to viewing sales data in fully visualized static formats such as bar and line graphs. Though these formats are effective, they tend to hide the more intricate interrelationships between data points. The use of a collaborative digital environment such as LEGO BrickLink helps students to interactively transform the data into a tangible form.
In our experiment, students portray different product categories, which include electronics, clothing, home appliances, and beauty, each for three years. Students create digital models using LEGO BrickLink Studio wherein the dimensions and color of the model represent the sales volume for each category during a particular year. With this, students are able to actively participate and interact with the data as they modify the quantitative proportions visually over time, which is significantly more engaging than working with the 2D graphs.
The LEGO BrickLink shared environment enables the students to work together, exchange models, and test different hypotheses while interpreting data. Collaboration is facilitated through the online platform where students can create complex visualizations, compare their own understanding of the data, and collaborate in creating dynamic visual models. Through collaboration, besides learning how to interpret trends, outliers, and patterns in the dataset, students also develop critical thinking and problem-solving skills through collaborative interaction.
Also, while designing with LEGO BrickLink, learners can experiment with means of portraying and communicating information in creative ways. Because the platform is very flexible, learners can experiment with different modes of representation, such as changing brick size and ordering to represent patterns of sales, predict sales, or graph anomalies by product type. This hands-on method fosters a closer relationship with information and its actual business application, and also with the technical, analytical, and teamwork skills of the students.
Lastly, using LEGO BrickLink Studio in the classroom allows students to improve their data visualization ability, their understanding of complex data sets, and their working ability in a team-based online platform. Using this tool, there is a playfully fun and easy manner through which students are able to interact with data that traditional 2D graphs and charts are not capable of competing with.
In this work, we are focused on the improvement of students data visualization skills by using LEGO bricks with LEGO BrickLink Studio. The activity is centered on students visualizing sales performance in various product categories over three years: 2018, 2019, 2020. Students analyze the sales data by creating interactive 3D models on LEGO BrickLink digital platform. For example, students are accustomed to viewing sales data in fully visualized static formats such as bar and line graphs. Though these formats are effective, they tend to hide the more intricate interrelationships between data points. The use of a collaborative digital environment such as LEGO BrickLink helps students to interactively transform the data into a tangible form.
In our experiment, students portray different product categories, which include electronics, clothing, home appliances, and beauty, each for three years. Students create digital models using LEGO BrickLink Studio wherein the dimensions and color of the model represent the sales volume for each category during a particular year. With this, students are able to actively participate and interact with the data as they modify the quantitative proportions visually over time, which is significantly more engaging than working with the 2D graphs.
The LEGO BrickLink shared environment enables the students to work together, exchange models, and test different hypotheses while interpreting data. Collaboration is facilitated through the online platform where students can create complex visualizations, compare their own understanding of the data, and collaborate in creating dynamic visual models. Through collaboration, besides learning how to interpret trends, outliers, and patterns in the dataset, students also develop critical thinking and problem-solving skills through collaborative interaction.
Also, while designing with LEGO BrickLink, learners can experiment with means of portraying and communicating information in creative ways. Because the platform is very flexible, learners can experiment with different modes of representation, such as changing brick size and ordering to represent patterns of sales, predict sales, or graph anomalies by product type. This hands-on method fosters a closer relationship with information and its actual business application, and also with the technical, analytical, and teamwork skills of the students.
Lastly, using LEGO BrickLink Studio in the classroom allows students to improve their data visualization ability, their understanding of complex data sets, and their working ability in a team-based online platform. Using this tool, there is a playfully fun and easy manner through which students are able to interact with data that traditional 2D graphs and charts are not capable of competing with.
Vidanelage, Upeksha Indeewari Edirisooriya Kirihami; van Vlient, Mark; Casteleyn, Sven; Granell-Canut, Carlos; Ronzhin, Stanislav; Lemmens, Rob
Knowledge extraction and footprint generation using the GeoSpace Body of Knowledge Proceedings Article
In: AGILE GIScience Series (Proceedings of the 28th AGILE Conference on Geographic Information Science), pp. 48, Copernicus Publications, 2025, (2025-05).
Abstract | Links | BibTeX | Tags: Body of Knowledge, education, GIScience, SpaceSUITE
@inproceedings{Upeksha2025a,
title = {Knowledge extraction and footprint generation using the GeoSpace Body of Knowledge},
author = {Upeksha Indeewari Edirisooriya Kirihami Vidanelage and Mark van Vlient and Sven Casteleyn and Carlos Granell-Canut and Stanislav Ronzhin and Rob Lemmens},
doi = {https://doi.org/10.5194/agile-giss-6-48-2025},
year = {2025},
date = {2025-06-15},
urldate = {2025-06-15},
booktitle = {AGILE GIScience Series (Proceedings of the 28th AGILE Conference on Geographic Information Science)},
volume = {6},
pages = {48},
publisher = {Copernicus Publications},
abstract = {Knowledge footprints are visualisations of personal and organisational expertise. They can be used for capturing, sharing and matching expertise in the context of promotion, research exposure, project collaboration, etc. We have developed a method for creating footprints in the geospatial domain, based on resources created by persons and organisations and using the GeoSpace Body of Knowledge as a shared, standardised vocabulary. We deployed an NLP-based keyword extraction method to annotate resources with GeoSpace BoK concepts and constructed a knowledge graph to connect these BoK concepts to personal or organisational profiles. Footprints are then created by querying the knowledge graph and visualizing the results. Initial tests have been carried out to validate the generated footprints.},
note = {2025-05},
keywords = {Body of Knowledge, education, GIScience, SpaceSUITE},
pubstate = {published},
tppubtype = {inproceedings}
}
Knowledge footprints are visualisations of personal and organisational expertise. They can be used for capturing, sharing and matching expertise in the context of promotion, research exposure, project collaboration, etc. We have developed a method for creating footprints in the geospatial domain, based on resources created by persons and organisations and using the GeoSpace Body of Knowledge as a shared, standardised vocabulary. We deployed an NLP-based keyword extraction method to annotate resources with GeoSpace BoK concepts and constructed a knowledge graph to connect these BoK concepts to personal or organisational profiles. Footprints are then created by querying the knowledge graph and visualizing the results. Initial tests have been carried out to validate the generated footprints.
Monteiro-Fialho, Leonardo; Cueto-Rubio, Enrique; Granell-Canut, Carlos; Trilles-Oliver, Sergio
Transportation Analytics Using Smart Card Data: A Systematic Review Journal Article
In: IEEE Transactions on Intelligent Transportation Systems, vol. 26, iss. 7, pp. 11010-11033, 2025, ISSN: 1558-0016, (2025-10).
Abstract | Links | BibTeX | Tags: public transport, smart data card
@article{Monteiro2025a,
title = {Transportation Analytics Using Smart Card Data: A Systematic Review},
author = {Leonardo Monteiro-Fialho and Enrique Cueto-Rubio and Carlos Granell-Canut and Sergio Trilles-Oliver},
doi = {http://dx.doi.org/10.1109/TITS.2025.3571101},
issn = {1558-0016},
year = {2025},
date = {2025-06-03},
urldate = {2025-06-03},
journal = {IEEE Transactions on Intelligent Transportation Systems},
volume = {26},
issue = {7},
pages = {11010-11033},
abstract = {The widespread adoption of smart card technology in mobility services, particularly in public transportation, as well as in car and bike sharing systems, has opened up new avenues for transportation service providers to gain insights into passenger travel behaviors. Smart card data offers a rich source of information on passenger trips, enabling a wide range of transportation analytics applications, including operator performance monitoring, demand modeling, and travel behavior analysis. This systematic mapping review aims to comprehensively examine the current state-of-the-art in leveraging smart cards for analytical studies applied to public transportation research. The review focuses on identifying and analyzing the main analytical purposes, methods, techniques, datasets, and trends used in these studies. The findings of this review provide valuable insights into the current research landscape of smart card data for public transport and highlight potential knowledge gaps that warrant further research.},
note = {2025-10},
keywords = {public transport, smart data card},
pubstate = {published},
tppubtype = {article}
}
The widespread adoption of smart card technology in mobility services, particularly in public transportation, as well as in car and bike sharing systems, has opened up new avenues for transportation service providers to gain insights into passenger travel behaviors. Smart card data offers a rich source of information on passenger trips, enabling a wide range of transportation analytics applications, including operator performance monitoring, demand modeling, and travel behavior analysis. This systematic mapping review aims to comprehensively examine the current state-of-the-art in leveraging smart cards for analytical studies applied to public transportation research. The review focuses on identifying and analyzing the main analytical purposes, methods, techniques, datasets, and trends used in these studies. The findings of this review provide valuable insights into the current research landscape of smart card data for public transport and highlight potential knowledge gaps that warrant further research.
Serra, Laura; Juan-Verdoy, Pablo; Díaz-Avalos, Carlos; Aragó-Galindo, Pau; Chaudhuri, Somnath; Trilles-Oliver, Sergio
In: Environmental Monitoring and Assessment, vol. 197, no. 619, 2025, ISSN: 1573-2959, (2025-12).
Abstract | Links | BibTeX | Tags: forest fire, multivariate analysis
@article{Serra2025a,
title = {Classification of wildfires in relation to land cover types and associated variables by applying cluster analysis: a case study in the Iberian Peninsula},
author = {Laura Serra and Pablo Juan-Verdoy and Carlos Díaz-Avalos and Pau Aragó-Galindo and Somnath Chaudhuri and Sergio Trilles-Oliver},
doi = {https://doi.org/10.1007/s10661-025-14053-y},
issn = {1573-2959},
year = {2025},
date = {2025-05-03},
urldate = {2025-05-03},
journal = {Environmental Monitoring and Assessment},
volume = {197},
number = {619},
abstract = {Wildfires are a major environmental problem that have both economic and ecological impacts. Wildfires typically spread in a particular pattern, determined by factors such as the elements on the ground that catch fire or their geographic location. This study reports and discusses how wildfires in the Valencian Community, Spain, have been spatially grouped in recent years (from 2016 to 2020). It also characterizes each cluster in terms of location and land cover. An exploratory analysis of the environmental variables associated with wildfires has been conducted using finite Gaussian mixture models in R (R package mclust). The primary findings can be used to better understand the types of wildfires that occur in individual spatial zones. Some interesting cluster patterns in specific geographical areas, such as river basins, have also been reported. The method can identify clusters of fires by detecting areas with similar characteristics at the land use level. It also allows for the implementation of measures aimed at reducing the impacts of wildfires and can help in the extinction of wildfires based on the characteristics of all the fires grouped using spatial and land cover dimensions.},
note = {2025-12},
keywords = {forest fire, multivariate analysis},
pubstate = {published},
tppubtype = {article}
}
Wildfires are a major environmental problem that have both economic and ecological impacts. Wildfires typically spread in a particular pattern, determined by factors such as the elements on the ground that catch fire or their geographic location. This study reports and discusses how wildfires in the Valencian Community, Spain, have been spatially grouped in recent years (from 2016 to 2020). It also characterizes each cluster in terms of location and land cover. An exploratory analysis of the environmental variables associated with wildfires has been conducted using finite Gaussian mixture models in R (R package mclust). The primary findings can be used to better understand the types of wildfires that occur in individual spatial zones. Some interesting cluster patterns in specific geographical areas, such as river basins, have also been reported. The method can identify clusters of fires by detecting areas with similar characteristics at the land use level. It also allows for the implementation of measures aimed at reducing the impacts of wildfires and can help in the extinction of wildfires based on the characteristics of all the fires grouped using spatial and land cover dimensions.
Del-Coco, Marco; Carcagni, Pierluigi; Trilles-Oliver, Sergio; Iskandaryan, Ditsuhi; Leo, Marco
The Role of AI in Smart Mobility: A Comprehensive Survey Journal Article
In: Electronics, vol. 14, iss. 9, pp. 1801, 2025, ISSN: 2079-9292, (2025-09).
Abstract | Links | BibTeX | Tags: public transport
@article{DelCoco2025a,
title = {The Role of AI in Smart Mobility: A Comprehensive Survey},
author = {Marco Del-Coco and Pierluigi Carcagni and Sergio Trilles-Oliver and Ditsuhi Iskandaryan and Marco Leo},
doi = {https://doi.org/10.3390/electronics14091801},
issn = {2079-9292},
year = {2025},
date = {2025-04-28},
urldate = {2025-04-28},
journal = {Electronics},
volume = {14},
issue = {9},
pages = {1801},
abstract = {The advancement in Artificial Intelligence, particularly the application of deep learning methodologies, has allowed for the implementation of modern smart transportation systems, which are making the driver experience increasingly reliable and safe. Unfortunately, a literature review revealed that no survey paper provides a collective overview of all the machine learning applications involved in smart transportation systems. To fill this gap, this paper provides a discussion on the role and advancement of deep learning methodologies in all the smart mobility aspects, highlighting their mutual dependencies. To this end, three key pillar areas are considered: smart vehicles, smart planning, and vehicle network and security. In each area, the subtasks commonly addressed by machine learning are pointed out, and state-of-the-art techniques are reviewed, with a final discussion about advancements according to recent findings in machine learning.},
note = {2025-09},
keywords = {public transport},
pubstate = {published},
tppubtype = {article}
}
The advancement in Artificial Intelligence, particularly the application of deep learning methodologies, has allowed for the implementation of modern smart transportation systems, which are making the driver experience increasingly reliable and safe. Unfortunately, a literature review revealed that no survey paper provides a collective overview of all the machine learning applications involved in smart transportation systems. To fill this gap, this paper provides a discussion on the role and advancement of deep learning methodologies in all the smart mobility aspects, highlighting their mutual dependencies. To this end, three key pillar areas are considered: smart vehicles, smart planning, and vehicle network and security. In each area, the subtasks commonly addressed by machine learning are pointed out, and state-of-the-art techniques are reviewed, with a final discussion about advancements according to recent findings in machine learning.
González-Mora, César; Garrigós, Irene; Casteleyn, Sven; Firmenich, Sergio
Augmenting Websites with Voice Commands: An Approach Focused on Accessibility Journal Article
In: Journal of Web Engineering, vol. 24, no. 2, pp. 163–198, 2025, ISSN: 1544-5976, (2025-11).
Abstract | Links | BibTeX | Tags: voice interaction, web accessibility
@article{González-Mora2025a,
title = {Augmenting Websites with Voice Commands: An Approach Focused on Accessibility},
author = {César González-Mora and Irene Garrigós and Sven Casteleyn and Sergio Firmenich},
doi = {ttps://doi.org/10.13052/jwe1540-9589.2421},
issn = {1544-5976},
year = {2025},
date = {2025-04-23},
urldate = {2025-04-23},
journal = {Journal of Web Engineering},
volume = {24},
number = {2},
pages = {163–198},
abstract = {Even now, users with disabilities encounter serious barriers when accessing the Web. In particular, blind and visually impaired users encounter difficulties browsing and reading the contents of a website. Screen readers provide some assistance, yet, as they are unable to interpret the Web structure, they summarise information and read specific labelled fragments. Therefore, the overall comprehension of the text remains challenging. In this sense, in order to improve the accessibility of websites on the fly, we propose a Web augmentation framework for accessibility (WAFRA). Our framework uses Web augmentation techniques that extend the website with voice interaction and new actions: label text fragments, read aloud these fragments, facilitate navigation, increase font size and show videos. In order to perform this accessibility improvement, we automatically provide annotations from DBPedia regarding important information for end users. Moreover, we also provide the option that intermediary users add new annotations for labelling or including more specific information, which can be shared with other users by crowdsourcing. The evaluation of the framework shows its usefulness to ease website access for users with visual disabilities compared to using screen readers.},
note = {2025-11},
keywords = {voice interaction, web accessibility},
pubstate = {published},
tppubtype = {article}
}
Even now, users with disabilities encounter serious barriers when accessing the Web. In particular, blind and visually impaired users encounter difficulties browsing and reading the contents of a website. Screen readers provide some assistance, yet, as they are unable to interpret the Web structure, they summarise information and read specific labelled fragments. Therefore, the overall comprehension of the text remains challenging. In this sense, in order to improve the accessibility of websites on the fly, we propose a Web augmentation framework for accessibility (WAFRA). Our framework uses Web augmentation techniques that extend the website with voice interaction and new actions: label text fragments, read aloud these fragments, facilitate navigation, increase font size and show videos. In order to perform this accessibility improvement, we automatically provide annotations from DBPedia regarding important information for end users. Moreover, we also provide the option that intermediary users add new annotations for labelling or including more specific information, which can be shared with other users by crowdsourcing. The evaluation of the framework shows its usefulness to ease website access for users with visual disabilities compared to using screen readers.
Chukhno, Nadezhda; Bravenec, Tomás; Díez-González, Javier; Trilles-Oliver, Sergio; Torres-Sospedra, Joaquín; Iera, Antonio; Araniti, Giuseppe
Are D2D and RIS in the same league? Cooperative RSSI-based localization model and performance comparison Journal Article
In: Ad Hoc Networks, vol. 175, pp. 103862, 2025, ISSN: 1570-8705, (2025-04).
Abstract | Links | BibTeX | Tags: A-wear, cellular networks, Sidelink
@article{Chukhno2025a,
title = {Are D2D and RIS in the same league? Cooperative RSSI-based localization model and performance comparison},
author = {Nadezhda Chukhno and Tomás Bravenec and Javier Díez-González and Sergio Trilles-Oliver and Joaquín Torres-Sospedra and Antonio Iera and Giuseppe Araniti},
doi = {https://doi.org/10.1016/j.adhoc.2025.103862},
issn = {1570-8705},
year = {2025},
date = {2025-04-20},
urldate = {2025-04-20},
journal = {Ad Hoc Networks},
volume = {175},
pages = {103862},
publisher = {Elsevier},
abstract = {The next generation of high-accuracy positioning services is required to satisfy the sub-meter accuracy level for more than 95% of the network area, including indoor, outdoor, and urban deployments. In this vein, inter-agent measurements appear to provide additional position information and, hence, have the capacity to boost localization accuracy. This paper researches cooperative positioning techniques by means of device-to-device (D2D) and reconfigurable intelligent surfaces (RIS) technologies leveraging received signal strength (RSS) based ranging. We estimate the maximum capacities of the positioning systems in terms of accuracy through the Gaussian noise model, proposed universal theoretical distance-dependent noise model, and empirical noise model. We also evaluate the positioning error achieved by combining two or more technologies. Numerical results reveal the use cases advantageous for RIS- and D2D-aided localization. Then, based on the results, valuable guidelines are derived on the optimal sensor fusion metric – median – that minimizes the mean error of the cooperative localization.},
note = {2025-04},
keywords = {A-wear, cellular networks, Sidelink},
pubstate = {published},
tppubtype = {article}
}
The next generation of high-accuracy positioning services is required to satisfy the sub-meter accuracy level for more than 95% of the network area, including indoor, outdoor, and urban deployments. In this vein, inter-agent measurements appear to provide additional position information and, hence, have the capacity to boost localization accuracy. This paper researches cooperative positioning techniques by means of device-to-device (D2D) and reconfigurable intelligent surfaces (RIS) technologies leveraging received signal strength (RSS) based ranging. We estimate the maximum capacities of the positioning systems in terms of accuracy through the Gaussian noise model, proposed universal theoretical distance-dependent noise model, and empirical noise model. We also evaluate the positioning error achieved by combining two or more technologies. Numerical results reveal the use cases advantageous for RIS- and D2D-aided localization. Then, based on the results, valuable guidelines are derived on the optimal sensor fusion metric – median – that minimizes the mean error of the cooperative localization.
Hammad, Sahibzada Saadoon; Trilles-Oliver, Sergio
Anomaly Detection for Trust Management in Internet of Things Systems Proceedings Article
In: Distributed Computing and Artificial Intelligence, Special Sessions II, 21st International Conference, Springer, Cham, 2025, ISBN: 978-3-031-80946-0, (2025-02).
Abstract | Links | BibTeX | Tags: Anomaly detection, Internet of things, machine learning
@inproceedings{Saadoon2025a,
title = {Anomaly Detection for Trust Management in Internet of Things Systems},
author = {Sahibzada Saadoon Hammad and Sergio Trilles-Oliver},
doi = {10.1007/978-3-031-80946-0_29},
isbn = {978-3-031-80946-0},
year = {2025},
date = {2025-03-15},
urldate = {2025-03-15},
booktitle = {Distributed Computing and Artificial Intelligence, Special Sessions II, 21st International Conference},
volume = {1151},
publisher = {Springer, Cham},
series = {Lecture Notes in Networks and Systems},
abstract = {The fast growth of Internet of Things systems has transformed the way policy decisions are made based on the data produced by these devices. These data are prone to errors and anomalies and can present privacy and security issues which can affect policy decisions. Therefore, it is necessary that, at each layer of Internet of Things architecture, the data undergo a process to ensure its quality. This paper presents a framework for building a trust management system for Internet of Things devices using anomaly detection in different layers of IoT architecture and formulation of a reputation index.},
note = {2025-02},
keywords = {Anomaly detection, Internet of things, machine learning},
pubstate = {published},
tppubtype = {inproceedings}
}
The fast growth of Internet of Things systems has transformed the way policy decisions are made based on the data produced by these devices. These data are prone to errors and anomalies and can present privacy and security issues which can affect policy decisions. Therefore, it is necessary that, at each layer of Internet of Things architecture, the data undergo a process to ensure its quality. This paper presents a framework for building a trust management system for Internet of Things devices using anomaly detection in different layers of IoT architecture and formulation of a reputation index.
Alonso-Olea, Iratxe; Díaz-Sanahuja, Laura; Casteleyn, Sven; Granell-Canut, Carlos; Bretón-López, Juana
Diseño preliminar y caso de uso de la aplicación Symptoms-JIT: una app para la exposición en vivo en trastornos de ansiedad Journal Article
In: Àgora de salut, vol. 11, pp. 111-121, 2025, ISSN: 2443-9827, (2025-01).
Abstract | Links | BibTeX | Tags: symptoms
@article{Alonso2025a,
title = {Diseño preliminar y caso de uso de la aplicación Symptoms-JIT: una app para la exposición en vivo en trastornos de ansiedad},
author = {Iratxe Alonso-Olea and Laura Díaz-Sanahuja and Sven Casteleyn and Carlos Granell-Canut and Juana Bretón-López},
url = {http://hdl.handle.net/10234/745532},
doi = {10.6035/AgoraSalut.2025.11.11},
issn = {2443-9827},
year = {2025},
date = {2025-02-01},
urldate = {2025-02-01},
journal = {Àgora de salut},
volume = {11},
pages = {111-121},
publisher = {Facultat de Ciències de la Salut, Universitat Jaume I},
abstract = {Un gran número de personas en el mundo sufre algún trastorno de ansiedad y si no recibe tratamiento el trastorno tiende a cronificarse, afectando a su salud y calidad de vida. La terapia cognitivo-conductual (TCC) es el tratamiento de elección, siendo el componente principal la exposición en vivo; sin embargo, esta no está exenta de dificultades. Las tecnologías pueden ayudar a su implementación. El objetivo del presente estudio es el diseño del contenido preliminar de la app Symptoms-Jit adaptado a un caso de uso en particular. Se trata de una app para teléfonos móviles basada en la TCC y las intervenciones just in time que maximiza la eficacia de la exposición en vivo en los trastornos de ansiedad. El caso de uso descrito consiste en un trastorno de agorafobia que podrá realizar el componente de exposición acompañado por la app. Se decidió plantear dos flujos distintos: uno en el que la situación de exposición se desarrolla de forma adecuada y otro en el que el paciente presenta ciertas dificultades (p. ej., tiene un pico de ansiedad muy elevado y/o necesita ayuda, realiza un escape o una evitación). La app cuenta con vídeos, infografías y notificaciones que van guiando la experiencia del usuario. Symptoms-Jit se muestra como un proyecto prometedor en el avance del uso de las tecnologías en las intervenciones psico lógicas, acercando los últimos avances científicos a la práctica clínica, cubriendo el vacío actual respecto al uso de todas las capacidades de los smartphones y yendo más allá de un mero contenido psicoeducativo. },
note = {2025-01},
keywords = {symptoms},
pubstate = {published},
tppubtype = {article}
}
Un gran número de personas en el mundo sufre algún trastorno de ansiedad y si no recibe tratamiento el trastorno tiende a cronificarse, afectando a su salud y calidad de vida. La terapia cognitivo-conductual (TCC) es el tratamiento de elección, siendo el componente principal la exposición en vivo; sin embargo, esta no está exenta de dificultades. Las tecnologías pueden ayudar a su implementación. El objetivo del presente estudio es el diseño del contenido preliminar de la app Symptoms-Jit adaptado a un caso de uso en particular. Se trata de una app para teléfonos móviles basada en la TCC y las intervenciones just in time que maximiza la eficacia de la exposición en vivo en los trastornos de ansiedad. El caso de uso descrito consiste en un trastorno de agorafobia que podrá realizar el componente de exposición acompañado por la app. Se decidió plantear dos flujos distintos: uno en el que la situación de exposición se desarrolla de forma adecuada y otro en el que el paciente presenta ciertas dificultades (p. ej., tiene un pico de ansiedad muy elevado y/o necesita ayuda, realiza un escape o una evitación). La app cuenta con vídeos, infografías y notificaciones que van guiando la experiencia del usuario. Symptoms-Jit se muestra como un proyecto prometedor en el avance del uso de las tecnologías en las intervenciones psico lógicas, acercando los últimos avances científicos a la práctica clínica, cubriendo el vacío actual respecto al uso de todas las capacidades de los smartphones y yendo más allá de un mero contenido psicoeducativo.
2024
Din, Teodor Constatin; Matey-Sanz, Miguel; Bautista, Adrian; Trilles-Oliver, Sergio; Torres-Sospedra, Joaquín
Feasibility Analysis of Self-Oriented BLE Anchors Powered by NEMA Motors for DoA-based Indoor Positioning Proceedings Article
In: 6th International Congress on Ultra Modern Telecommunications and Control Systems and Workshops (ICUMT 2024), pp. 149-154, IEEE, 2024, ISBN: 978-3-8007-6544-7, (2024-19).
Abstract | Links | BibTeX | Tags: Antennas, Indoor localization, Indoor positioning
@inproceedings{Din2024b,
title = {Feasibility Analysis of Self-Oriented BLE Anchors Powered by NEMA Motors for DoA-based Indoor Positioning},
author = {Teodor Constatin Din and Miguel Matey-Sanz and Adrian Bautista and Sergio Trilles-Oliver and Joaquín Torres-Sospedra},
url = {https://ieeexplore.ieee.org/abstract/document/11048828},
isbn = {978-3-8007-6544-7},
year = {2024},
date = {2024-12-01},
urldate = {2024-12-01},
booktitle = {6th International Congress on Ultra Modern Telecommunications and Control Systems and Workshops (ICUMT 2024)},
pages = {149-154},
publisher = {IEEE},
abstract = {Indoor positioning systems (IPS) are widely used in various scenarios, utilizing fingerprinting, Bluetooth, or Wi-Fi technologies. However, the current infrastructure for indoor positioning is insufficient and lacks consistency over time due to environmental changes and other factors. This lack of adaptability to dynamic environments poses a significant challenge in indoor localization today. A fresh perspective is required to address these issues, emphasizing the need for dynamic and adaptable devices. Unfortunately, development efforts have primarily focused on fingerprinting algorithms and artificial intelligence models, overlooking the potential of adaptable hardware solutions. This paper presents an analysis of a novel dynamic antenna setup designed to adapt to changing environments, providing an enhanced indoor positioning solution based on Bluetooth Low Energy (BLE) and Direction-of-Arrival (DoA) technology. The goal is to evaluate and improve upon a previous design, reduce the error, and enhance the feasibility, thus providing an accurate position of the moving device in many conditions for different scenarios. This approach provides a solution for positioning and coverage and an evolving solution over time that can adapt to other systems in continuously changing environments.},
note = {2024-19},
keywords = {Antennas, Indoor localization, Indoor positioning},
pubstate = {published},
tppubtype = {inproceedings}
}
Indoor positioning systems (IPS) are widely used in various scenarios, utilizing fingerprinting, Bluetooth, or Wi-Fi technologies. However, the current infrastructure for indoor positioning is insufficient and lacks consistency over time due to environmental changes and other factors. This lack of adaptability to dynamic environments poses a significant challenge in indoor localization today. A fresh perspective is required to address these issues, emphasizing the need for dynamic and adaptable devices. Unfortunately, development efforts have primarily focused on fingerprinting algorithms and artificial intelligence models, overlooking the potential of adaptable hardware solutions. This paper presents an analysis of a novel dynamic antenna setup designed to adapt to changing environments, providing an enhanced indoor positioning solution based on Bluetooth Low Energy (BLE) and Direction-of-Arrival (DoA) technology. The goal is to evaluate and improve upon a previous design, reduce the error, and enhance the feasibility, thus providing an accurate position of the moving device in many conditions for different scenarios. This approach provides a solution for positioning and coverage and an evolving solution over time that can adapt to other systems in continuously changing environments.
Cid-Giménez, Judith; Quintana-Seguí, P.; Trilles-Oliver, Sergio; Clavera-Gispert, R.; Vilasis-Cardona, X.
Comparison of gap-filling methods for in situ soil moisture sensor time series data Proceedings Article
In: XXX Jornades de Meteorologia Eduard Fontserè, ACAM (Associació Catalana de Meteorologia), Barcelona, Spain, 2024, (2024-21).
Links | BibTeX | Tags: machine learning, Meteorology
@inproceedings{Cid2024a,
title = {Comparison of gap-filling methods for in situ soil moisture sensor time series data},
author = {Judith Cid-Giménez and P. Quintana-Seguí and Sergio Trilles-Oliver and R. Clavera-Gispert and X. Vilasis-Cardona},
url = {https://www.acam.cat/},
year = {2024},
date = {2024-11-24},
urldate = {2024-11-24},
booktitle = {XXX Jornades de Meteorologia Eduard Fontserè},
publisher = {ACAM (Associació Catalana de Meteorologia)},
address = {Barcelona, Spain},
note = {2024-21},
keywords = {machine learning, Meteorology},
pubstate = {published},
tppubtype = {inproceedings}
}
Ramos-Romero, Francisco; Trilles-Oliver, Sergio
FROM RAW DATA TO A DATA STORY BY USING LEGO PIECES Proceedings Article
In: ICERI2024 Proceedings, pp. 10526-10531, IATED, 2024, ISBN: 978-84-09-63010-3, (2024-18).
Abstract | Links | BibTeX | Tags: data visualization, storytelling
@inproceedings{Ramos2024b,
title = {FROM RAW DATA TO A DATA STORY BY USING LEGO PIECES},
author = {Francisco Ramos-Romero and Sergio Trilles-Oliver},
doi = {https://doi.org/10.21125/iceri.2024.2717},
isbn = {978-84-09-63010-3},
year = {2024},
date = {2024-11-11},
urldate = {2024-11-11},
booktitle = {ICERI2024 Proceedings},
pages = {10526-10531},
publisher = {IATED},
abstract = {The journey from raw data to a data story is a process including some stages. Data collection: You collect information to evaluate and comprehend its performance or behaviors. Data preparation: You clean, organize, and merge the data to make it ready for analysis. Data visualization: You create visual representations of the data to facilitate easier monitoring and understanding. Data analysis: You investigate the data to uncover meaningful insights for a specific audience and Data storytelling: You convey your insights through narratives and visuals to ensure they resonate and drive change. Data storytelling is the culmination of the multi-step process above commented. The quality of your data stories hinges on the effectiveness of each preceding step. If we don't tell the data story well, all the prior effort can be invalid. In this work, we are focused in the data visualization step by offering some alternatives to the typical charts and graphics solutions. In particular, we use LEGO pieces to reinforce the knowledge and to effectively use the existing data visualisation techniques.},
note = {2024-18},
keywords = {data visualization, storytelling},
pubstate = {published},
tppubtype = {inproceedings}
}
The journey from raw data to a data story is a process including some stages. Data collection: You collect information to evaluate and comprehend its performance or behaviors. Data preparation: You clean, organize, and merge the data to make it ready for analysis. Data visualization: You create visual representations of the data to facilitate easier monitoring and understanding. Data analysis: You investigate the data to uncover meaningful insights for a specific audience and Data storytelling: You convey your insights through narratives and visuals to ensure they resonate and drive change. Data storytelling is the culmination of the multi-step process above commented. The quality of your data stories hinges on the effectiveness of each preceding step. If we don't tell the data story well, all the prior effort can be invalid. In this work, we are focused in the data visualization step by offering some alternatives to the typical charts and graphics solutions. In particular, we use LEGO pieces to reinforce the knowledge and to effectively use the existing data visualisation techniques.
Matey-Sanz, Miguel
Human Activity Recognition with Consumer Devices and Real-Life Perspectives PhD Thesis
INIT, UJI, 2024, (2024-15).
Abstract | Links | BibTeX | Tags: activity recognition, machine learning, smartphone app, smartwatch
@phdthesis{Matey2024c,
title = {Human Activity Recognition with Consumer Devices and Real-Life Perspectives},
author = {Miguel Matey-Sanz},
doi = {http://dx.doi.org/10.6035/14101.2024.663821},
year = {2024},
date = {2024-10-30},
urldate = {2024-10-30},
school = {INIT, UJI},
abstract = {During the last decade, research on human activity recognition has grown due to its applications in diverse fields such as video surveillance, exercise monitoring or health monitoring systems. In the latter case, researchers are putting their efforts into using human activity recognition in monitoring elderly people, for example, for fall prevention and detection applications. Existing research usually has drawbacks regarding their requirements regarding sensing devices (e.g., cost, quantity, location). Therefore, research needs to keep these drawbacks in mind to have a real impact on society. This thesis addresses the abovementioned issue by focusing on the feasibility of the use of consumer devices such as smartphones and smartwatches, and cheap devices like microcontrollers, for human activity recognition and its application in real-life problems.},
note = {2024-15},
keywords = {activity recognition, machine learning, smartphone app, smartwatch},
pubstate = {published},
tppubtype = {phdthesis}
}
During the last decade, research on human activity recognition has grown due to its applications in diverse fields such as video surveillance, exercise monitoring or health monitoring systems. In the latter case, researchers are putting their efforts into using human activity recognition in monitoring elderly people, for example, for fall prevention and detection applications. Existing research usually has drawbacks regarding their requirements regarding sensing devices (e.g., cost, quantity, location). Therefore, research needs to keep these drawbacks in mind to have a real impact on society. This thesis addresses the abovementioned issue by focusing on the feasibility of the use of consumer devices such as smartphones and smartwatches, and cheap devices like microcontrollers, for human activity recognition and its application in real-life problems.
González-Pérez, Alberto; Díaz-Sanahuja, Laura; Matey-Sanz, Miguel; Osma, Jorge; Granell-Canut, Carlos; Bretón-López, Juana; Casteleyn, Sven
Towards a self-applied, mobile-based geolocated exposure therapy software for anxiety disorders: SyMptOMS-ET app Journal Article
In: Digital Health, vol. 10, pp. 1-17, 2024, ISBN: 2055-2076, (2024-13).
Abstract | Links | BibTeX | Tags: exposure therapy, mental health, mHealth, smartphone app
@article{Gonzalez-Perez2024a,
title = {Towards a self-applied, mobile-based geolocated exposure therapy software for anxiety disorders: SyMptOMS-ET app},
author = {Alberto González-Pérez and Laura Díaz-Sanahuja and Miguel Matey-Sanz and Jorge Osma and Carlos Granell-Canut and Juana Bretón-López and Sven Casteleyn},
doi = {https://doi.org/10.1177/20552076241283942},
isbn = {2055-2076},
year = {2024},
date = {2024-10-28},
urldate = {2024-10-28},
journal = {Digital Health},
volume = {10},
pages = {1-17},
publisher = {SAGE},
abstract = {Objective
While exposure therapy (ET) has the potential to help people tolerate intense situation-specific emotions and change avoidance behaviours, no smartphone solution exists to guide the process of in-vivo ET. A geolocation-based smartphone software component was designed and developed to instrumentalize patient guidance in in-vivo ET and its psychological validity was assessed by a group of independent psychology experts.
Methods
A team of computer scientists and psychologists developed the ET Component for in-vivo ET using geolocation-based technology, following the process-centred design methodology. The ET Component was integrated into the SyMptOMS-ET Android application, which was developed following the co-design methodology. Next, nine independent psychology experts tested and evaluated the ET Component and the SyMptOMS-ET app in the field, following the think-aloud methodology. Participants also completed the Mobile Application Rating Scale (MARS) instrument to quantitatively evaluate the solutions.
Results
We present the SyMptOMS-ET app’s main features and the ET Component exposure workflow. Next, we discuss the feedback obtained and the results of the MARS instrument. Participants who tested the app were satisfied with the ET Component during exposure scenarios (score of mu4.32 out of 5 [mu 0.28] on MARS quality aspects), agreed on the soundness of the theoretical foundations of the solutions developed (score of mu4.57 [mu0.48] on MARS treatment support aspects), and provided minor think-a-loud comments to improve them.
Conclusions
The results of the expert evaluation demonstrate the psychological validity of the ET Component and the SyMptOMS-ET app. However, further studies are needed to discern the acceptability and efficacy of the mHealth tool in the target population.},
note = {2024-13},
keywords = {exposure therapy, mental health, mHealth, smartphone app},
pubstate = {published},
tppubtype = {article}
}
Objective
While exposure therapy (ET) has the potential to help people tolerate intense situation-specific emotions and change avoidance behaviours, no smartphone solution exists to guide the process of in-vivo ET. A geolocation-based smartphone software component was designed and developed to instrumentalize patient guidance in in-vivo ET and its psychological validity was assessed by a group of independent psychology experts.
Methods
A team of computer scientists and psychologists developed the ET Component for in-vivo ET using geolocation-based technology, following the process-centred design methodology. The ET Component was integrated into the SyMptOMS-ET Android application, which was developed following the co-design methodology. Next, nine independent psychology experts tested and evaluated the ET Component and the SyMptOMS-ET app in the field, following the think-aloud methodology. Participants also completed the Mobile Application Rating Scale (MARS) instrument to quantitatively evaluate the solutions.
Results
We present the SyMptOMS-ET app’s main features and the ET Component exposure workflow. Next, we discuss the feedback obtained and the results of the MARS instrument. Participants who tested the app were satisfied with the ET Component during exposure scenarios (score of mu4.32 out of 5 [mu 0.28] on MARS quality aspects), agreed on the soundness of the theoretical foundations of the solutions developed (score of mu4.57 [mu0.48] on MARS treatment support aspects), and provided minor think-a-loud comments to improve them.
Conclusions
The results of the expert evaluation demonstrate the psychological validity of the ET Component and the SyMptOMS-ET app. However, further studies are needed to discern the acceptability and efficacy of the mHealth tool in the target population.
While exposure therapy (ET) has the potential to help people tolerate intense situation-specific emotions and change avoidance behaviours, no smartphone solution exists to guide the process of in-vivo ET. A geolocation-based smartphone software component was designed and developed to instrumentalize patient guidance in in-vivo ET and its psychological validity was assessed by a group of independent psychology experts.
Methods
A team of computer scientists and psychologists developed the ET Component for in-vivo ET using geolocation-based technology, following the process-centred design methodology. The ET Component was integrated into the SyMptOMS-ET Android application, which was developed following the co-design methodology. Next, nine independent psychology experts tested and evaluated the ET Component and the SyMptOMS-ET app in the field, following the think-aloud methodology. Participants also completed the Mobile Application Rating Scale (MARS) instrument to quantitatively evaluate the solutions.
Results
We present the SyMptOMS-ET app’s main features and the ET Component exposure workflow. Next, we discuss the feedback obtained and the results of the MARS instrument. Participants who tested the app were satisfied with the ET Component during exposure scenarios (score of mu4.32 out of 5 [mu 0.28] on MARS quality aspects), agreed on the soundness of the theoretical foundations of the solutions developed (score of mu4.57 [mu0.48] on MARS treatment support aspects), and provided minor think-a-loud comments to improve them.
Conclusions
The results of the expert evaluation demonstrate the psychological validity of the ET Component and the SyMptOMS-ET app. However, further studies are needed to discern the acceptability and efficacy of the mHealth tool in the target population.
Butinar, Zaklin; Donati, Annalisa; Boeree, Henry; Carbonaro, Milva; Missoni-Steinbacher, Eva-Maria; Schernthanner-Hofer, Barbara; Tkalec, Isabella; Povero, Gabriella; Deisting, Baerbel; Casteleyn, Sven; Lemmens, Rob; Bocim-Dumitriu, Andrei
SpaceSUITE: Bridging the Gap Between the Supply and Demand of Skills in the Downstream Space Sector Proceedings Article
In: Proceedings of the 75th International Astronautical Congress (IAC), pp. 1201-1205, International Astronautical Federation (IAF), 2024, (2024-20).
Abstract | Links | BibTeX | Tags: Body of Knowledge, education
@inproceedings{Butinar2024a,
title = {SpaceSUITE: Bridging the Gap Between the Supply and Demand of Skills in the Downstream Space Sector},
author = {Zaklin Butinar and Annalisa Donati and Henry Boeree and Milva Carbonaro and Eva-Maria Missoni-Steinbacher and Barbara Schernthanner-Hofer and Isabella Tkalec and Gabriella Povero and Baerbel Deisting and Sven Casteleyn and Rob Lemmens and Andrei Bocim-Dumitriu},
doi = {https://doi.org/10.52202/078378-0150},
year = {2024},
date = {2024-10-24},
urldate = {2024-10-24},
booktitle = {Proceedings of the 75th International Astronautical Congress (IAC)},
pages = {1201-1205},
publisher = {International Astronautical Federation (IAF)},
abstract = {The rapid development of the space sector, resulting from widely increased capabilities of satellites, brings new challenges for the space downstream sector and the need to adapt and take full advantage of such new space technologies. This recent disruption of the market generated a new demand for development of skills, reskilling and upskilling of the current and future space workforce, which has also been identified as essential to ensure the competitiveness and innovation of the space sector of the EU. Addressing the challenge of matching the supply and demand of skills through the development of innovative resources for education and training of the space workforce, a new Erasmus+ Blueprint project, SpaceSUITE, was launched in 2024. The expected outcome of the SpaceSUITE project is therefore conceiving and fomenting a skills intelligence approach to address skills mismatches, identify emerging and new skills and devise a skill development strategy. A comprehensive assessment of the existing skills and gaps identification is of utmost importance for the efficient preparation of new curricula for higher education (HE) and vocational education and training (VET) providers. Considering the aforementioned, the project is targeting professionals, graduates and students, central for the EU Space Programme and for the further expansion of the downstream space sector. The diverse SpaceSUITE consortium, consisting of the expertise from Academia, VET providers, associations of governments, clusters and representatives of industry companies, is aiming at creating a lasting impact on education and training by designing, developing and delivering new curricula and training programmes for HE and VET, as well as by enhancing collaboration and exchange of knowledge and practises within the downstream space ecosystems. The presentation of the SpaceSUITE project will highlight the importance and methods of skills development, upskilling and reskilling of the current and future space workforce, and contribute to the visibility of the project. Namely, the first step for a skilled space sector is to inform aspiring talents about training and job opportunities in the space sector, hence attracting and training the future space workforce, as it has been noted that the level of awareness of such opportunities is quite low. The presentation will then focus on the expected innovative outcomes of the project, including the development of a repository consisting of education and training resources. It will conclude by emphasising the project’s lasting impact within the duration of the project in the next four years and longer.},
note = {2024-20},
keywords = {Body of Knowledge, education},
pubstate = {published},
tppubtype = {inproceedings}
}
The rapid development of the space sector, resulting from widely increased capabilities of satellites, brings new challenges for the space downstream sector and the need to adapt and take full advantage of such new space technologies. This recent disruption of the market generated a new demand for development of skills, reskilling and upskilling of the current and future space workforce, which has also been identified as essential to ensure the competitiveness and innovation of the space sector of the EU. Addressing the challenge of matching the supply and demand of skills through the development of innovative resources for education and training of the space workforce, a new Erasmus+ Blueprint project, SpaceSUITE, was launched in 2024. The expected outcome of the SpaceSUITE project is therefore conceiving and fomenting a skills intelligence approach to address skills mismatches, identify emerging and new skills and devise a skill development strategy. A comprehensive assessment of the existing skills and gaps identification is of utmost importance for the efficient preparation of new curricula for higher education (HE) and vocational education and training (VET) providers. Considering the aforementioned, the project is targeting professionals, graduates and students, central for the EU Space Programme and for the further expansion of the downstream space sector. The diverse SpaceSUITE consortium, consisting of the expertise from Academia, VET providers, associations of governments, clusters and representatives of industry companies, is aiming at creating a lasting impact on education and training by designing, developing and delivering new curricula and training programmes for HE and VET, as well as by enhancing collaboration and exchange of knowledge and practises within the downstream space ecosystems. The presentation of the SpaceSUITE project will highlight the importance and methods of skills development, upskilling and reskilling of the current and future space workforce, and contribute to the visibility of the project. Namely, the first step for a skilled space sector is to inform aspiring talents about training and job opportunities in the space sector, hence attracting and training the future space workforce, as it has been noted that the level of awareness of such opportunities is quite low. The presentation will then focus on the expected innovative outcomes of the project, including the development of a repository consisting of education and training resources. It will conclude by emphasising the project’s lasting impact within the duration of the project in the next four years and longer.
Din, Teodor Constatin; Huerta-Guijarro, Joaquín; Trilles-Oliver, Sergio; Torres-Sospedra, Joaquín
Feasibility Analysis of Self-oriented Antennas for Indoor Positioning based on Direction-of-Arrival and Bluetooth-Low-Energy Proceedings Article
In: 2024 IEEE 14th International Conference on Indoor Positioning and Indoor Navigation (IPIN), pp. 1-6, IEEE, 2024, ISBN: 979-8-3503-6641-9, (2024-17).
Abstract | Links | BibTeX | Tags: Antennas, Indoor localization, Indoor positioning
@inproceedings{Din2024a,
title = {Feasibility Analysis of Self-oriented Antennas for Indoor Positioning based on Direction-of-Arrival and Bluetooth-Low-Energy},
author = {Teodor Constatin Din and Joaquín Huerta-Guijarro and Sergio Trilles-Oliver and Joaquín Torres-Sospedra},
doi = {https://doi.org/10.1109/IPIN62893.2024.10786160},
isbn = {979-8-3503-6641-9},
year = {2024},
date = {2024-10-17},
urldate = {2024-10-17},
booktitle = {2024 IEEE 14th International Conference on Indoor Positioning and Indoor Navigation (IPIN)},
pages = {1-6},
publisher = {IEEE},
abstract = {Indoor positioning systems have typically relied on static anchors, such as beacons or WiFi routers, and static environmental conditions, such as magnetic fields. On the other way around, it is also common to have fixed sensing devices, such as cameras, monitoring the environment, or passive receivers collecting relevant measurements from devices being tracked (signal strength, time/direction of arrival, among others). In one form or in another, we can usually find a static device. Furthermore, the evaluation of Radio Frequency-based positioning systems has commonly relied on measurements from static evaluation locations, being a continuous evaluation less frequent in solutions relying on, for instance, fingerprinting or based on signal strength. However, there is a need for a paradigm shift in indoor positioning systems as dynamic conditions are being slowly introduced. This paper introduces an exploratory analysis of a novel approach to be integrated into existing indoor positioning solutions based on Bluetooth Low Energy-based Direction-of-Arrival solutions. The core idea is to allow the infrastructure sensing the environment to adjust the orientation of the antennas, enhance the coverage, and provide better positioning of the devices being tracked. i.e., this approach will enable the system to evolve over time, continuously adapting to current environmental conditions. We describe the low-cost infrastructure needed to enable self-orientation for a commercial Bluetooth Low Energy board providing Direction-of-Arrival measurements.},
note = {2024-17},
keywords = {Antennas, Indoor localization, Indoor positioning},
pubstate = {published},
tppubtype = {inproceedings}
}
Indoor positioning systems have typically relied on static anchors, such as beacons or WiFi routers, and static environmental conditions, such as magnetic fields. On the other way around, it is also common to have fixed sensing devices, such as cameras, monitoring the environment, or passive receivers collecting relevant measurements from devices being tracked (signal strength, time/direction of arrival, among others). In one form or in another, we can usually find a static device. Furthermore, the evaluation of Radio Frequency-based positioning systems has commonly relied on measurements from static evaluation locations, being a continuous evaluation less frequent in solutions relying on, for instance, fingerprinting or based on signal strength. However, there is a need for a paradigm shift in indoor positioning systems as dynamic conditions are being slowly introduced. This paper introduces an exploratory analysis of a novel approach to be integrated into existing indoor positioning solutions based on Bluetooth Low Energy-based Direction-of-Arrival solutions. The core idea is to allow the infrastructure sensing the environment to adjust the orientation of the antennas, enhance the coverage, and provide better positioning of the devices being tracked. i.e., this approach will enable the system to evolve over time, continuously adapting to current environmental conditions. We describe the low-cost infrastructure needed to enable self-orientation for a commercial Bluetooth Low Energy board providing Direction-of-Arrival measurements.
Matey-Sanz, Miguel; González-Pérez, Alberto; Casteleyn, Sven; Granell-Canut, Carlos
Implementing and Evaluating the Timed Up and Go Test Automation Using Smartphones and Smartwatches Journal Article
In: IEEE Journal of Biomedical and Health Informatics, vol. 28, iss. 11, pp. 6594 - 6605, 2024, ISSN: 2168-2208, (2024-14).
Abstract | Links | BibTeX | Tags: activity recognition, machine learning, Mobile apps, symptoms, wearables
@article{Matey2024b,
title = {Implementing and Evaluating the Timed Up and Go Test Automation Using Smartphones and Smartwatches},
author = {Miguel Matey-Sanz and Alberto González-Pérez and Sven Casteleyn and Carlos Granell-Canut},
doi = {https://doi.org/10.1109/JBHI.2024.3456169},
issn = {2168-2208},
year = {2024},
date = {2024-09-09},
urldate = {2024-09-09},
journal = {IEEE Journal of Biomedical and Health Informatics},
volume = {28},
issue = {11},
pages = {6594 - 6605},
publisher = {IEEE},
abstract = {Physical performance tests aim to assess the physical abilities and mobility skills of individuals for various healthcare purposes. They are often driven by experts and usually performed at their practice, and therefore they are resource-intensive and time-demanding. For tests based on objective measurements (e.g., duration, repetitions), technology can be used to automate them, allowing the patients to perform the test themselves, more frequently and anywhere, while alleviating the expert from supervising the test. The well-known Timed Up and Go (TUG) test, typically used for mobility assessment, is an ideal candidate for automation, as inertial sensors (among others) can be deployed to detect the various movements constituting the test without expert supervision. To move from expert-led testing to self-administered testing, we present a mHealth system capable of automating the TUG test using a pocket-sized smartphone or a wrist smartwatch paired with a smartphone, where data from inertial sensors are used to detect the activities carried out by the patient while performing the test and compute their results in real time. All processing (i.e., data processing, machine learning-based activity inference, results calculation) takes place on the smartphone. The use of both devices to automate the TUG test was evaluated (w.r.t. accuracy, reliability and battery consumption) and mutually compared, and set off with a reference method, obtaining excellent Bland-Altman agreement results and Intraclass Correlation Coefficient reliability. Results also suggest that the smartwatch-based system performs better than the smartphone-based system.},
note = {2024-14},
keywords = {activity recognition, machine learning, Mobile apps, symptoms, wearables},
pubstate = {published},
tppubtype = {article}
}
Physical performance tests aim to assess the physical abilities and mobility skills of individuals for various healthcare purposes. They are often driven by experts and usually performed at their practice, and therefore they are resource-intensive and time-demanding. For tests based on objective measurements (e.g., duration, repetitions), technology can be used to automate them, allowing the patients to perform the test themselves, more frequently and anywhere, while alleviating the expert from supervising the test. The well-known Timed Up and Go (TUG) test, typically used for mobility assessment, is an ideal candidate for automation, as inertial sensors (among others) can be deployed to detect the various movements constituting the test without expert supervision. To move from expert-led testing to self-administered testing, we present a mHealth system capable of automating the TUG test using a pocket-sized smartphone or a wrist smartwatch paired with a smartphone, where data from inertial sensors are used to detect the activities carried out by the patient while performing the test and compute their results in real time. All processing (i.e., data processing, machine learning-based activity inference, results calculation) takes place on the smartphone. The use of both devices to automate the TUG test was evaluated (w.r.t. accuracy, reliability and battery consumption) and mutually compared, and set off with a reference method, obtaining excellent Bland-Altman agreement results and Intraclass Correlation Coefficient reliability. Results also suggest that the smartwatch-based system performs better than the smartphone-based system.
Klus, Roman; Talvitie, Jukka; Torres-Sospedra, Joaquín; Quezada-Gaibor, Darwin; Casteleyn, Sven; Cabric, Danijela; Valkama, Mikko
C2R: A Novel Architecture for Boosting Indoor Positioning With Scarce Data Journal Article
In: IEEE Internet of Things Journal, vol. 11, iss. 20, pp. 32868-32882, 2024, ISSN: 2327-4662, (2024-11).
Abstract | Links | BibTeX | Tags: deep learning, Indoor localization, Wi-Fi fingerprint
@article{Klus2025a,
title = {C2R: A Novel Architecture for Boosting Indoor Positioning With Scarce Data},
author = {Roman Klus and Jukka Talvitie and Joaquín Torres-Sospedra and Darwin Quezada-Gaibor and Sven Casteleyn and Danijela Cabric and Mikko Valkama},
doi = {https://doi.org/10.1109/JIOT.2024.3420122},
issn = {2327-4662},
year = {2024},
date = {2024-09-01},
urldate = {2024-09-01},
journal = {IEEE Internet of Things Journal},
volume = {11},
issue = {20},
pages = {32868-32882},
publisher = {IEEE},
abstract = {Improving the performance of Artificial Neural Network (ANN) regression models on small or scarce datasets, such as wireless network positioning data, can be realized by simplifying the task. One such approach includes implementing the regression model as a classifier, followed by a probabilistic mapping algorithm that transforms class probabilities into the multi-dimensional regression output. In this work, we propose the so-called c2r, a novel ANN-based architecture that transforms the classification model into a robust regressor, while enabling end-to-end training. The proposed solution can remove the impact of less likely classes from the probabilistic mapping by implementing a novel, trainable differential thresholded Rectified Linear Unit layer. The proposed solution is introduced and evaluated in the indoor positioning application domain, using 23 real-world, openly available positioning datasets. The proposed C2R model is shown to achieve significant improvements over the numerous benchmark methods in terms of positioning accuracy. Specifically, when averaged across the 23 datasets, the proposed c2r improves the mean positioning error by 7.9% compared to weighted knn with k=3, from 5.43 m to 5.00 m, and by 15.4% compared to a dense neural network (DNN), from 5.91 m to 5.00 m, while adapting the learned threshold. Finally, the proposed method adds only a single training parameter to the ann, thus as shown through analytical and empirical means in the article, there is no significant increase in the computational complexity.},
note = {2024-11},
keywords = {deep learning, Indoor localization, Wi-Fi fingerprint},
pubstate = {published},
tppubtype = {article}
}
Improving the performance of Artificial Neural Network (ANN) regression models on small or scarce datasets, such as wireless network positioning data, can be realized by simplifying the task. One such approach includes implementing the regression model as a classifier, followed by a probabilistic mapping algorithm that transforms class probabilities into the multi-dimensional regression output. In this work, we propose the so-called c2r, a novel ANN-based architecture that transforms the classification model into a robust regressor, while enabling end-to-end training. The proposed solution can remove the impact of less likely classes from the probabilistic mapping by implementing a novel, trainable differential thresholded Rectified Linear Unit layer. The proposed solution is introduced and evaluated in the indoor positioning application domain, using 23 real-world, openly available positioning datasets. The proposed C2R model is shown to achieve significant improvements over the numerous benchmark methods in terms of positioning accuracy. Specifically, when averaged across the 23 datasets, the proposed c2r improves the mean positioning error by 7.9% compared to weighted knn with k=3, from 5.43 m to 5.00 m, and by 15.4% compared to a dense neural network (DNN), from 5.91 m to 5.00 m, while adapting the learned threshold. Finally, the proposed method adds only a single training parameter to the ann, thus as shown through analytical and empirical means in the article, there is no significant increase in the computational complexity.
Kotze, André; Hildemann, Moritz Jan; Santos, Vitor; Granell-Canut, Carlos
Genetic Programming to Optimize 3D Trajectories Journal Article
In: ISPRS International Journal of Geo-Information, vol. 13, no. 8, pp. 295, 2024, ISSN: 2220-9964, (2024-10).
Abstract | Links | BibTeX | Tags: 3D, genetic algorithms, trajectory optimisation
@article{Kotze2024a,
title = {Genetic Programming to Optimize 3D Trajectories},
author = {André Kotze and Moritz Jan Hildemann and Vitor Santos and Carlos Granell-Canut},
doi = {https://doi.org/10.3390/ijgi13080295},
issn = {2220-9964},
year = {2024},
date = {2024-08-20},
urldate = {2024-08-20},
journal = {ISPRS International Journal of Geo-Information},
volume = {13},
number = {8},
pages = {295},
publisher = {MDPI},
abstract = {Trajectory optimization is a method of finding the optimal route connecting a start and end point. The suitability of a trajectory depends on not intersecting any obstacles, as well as predefined performance metrics. In the context of unmanned aerial vehicles (UAVs), the goal is to minimize the route cost, in terms of energy or time, while avoiding restricted flight zones. Artificial intelligence techniques, including evolutionary computation, have been applied to trajectory optimization with varying degrees of success. This work explores the use of genetic programming (GP) for 3D trajectory optimization by developing a novel GP algorithm to optimize trajectories in a 3D space by encoding 3D geographic trajectories as function trees. The effects of parameterization are also explored and discussed, demonstrating the advantages and drawbacks of custom parameter settings along with additional evolutionary computational techniques. The results demonstrate the effectiveness of the proposed algorithm, which outperforms existing methods in terms of speed, automaticity, and robustness, highlighting the potential for GP-based algorithms to be applied to other complex optimization problems in science and engineering.},
note = {2024-10},
keywords = {3D, genetic algorithms, trajectory optimisation},
pubstate = {published},
tppubtype = {article}
}
Trajectory optimization is a method of finding the optimal route connecting a start and end point. The suitability of a trajectory depends on not intersecting any obstacles, as well as predefined performance metrics. In the context of unmanned aerial vehicles (UAVs), the goal is to minimize the route cost, in terms of energy or time, while avoiding restricted flight zones. Artificial intelligence techniques, including evolutionary computation, have been applied to trajectory optimization with varying degrees of success. This work explores the use of genetic programming (GP) for 3D trajectory optimization by developing a novel GP algorithm to optimize trajectories in a 3D space by encoding 3D geographic trajectories as function trees. The effects of parameterization are also explored and discussed, demonstrating the advantages and drawbacks of custom parameter settings along with additional evolutionary computational techniques. The results demonstrate the effectiveness of the proposed algorithm, which outperforms existing methods in terms of speed, automaticity, and robustness, highlighting the potential for GP-based algorithms to be applied to other complex optimization problems in science and engineering.
Trilles-Oliver, Sergio; Monfort-Muriach, Aida; Cueto-Rubio, Enrique; López-Girona, Carmen; Granell-Canut, Carlos
Sucre4Stem: A K-12 Educational Tool for Integrating Computational Thinking and Programming Across Multidisciplinary Disciplines Journal Article
In: IEEE Transactions on Education, vol. 67, iss. 6, pp. 868-877, 2024, ISSN: 0018-9359, (2024-12).
Abstract | Links | BibTeX | Tags: education, Internet of things, SUCRE, sucre4kids, sucre4stem
@article{Trilles2024c,
title = {Sucre4Stem: A K-12 Educational Tool for Integrating Computational Thinking and Programming Across Multidisciplinary Disciplines},
author = {Sergio Trilles-Oliver and Aida Monfort-Muriach and Enrique Cueto-Rubio and Carmen López-Girona and Carlos Granell-Canut},
doi = {https://doi.org/10.1109/TE.2024.3422666},
issn = { 0018-9359},
year = {2024},
date = {2024-07-29},
urldate = {2024-07-29},
journal = {IEEE Transactions on Education},
volume = {67},
issue = {6},
pages = {868-877},
publisher = {IEEE},
abstract = {This article discusses the latest developments of the Sucre4Stem tool, as part of the Sucre initiative, which aims to promote interest in computational thinking and programming skills in K-12 students. The tool follows the Internet of Things approach and consists of two prominent components: 1) SucreCore and 2) SucreCode . SucreCore incorporates an advanced microcontroller packaged in a more compact design and enables wireless connectivity. SucreCode , the block-based visual programming tool, supports two different sets of blocks depending on the education grade, and facilitates wireless communication with SucreCore . At the educational level, Sucre4Stem fosters new group dynamics and encourages students to experiment real-world projects by promoting the “programming to learn” approach to concepts from other disciplines as opposed to the strategy widely applied in schools of “learning to program” in isolation.},
note = {2024-12},
keywords = {education, Internet of things, SUCRE, sucre4kids, sucre4stem},
pubstate = {published},
tppubtype = {article}
}
This article discusses the latest developments of the Sucre4Stem tool, as part of the Sucre initiative, which aims to promote interest in computational thinking and programming skills in K-12 students. The tool follows the Internet of Things approach and consists of two prominent components: 1) SucreCore and 2) SucreCode . SucreCore incorporates an advanced microcontroller packaged in a more compact design and enables wireless connectivity. SucreCode , the block-based visual programming tool, supports two different sets of blocks depending on the education grade, and facilitates wireless communication with SucreCore . At the educational level, Sucre4Stem fosters new group dynamics and encourages students to experiment real-world projects by promoting the “programming to learn” approach to concepts from other disciplines as opposed to the strategy widely applied in schools of “learning to program” in isolation.
Novak, Robert; Delgado, Marcos; García-Sipols, Ana Elizabeth; Trilles-Oliver, Sergio; de Blas, Clara Simón; Gallego, Micael; Rodríguez-Sánchez, Maria Cristina
A Real-Time Framework for Enhancing Emergency Response Effectiveness in Firefighting Contexts Proceedings Article
In: Seminario Anual de Automática, Electrónica Industrial e Instrumentación, pp. 1-7, Granada, 2024, (2024-16).
Abstract | BibTeX | Tags: machine learning, Real time analysis, Smart Cities
@inproceedings{Novak2024a,
title = {A Real-Time Framework for Enhancing Emergency Response Effectiveness in Firefighting Contexts},
author = {Robert Novak and Marcos Delgado and Ana Elizabeth García-Sipols and Sergio Trilles-Oliver and Clara Simón de Blas and Micael Gallego and Maria Cristina Rodríguez-Sánchez},
year = {2024},
date = {2024-07-03},
urldate = {2024-07-03},
booktitle = {Seminario Anual de Automática, Electrónica Industrial e Instrumentación},
pages = {1-7},
address = {Granada},
abstract = {This study presents a real-time framework designed to enhance emergency response effectiveness, initially applied in firefighting contexts but potentially generalizable to other emergency scenarios. Integrating advanced sensors with a comprehensive mathematical framework significantly enhances immediate situational awareness and substantially improves operational decision-making. Deployed and tested at Fire Station 9 in Chamartín, the system utilizes strategically placed sensors with variable transmission rates to simulate diverse emergency scenarios. The core achievement of this research is the demonstration of the framework’s capacity to provide real-time predictions, enabling emergency responders to act swiftly and accurately in dynamic situations. The results highlight the significant potential of real-time data analytics in revolutionizing emergency response strategies, offering a path towards safer and more efficient firefighting operations.},
note = {2024-16},
keywords = {machine learning, Real time analysis, Smart Cities},
pubstate = {published},
tppubtype = {inproceedings}
}
This study presents a real-time framework designed to enhance emergency response effectiveness, initially applied in firefighting contexts but potentially generalizable to other emergency scenarios. Integrating advanced sensors with a comprehensive mathematical framework significantly enhances immediate situational awareness and substantially improves operational decision-making. Deployed and tested at Fire Station 9 in Chamartín, the system utilizes strategically placed sensors with variable transmission rates to simulate diverse emergency scenarios. The core achievement of this research is the demonstration of the framework’s capacity to provide real-time predictions, enabling emergency responders to act swiftly and accurately in dynamic situations. The results highlight the significant potential of real-time data analytics in revolutionizing emergency response strategies, offering a path towards safer and more efficient firefighting operations.
Ramos-Romero, Francisco; Trilles-Oliver, Sergio; Granell-Canut, Carlos
ARE YOU ABLE TO TELL STORIES WITH DATA? Proceedings Article
In: EDULEARN24 Proceedings, pp. 6978-6982, IATED, 2024, ISBN: 978-84-09-62938-1, (2024-09).
Abstract | Links | BibTeX | Tags: data visualization, storytelling
@inproceedings{Ramos2024a,
title = {ARE YOU ABLE TO TELL STORIES WITH DATA?},
author = {Francisco Ramos-Romero and Sergio Trilles-Oliver and Carlos Granell-Canut},
doi = {https://doi.org/10.21125/edulearn.2024.1653},
isbn = {978-84-09-62938-1},
year = {2024},
date = {2024-07-03},
urldate = {2024-07-03},
booktitle = {EDULEARN24 Proceedings},
pages = {6978-6982},
publisher = {IATED},
abstract = {During our first education years, at the school, even at the high school, we learnt very much about many different subjects. However, in most cases, an important ability for our professional future is missed: how to create and tell stories with data and numbers. This lack of information has produced a big problem: users have access to a large amount of information, due to the current technological advances, but they are unable efficiently use data to tell stories, which is key to convert them into relevant information.
In this paper, we present a study we performed with master students aimed at improving their data visualization skills. We divided this study into several stages. Firstly, the students learn by accomplishing different tasks following a clear path divided into these sections: analysis of the audience, selecting the appropriate visuals, simplification, focus, communication with data, storytelling, and final visuals. Every task was presented in a visual and natural way, with different options, where the students should choose the correct answers, from a clear and objective point of view. All the tasks are part of a global questionnaire, which was carried out by the students so that they prove their competence in telling effective stories with numbers and data. The results shown clear lacks in different tasks such a simplification and communication with data, where most of students didn’t correctly answer the questions. As a conclusion, we can claim that more effort must be done in setting a clear objective in the visual communication field. In particular, simplifying data, focusing on the important part of the message to the audience, and also in the way and shape that data are presented.},
note = {2024-09},
keywords = {data visualization, storytelling},
pubstate = {published},
tppubtype = {inproceedings}
}
During our first education years, at the school, even at the high school, we learnt very much about many different subjects. However, in most cases, an important ability for our professional future is missed: how to create and tell stories with data and numbers. This lack of information has produced a big problem: users have access to a large amount of information, due to the current technological advances, but they are unable efficiently use data to tell stories, which is key to convert them into relevant information.
In this paper, we present a study we performed with master students aimed at improving their data visualization skills. We divided this study into several stages. Firstly, the students learn by accomplishing different tasks following a clear path divided into these sections: analysis of the audience, selecting the appropriate visuals, simplification, focus, communication with data, storytelling, and final visuals. Every task was presented in a visual and natural way, with different options, where the students should choose the correct answers, from a clear and objective point of view. All the tasks are part of a global questionnaire, which was carried out by the students so that they prove their competence in telling effective stories with numbers and data. The results shown clear lacks in different tasks such a simplification and communication with data, where most of students didn’t correctly answer the questions. As a conclusion, we can claim that more effort must be done in setting a clear objective in the visual communication field. In particular, simplifying data, focusing on the important part of the message to the audience, and also in the way and shape that data are presented.
In this paper, we present a study we performed with master students aimed at improving their data visualization skills. We divided this study into several stages. Firstly, the students learn by accomplishing different tasks following a clear path divided into these sections: analysis of the audience, selecting the appropriate visuals, simplification, focus, communication with data, storytelling, and final visuals. Every task was presented in a visual and natural way, with different options, where the students should choose the correct answers, from a clear and objective point of view. All the tasks are part of a global questionnaire, which was carried out by the students so that they prove their competence in telling effective stories with numbers and data. The results shown clear lacks in different tasks such a simplification and communication with data, where most of students didn’t correctly answer the questions. As a conclusion, we can claim that more effort must be done in setting a clear objective in the visual communication field. In particular, simplifying data, focusing on the important part of the message to the audience, and also in the way and shape that data are presented.
Trilles-Oliver, Sergio; Granell-Canut, Carlos; Ramos-Romero, Francisco
SUCRE4STEM'S DUAL APPROACH TO ENHANCING COMPUTATIONAL THINKING AND PROGRAMMING SKILLS Proceedings Article
In: EDULEARN24 Proceedings, pp. 8094-8103, IATED, 2024, ISBN: 978-84-09-62938-1, (2024-08).
Abstract | Links | BibTeX | Tags: Internet of things, SUCRE, sucre4stem
@inproceedings{Trilles2024b,
title = {SUCRE4STEM'S DUAL APPROACH TO ENHANCING COMPUTATIONAL THINKING AND PROGRAMMING SKILLS},
author = {Sergio Trilles-Oliver and Carlos Granell-Canut and Francisco Ramos-Romero},
doi = {https://doi.org/10.21125/edulearn.2024.1908},
isbn = {978-84-09-62938-1},
year = {2024},
date = {2024-07-03},
urldate = {2024-07-03},
booktitle = {EDULEARN24 Proceedings},
pages = {8094-8103},
publisher = {IATED},
abstract = {This article highlights recent advancements in the Sucre4Stem initiative, a key component of the broader Sucre project designed to kindle interest in computational thinking and programming among K-12 students. At its core, Sucre4Stem embraces the Internet of Things (IoT) ideology and is built around two main elements: SucreCore and SucreCode. SucreCore features a sophisticated microcontroller in a sleeker design, complemented by wireless connectivity options. On the other hand, SucreCode presents a block-based visual programming interface that now offers the choice between two distinct block sets tailored to different educational levels: one for primary education students (Grades 3-6) incorporating basic programming concepts with engaging graphics, and another for high school students (Grades 7-12), which introduces more advanced concepts closer to traditional coding. This dual approach not only makes Sucre4Stem versatile across educational stages but also enhances its educational impact by fostering new group dynamics and empowering students to undertake real-world projects.},
note = {2024-08},
keywords = {Internet of things, SUCRE, sucre4stem},
pubstate = {published},
tppubtype = {inproceedings}
}
This article highlights recent advancements in the Sucre4Stem initiative, a key component of the broader Sucre project designed to kindle interest in computational thinking and programming among K-12 students. At its core, Sucre4Stem embraces the Internet of Things (IoT) ideology and is built around two main elements: SucreCore and SucreCode. SucreCore features a sophisticated microcontroller in a sleeker design, complemented by wireless connectivity options. On the other hand, SucreCode presents a block-based visual programming interface that now offers the choice between two distinct block sets tailored to different educational levels: one for primary education students (Grades 3-6) incorporating basic programming concepts with engaging graphics, and another for high school students (Grades 7-12), which introduces more advanced concepts closer to traditional coding. This dual approach not only makes Sucre4Stem versatile across educational stages but also enhances its educational impact by fostering new group dynamics and empowering students to undertake real-world projects.
Matey-Sanz, Miguel; Granell-Canut, Carlos; Cárdenas, Ramón A. Mollineda
Estrategias de control y seguimiento activo de proyectos de desarrollo de software Proceedings Article
In: Actas de las Jornadas sobre Enseñanza Universitaria de la Informática (JENUI), pp. 165-172, AENUI, 2024, ISSN: 2531-0607, (2024-07).
Abstract | Links | BibTeX | Tags: docente
@inproceedings{Matey2024a,
title = {Estrategias de control y seguimiento activo de proyectos de desarrollo de software},
author = {Miguel Matey-Sanz and Carlos Granell-Canut and Ramón A. Mollineda Cárdenas},
url = {https://aenui.org/actas/pdf/JENUI_2024_021.pdf},
issn = {2531-0607},
year = {2024},
date = {2024-07-01},
urldate = {2024-07-01},
booktitle = {Actas de las Jornadas sobre Enseñanza Universitaria de la Informática (JENUI)},
volume = {9},
pages = { 165-172},
publisher = {AENUI},
abstract = {A system of active control and monitoring actions for software development projects by teams is proposed. It has been designed within the framework of a coordination action of two subjects from the fourth year of a Degree in Computer Engineering, the cornerstone of which is an agile development project guided by acceptance tests and evolutionary design. Students face multiple complexities: realistic scenario (e.g., mobility application), development methodology (ATDD), technical requirements (e.g., executable tests, decoupled architecture), connection to public services (e.g., geocoding, route calculation) and the use of modern technologies for cross-platform development, integration and deployment. Despite having resources from two subjects and a well-defined itinerary, the risk of dropping out was significant. To reinforce the control mechanisms, a system was created with warning cards, two sessions dedicated to the defence of partial deliverable, and adaptations of the GitFlow methodology and a commit standard (Conventional commits) to actively monitor the project and the individual contribution of the students. As a result, improvements have been observed in the rate of projects completed in the
first call, the project quality, and the increase in training measured from pre and post surveys.},
note = {2024-07},
keywords = {docente},
pubstate = {published},
tppubtype = {inproceedings}
}
A system of active control and monitoring actions for software development projects by teams is proposed. It has been designed within the framework of a coordination action of two subjects from the fourth year of a Degree in Computer Engineering, the cornerstone of which is an agile development project guided by acceptance tests and evolutionary design. Students face multiple complexities: realistic scenario (e.g., mobility application), development methodology (ATDD), technical requirements (e.g., executable tests, decoupled architecture), connection to public services (e.g., geocoding, route calculation) and the use of modern technologies for cross-platform development, integration and deployment. Despite having resources from two subjects and a well-defined itinerary, the risk of dropping out was significant. To reinforce the control mechanisms, a system was created with warning cards, two sessions dedicated to the defence of partial deliverable, and adaptations of the GitFlow methodology and a commit standard (Conventional commits) to actively monitor the project and the individual contribution of the students. As a result, improvements have been observed in the rate of projects completed in the
first call, the project quality, and the increase in training measured from pre and post surveys.
first call, the project quality, and the increase in training measured from pre and post surveys.
Klus, Lucie; Klus, Roman; Lohan, Elena Simona; Nurmi, Jari; Granell-Canut, Carlos; Valkama, Mikko; Talvitie, Jukka; Casteleyn, Sven; Torres-Sospedra, Joaquín
TUJI1 Dataset: Multi-device dataset for indoor localization with high measurement density Journal Article
In: Data in Brief, vol. 54, pp. 110356, 2024, ISSN: 2352-3409, (2024-06).
Abstract | Links | BibTeX | Tags: Indoor positioning
@article{Klus2024b,
title = {TUJI1 Dataset: Multi-device dataset for indoor localization with high measurement density},
author = {Lucie Klus and Roman Klus and Elena Simona Lohan and Jari Nurmi and Carlos Granell-Canut and Mikko Valkama and Jukka Talvitie and Sven Casteleyn and Joaquín Torres-Sospedra},
doi = {https://doi.org/10.1016/j.dib.2024.110356},
issn = {2352-3409},
year = {2024},
date = {2024-06-01},
urldate = {2024-06-01},
journal = {Data in Brief},
volume = {54},
pages = {110356},
publisher = {Elsevier},
abstract = {Positioning in indoor scenarios using signals of opportunity is an effective solution enabling accurate and reliable performance in Global Navigation Satellite System (GNSS)-obscured scenarios. Despite the availability of numerous fingerprinting datasets utilizing various wireless signals, the challenge of device heterogeneity and sample density remains an unanswered issue. To address this gap, this work introduces TUJI1, an anonymized IEEE 802.11 Wireless LAN (Wi-Fi) fingerprinting dataset collected using 5 different commercial devices in a fine-grained grid. The dataset contains the matched fingerprints of Received Signal Strength Indicator (RSSI) measurements with the corresponding coordinates, split into training and testing subsets for effortless and fair reproducibility.},
note = {2024-06},
keywords = {Indoor positioning},
pubstate = {published},
tppubtype = {article}
}
Positioning in indoor scenarios using signals of opportunity is an effective solution enabling accurate and reliable performance in Global Navigation Satellite System (GNSS)-obscured scenarios. Despite the availability of numerous fingerprinting datasets utilizing various wireless signals, the challenge of device heterogeneity and sample density remains an unanswered issue. To address this gap, this work introduces TUJI1, an anonymized IEEE 802.11 Wireless LAN (Wi-Fi) fingerprinting dataset collected using 5 different commercial devices in a fine-grained grid. The dataset contains the matched fingerprints of Received Signal Strength Indicator (RSSI) measurements with the corresponding coordinates, split into training and testing subsets for effortless and fair reproducibility.
Casanova-Marqués, Raúl
Privacy-enhancing technologies and privacy-enhancing cryptography for wearables PhD Thesis
Brno University of Technology, 2024, (2024-05).
Abstract | Links | BibTeX | Tags: A-wear, cryptography, Indoor positioning, Internet of things, privacy protection, wearables
@phdthesis{Casanova2024a,
title = {Privacy-enhancing technologies and privacy-enhancing cryptography for wearables},
author = {Raúl Casanova-Marqués},
url = {http://hdl.handle.net/10803/690875},
doi = {http://dx.doi.org/10.6035/14124.2024.839804},
year = {2024},
date = {2024-04-29},
urldate = {2024-04-29},
school = {Brno University of Technology},
abstract = {In response to escalating privacy concerns and the need for secure digital communication, cryptographic mechanisms have been developed to ensure impervious information exchange. However, traditional cryptographic approaches are inadequate in dynamic and resource-constrained environments, such as wearable devices. This thesis investigates attribute-based credential schemes, offering fine-grained access control based on user-specific attributes. Specifically, it assesses the effectiveness and scalability of attribute-based anonymous credential schemes within dynamic wearable device architectures. The study focuses on enhancing these schemes by incorporating user revocation while preserving privacy. Additionally, the research develops methods for attribute-based authentication protocols on smart cards with limited elliptic curve cryptography support and addresses usability challenges. Furthermore, the thesis explores the integration of anonymous authentication in collaborative indoor positioning systems to ensure privacy and security. It also delves into implementing attribute-based authentication in resource-constrained environments, including Internet of Things devices, and evaluating their feasibility in dynamic wearable device architectures.},
note = {2024-05},
keywords = {A-wear, cryptography, Indoor positioning, Internet of things, privacy protection, wearables},
pubstate = {published},
tppubtype = {phdthesis}
}
In response to escalating privacy concerns and the need for secure digital communication, cryptographic mechanisms have been developed to ensure impervious information exchange. However, traditional cryptographic approaches are inadequate in dynamic and resource-constrained environments, such as wearable devices. This thesis investigates attribute-based credential schemes, offering fine-grained access control based on user-specific attributes. Specifically, it assesses the effectiveness and scalability of attribute-based anonymous credential schemes within dynamic wearable device architectures. The study focuses on enhancing these schemes by incorporating user revocation while preserving privacy. Additionally, the research develops methods for attribute-based authentication protocols on smart cards with limited elliptic curve cryptography support and addresses usability challenges. Furthermore, the thesis explores the integration of anonymous authentication in collaborative indoor positioning systems to ensure privacy and security. It also delves into implementing attribute-based authentication in resource-constrained environments, including Internet of Things devices, and evaluating their feasibility in dynamic wearable device architectures.
Trilles-Oliver, Sergio; Hammad, Sahibzada Saadoon; Iskandaryan, Ditsuhi
Anomaly detection based on Artificial Intelligence of Things: A Systematic Literature Mapping Journal Article
In: Internet of Things, vol. 25, pp. 101063, 2024, ISSN: 2542-6605, (2024-02).
Abstract | Links | BibTeX | Tags: Anomaly detection, Edge computing, Internet of things, TidyML
@article{Trilles2024a,
title = {Anomaly detection based on Artificial Intelligence of Things: A Systematic Literature Mapping},
author = {Sergio Trilles-Oliver and Sahibzada Saadoon Hammad and Ditsuhi Iskandaryan},
doi = {https://doi.org/10.1016/j.iot.2024.101063},
issn = {2542-6605},
year = {2024},
date = {2024-04-01},
urldate = {2024-04-01},
journal = {Internet of Things},
volume = {25},
pages = {101063},
publisher = {Elsevier},
abstract = {Advanced Machine Learning (ML) algorithms can be applied using Edge Computing (EC) to detect anomalies, which is the basis of Artificial Intelligence of Things (AIoT). EC has emerged as a solution for processing and analysing information on IoT devices. This field aims to allow the implementation of Machine/Deep Learning (DL) models on MicroController Units (MCUs). Integrating anomaly detection analysis on Internet of Things (IoT) devices produces clear benefits as it ensures the use of accurate data from the initial stage. However, this process poses a challenge due to the unique characteristics of IoT. This article presents a Systematic Literature Mapping of scientific research on the application of anomaly detection techniques in EC using MCUs. A total of 18 papers published over the period 2021–2023 were selected from a total of 162 in four databases of scientific papers. The results of this paper provide a comprehensive overview of anomaly detection using TinyML and MCUs. The main contributions of this survey are the fact that it aims to: (a) study techniques for anomaly detection in ML/DL and validation metrics used in the AIoT; (b) analyse data used in the estimation of models; (c) show how ML is applied in EC using hardware or software; (d) investigate the main microcontrollers, types of power supply, and communication technology; and (e) develop a taxonomy of ML/DL algorithms used to detect anomalies in TinyML. Finally, the benefits and challenges of this kind of TinyML analysis are described.},
note = {2024-02},
keywords = {Anomaly detection, Edge computing, Internet of things, TidyML},
pubstate = {published},
tppubtype = {article}
}
Advanced Machine Learning (ML) algorithms can be applied using Edge Computing (EC) to detect anomalies, which is the basis of Artificial Intelligence of Things (AIoT). EC has emerged as a solution for processing and analysing information on IoT devices. This field aims to allow the implementation of Machine/Deep Learning (DL) models on MicroController Units (MCUs). Integrating anomaly detection analysis on Internet of Things (IoT) devices produces clear benefits as it ensures the use of accurate data from the initial stage. However, this process poses a challenge due to the unique characteristics of IoT. This article presents a Systematic Literature Mapping of scientific research on the application of anomaly detection techniques in EC using MCUs. A total of 18 papers published over the period 2021–2023 were selected from a total of 162 in four databases of scientific papers. The results of this paper provide a comprehensive overview of anomaly detection using TinyML and MCUs. The main contributions of this survey are the fact that it aims to: (a) study techniques for anomaly detection in ML/DL and validation metrics used in the AIoT; (b) analyse data used in the estimation of models; (c) show how ML is applied in EC using hardware or software; (d) investigate the main microcontrollers, types of power supply, and communication technology; and (e) develop a taxonomy of ML/DL algorithms used to detect anomalies in TinyML. Finally, the benefits and challenges of this kind of TinyML analysis are described.
Macias, Juan Emilio Zurita; Trilles-Oliver, Sergio
Machine learning-based prediction model for battery levels in IoT devices using meteorological variables Journal Article
In: Internet of Things, vol. 25, pp. 101109, 2024, ISSN: 2542-6605, (2024-03).
Abstract | Links | BibTeX | Tags: battery level prediction, Internet of things, machine learning
@article{Zurita2024a,
title = {Machine learning-based prediction model for battery levels in IoT devices using meteorological variables},
author = {Juan Emilio Zurita Macias and Sergio Trilles-Oliver},
doi = {https://doi.org/10.1016/j.iot.2024.101109},
issn = {2542-6605},
year = {2024},
date = {2024-04-01},
urldate = {2024-04-01},
journal = {Internet of Things},
volume = {25},
pages = {101109},
publisher = {Elsevier},
abstract = {Efficient energy management is vital for the sustainability of IoT devices employing solar harvesting systems, particularly to circumvent battery depletion during periods of diminished solar incidence. Embracing the structured methodology of CRISP-DM, this study introduces machine learning (ML) models that utilise meteorological data to predict battery charge levels in solar-powered IoT devices. These models enable proactive adjustments to the devices’ data sampling frequencies, ensuring effective energy utilisation. The proposed ML models were evaluated using authentic battery charge data and weather forecast records. The empirical results of this study corroborate the predictive prowess of the models, with an average accuracy reaching as high as 94.09% in specific test cases. This substantiates the potential of the developed methodology to significantly enhance the energy autonomy of IoT devices through predictive analytics.},
note = {2024-03},
keywords = {battery level prediction, Internet of things, machine learning},
pubstate = {published},
tppubtype = {article}
}
Efficient energy management is vital for the sustainability of IoT devices employing solar harvesting systems, particularly to circumvent battery depletion during periods of diminished solar incidence. Embracing the structured methodology of CRISP-DM, this study introduces machine learning (ML) models that utilise meteorological data to predict battery charge levels in solar-powered IoT devices. These models enable proactive adjustments to the devices’ data sampling frequencies, ensuring effective energy utilisation. The proposed ML models were evaluated using authentic battery charge data and weather forecast records. The empirical results of this study corroborate the predictive prowess of the models, with an average accuracy reaching as high as 94.09% in specific test cases. This substantiates the potential of the developed methodology to significantly enhance the energy autonomy of IoT devices through predictive analytics.
Gómez-Cambronero, Águeda; Mann, Anna-Lisa; Mira, Adriana; Doherty, Gavin; Casteleyn, Sven
Smartphone-based serious games for mental health: a scoping review Journal Article
In: Multimedia Tools and Applications, vol. 83, pp. 84047–84094, 2024, ISSN: 1573-7721, (2024-04).
Abstract | Links | BibTeX | Tags: mental health, serious games, symptoms, Systematic mapping
@article{GomezCambronero2024a,
title = {Smartphone-based serious games for mental health: a scoping review},
author = {Águeda Gómez-Cambronero and Anna-Lisa Mann and Adriana Mira and Gavin Doherty and Sven Casteleyn},
doi = {https://doi.org/10.1007/s11042-024-18971-w},
issn = {1573-7721},
year = {2024},
date = {2024-04-01},
urldate = {2024-04-01},
journal = {Multimedia Tools and Applications},
volume = {83},
pages = {84047–84094},
publisher = {Springer, Cham},
abstract = {The use of smartphone-based Serious Games in mental health care is an emerging and promising research field. Combining the intrinsic characteristics of games (e.g., interactiveness, immersiveness, playfulness, user-tailoring and engaging nature) with the capabilities of smartphones (e.g., versatility, ubiquitous connectivity, built-in sensors and anywhere–anytime nature) yields great potential to deliver innovative psychological treatments, which are engaging, effective, fun and always available. This article presents a scoping review, based on the PRISMA (scoping review extension) guidelines, of the field of smartphone-based serious games for mental health care. The review combines an analysis of the technical characteristics, including game design, smartphone and game-specific features, with psychological dimensions, including type and purpose of use, underlying psychological frameworks and strategies. It also explores the integration of psychological features into Serious Games and summarizes the findings of evaluations performed. A systematic search identified 40 smartphone-based Serious Games for mental health care. The majority consist of standalone and self-administrable interventions, applying a myriad of psychological strategies to address a wide range of psychological symptoms and disorders. The findings explore the potential of Serious Games as treatments and for enhancing patient engagement; we conclude by proposing several avenues for future research in order to identify best practices and success factors.},
note = {2024-04},
keywords = {mental health, serious games, symptoms, Systematic mapping},
pubstate = {published},
tppubtype = {article}
}
The use of smartphone-based Serious Games in mental health care is an emerging and promising research field. Combining the intrinsic characteristics of games (e.g., interactiveness, immersiveness, playfulness, user-tailoring and engaging nature) with the capabilities of smartphones (e.g., versatility, ubiquitous connectivity, built-in sensors and anywhere–anytime nature) yields great potential to deliver innovative psychological treatments, which are engaging, effective, fun and always available. This article presents a scoping review, based on the PRISMA (scoping review extension) guidelines, of the field of smartphone-based serious games for mental health care. The review combines an analysis of the technical characteristics, including game design, smartphone and game-specific features, with psychological dimensions, including type and purpose of use, underlying psychological frameworks and strategies. It also explores the integration of psychological features into Serious Games and summarizes the findings of evaluations performed. A systematic search identified 40 smartphone-based Serious Games for mental health care. The majority consist of standalone and self-administrable interventions, applying a myriad of psychological strategies to address a wide range of psychological symptoms and disorders. The findings explore the potential of Serious Games as treatments and for enhancing patient engagement; we conclude by proposing several avenues for future research in order to identify best practices and success factors.
Klus, Lucie; Klus, Roman; Torres-Sospedra, Joaquín; Lohan, Elena Simona; Granell-Canut, Carlos; Nurmi, Jari
EWOk: Towards Efficient Multidimensional Compression of Indoor Positioning Datasets Journal Article
In: IEEE Transactions on Mobile Computing, vol. 25, no. 5, pp. 3589-3604, 2024, ISSN: 1558-0660, (2024-01).
Abstract | Links | BibTeX | Tags: A-wear, machine learning, prediction algorithms, Wi-Fi fingerprint
@article{Klus2024a,
title = {EWOk: Towards Efficient Multidimensional Compression of Indoor Positioning Datasets},
author = {Lucie Klus and Roman Klus and Joaquín Torres-Sospedra and Elena Simona Lohan and Carlos Granell-Canut and Jari Nurmi},
doi = {https://doi.org/10.1109/TMC.2023.3277333},
issn = {1558-0660},
year = {2024},
date = {2024-03-01},
urldate = {2024-03-01},
journal = {IEEE Transactions on Mobile Computing},
volume = {25},
number = {5},
pages = {3589-3604},
publisher = {IEEE},
abstract = {Indoor positioning performed directly at the end-user device ensures reliability in case the network connection fails but is limited by the size of the RSS radio map necessary to match the measured array to the device’s location. Reducing the size of the RSS database enables faster processing, and saves storage space and radio resources necessary for the database transfer, thus cutting implementation and operation costs, and increasing the quality of service. In this work, we propose EWOk, an Element-Wise cOmpression using k-means, which reduces the size of the individual radio measurements within the fingerprinting radio map while sustaining or boosting the dataset’s positioning capabilities. We show that the 7-bit representation of measurements is sufficient in positioning scenarios, and reducing the data size further using EWOk results in higher compression and faster data transfer and processing. To eliminate the inherent uncertainty of k-means we propose a data-dependent, non-random initiation scheme to ensure stability and limit variance. We further combine EWOk with principal component analysis to show its applicability in combination with other methods, and to demonstrate the efficiency of the resulting multidimensional compression. We evaluate EWOk on 25 RSS fingerprinting datasets and show that it positively impacts compression efficiency, and positioning performance.},
note = {2024-01},
keywords = {A-wear, machine learning, prediction algorithms, Wi-Fi fingerprint},
pubstate = {published},
tppubtype = {article}
}
Indoor positioning performed directly at the end-user device ensures reliability in case the network connection fails but is limited by the size of the RSS radio map necessary to match the measured array to the device’s location. Reducing the size of the RSS database enables faster processing, and saves storage space and radio resources necessary for the database transfer, thus cutting implementation and operation costs, and increasing the quality of service. In this work, we propose EWOk, an Element-Wise cOmpression using k-means, which reduces the size of the individual radio measurements within the fingerprinting radio map while sustaining or boosting the dataset’s positioning capabilities. We show that the 7-bit representation of measurements is sufficient in positioning scenarios, and reducing the data size further using EWOk results in higher compression and faster data transfer and processing. To eliminate the inherent uncertainty of k-means we propose a data-dependent, non-random initiation scheme to ensure stability and limit variance. We further combine EWOk with principal component analysis to show its applicability in combination with other methods, and to demonstrate the efficiency of the resulting multidimensional compression. We evaluate EWOk on 25 RSS fingerprinting datasets and show that it positively impacts compression efficiency, and positioning performance.
2023
Bravenec, Tomás
Exploiting Wireless Communications for Localization: Beyond Fingerprinting PhD Thesis
INIT, UJI, 2023, (2023-32).
Abstract | Links | BibTeX | Tags: A-wear, data analysis methods, geoprivacy, Indoor positioning, machine learning
@phdthesis{Bravenec2023d,
title = {Exploiting Wireless Communications for Localization: Beyond Fingerprinting},
author = {Tomás Bravenec},
url = {http://hdl.handle.net/10803/689593},
doi = {http://dx.doi.org/10.6035/14124.2023.868082},
year = {2023},
date = {2023-12-18},
urldate = {2023-12-18},
school = {INIT, UJI},
abstract = {The field of Location-based Services (LBS) has experienced significant growth over the past decade, driven by increasing interest in fitness tracking, robotics, and eHealth. This dissertation focuses on evaluating privacy measures in Indoor Positioning Systems (IPS), particularly in the context of ubiquitous Wi-Fi networks. It addresses non-cooperative user tracking through the exploitation of unencrypted Wi-Fi management frames, which contain enough information for device fingerprinting despite MAC address randomization. The research also explores an algorithm to estimate room occupancy based on passive Wi-Fi frame sniffing and Received Signal Strength Indicator (RSSI) measurements. Such room occupancy detection has implications for energy regulations in smart buildings. Furthermore, the thesis investigates methods to reduce computational requirements of machine learning and positioning algorithms through optimizing neural networks and employing interpolation techniques for IPS based on RSSI fingerprinting. The work contributes datasets, analysis scripts, and firmware to improve reproducibility and supports advancements in the LBS field.},
note = {2023-32},
keywords = {A-wear, data analysis methods, geoprivacy, Indoor positioning, machine learning},
pubstate = {published},
tppubtype = {phdthesis}
}
The field of Location-based Services (LBS) has experienced significant growth over the past decade, driven by increasing interest in fitness tracking, robotics, and eHealth. This dissertation focuses on evaluating privacy measures in Indoor Positioning Systems (IPS), particularly in the context of ubiquitous Wi-Fi networks. It addresses non-cooperative user tracking through the exploitation of unencrypted Wi-Fi management frames, which contain enough information for device fingerprinting despite MAC address randomization. The research also explores an algorithm to estimate room occupancy based on passive Wi-Fi frame sniffing and Received Signal Strength Indicator (RSSI) measurements. Such room occupancy detection has implications for energy regulations in smart buildings. Furthermore, the thesis investigates methods to reduce computational requirements of machine learning and positioning algorithms through optimizing neural networks and employing interpolation techniques for IPS based on RSSI fingerprinting. The work contributes datasets, analysis scripts, and firmware to improve reproducibility and supports advancements in the LBS field.
Matey-Sanz, Miguel; Casteleyn, Sven; Granell-Canut, Carlos
Dataset of inertial measurements of smartphones and smartwatches for human activity recognition Journal Article
In: Data in Brief, vol. 51, pp. 109809, 2023, ISSN: 2352-3409, (2023-31).
Abstract | Links | BibTeX | Tags: activity recognition, dataset, machine learning, smartphone app, smartwatch, symptoms
@article{Matey2023c,
title = {Dataset of inertial measurements of smartphones and smartwatches for human activity recognition},
author = {Miguel Matey-Sanz and Sven Casteleyn and Carlos Granell-Canut},
doi = {https://doi.org/10.1016/j.dib.2023.109809},
issn = {2352-3409},
year = {2023},
date = {2023-12-15},
urldate = {2023-12-15},
journal = {Data in Brief},
volume = {51},
pages = {109809},
publisher = {Elsevier},
abstract = {This article describes a dataset for human activity recognition with inertial measurements, i.e., accelerometer and gyroscope, from a smartphone and a smartwatch placed in the left pocket and on the left wrist, respectively. Twenty-three heterogeneous subjects (μ = 44.3, σ = 14.3, 56% male) participated in the data collection, which consisted of performing five activities (seated, standing up, walking, turning, and sitting down) arranged in a specific sequence (corresponding with the TUG test). Subjects performed the sequence of activities multiple times while the devices collected inertial data at 100 Hz and were video-recorded by a researcher for data labelling purposes. The goal of this dataset is to provide smartphone- and smartwatch-based inertial data for human activity recognition collected from a heterogeneous (i.e., age-diverse, gender-balanced) set of subjects. Along with the dataset, the repository includes demographic information (age, gender), information about each sequence of activities (smartphone's orientation in the pocket, direction of turns), and a Python package with utility functions (data loading, visualization, etc). The dataset can be reused for different purposes in the field of human activity recognition, from cross-subject evaluation to comparison of recognition performance using data from smartphones and smartwatches.},
note = {2023-31},
keywords = {activity recognition, dataset, machine learning, smartphone app, smartwatch, symptoms},
pubstate = {published},
tppubtype = {article}
}
This article describes a dataset for human activity recognition with inertial measurements, i.e., accelerometer and gyroscope, from a smartphone and a smartwatch placed in the left pocket and on the left wrist, respectively. Twenty-three heterogeneous subjects (μ = 44.3, σ = 14.3, 56% male) participated in the data collection, which consisted of performing five activities (seated, standing up, walking, turning, and sitting down) arranged in a specific sequence (corresponding with the TUG test). Subjects performed the sequence of activities multiple times while the devices collected inertial data at 100 Hz and were video-recorded by a researcher for data labelling purposes. The goal of this dataset is to provide smartphone- and smartwatch-based inertial data for human activity recognition collected from a heterogeneous (i.e., age-diverse, gender-balanced) set of subjects. Along with the dataset, the repository includes demographic information (age, gender), information about each sequence of activities (smartphone's orientation in the pocket, direction of turns), and a Python package with utility functions (data loading, visualization, etc). The dataset can be reused for different purposes in the field of human activity recognition, from cross-subject evaluation to comparison of recognition performance using data from smartphones and smartwatches.
Gómez-Cambronero, Águeda
"Horizon: Resilience": A Smartphone-based Serious Game Intervention for Depressive Symptoms PhD Thesis
INIT, UJI, 2023, (2023-33).
Abstract | Links | BibTeX | Tags: mental health, Mobile apps, mobile computing, serious games, symptoms
@phdthesis{GomezCambronero2023b,
title = {"Horizon: Resilience": A Smartphone-based Serious Game Intervention for Depressive Symptoms},
author = {Águeda Gómez-Cambronero},
url = {http://hdl.handle.net/10803/689528},
doi = {http://dx.doi.org/10.6035/14101.2023.544418},
year = {2023},
date = {2023-12-11},
urldate = {2023-12-11},
school = {INIT, UJI},
abstract = {Depression is the most prevalent mental issue in our society, leading to disability and suicide deaths. The COVID-19 pandemic has intensified the need for depression treatment and prevention. While effective, evidence-based psychological treatments for depression exists, only a small percentage of those in need actually receive them. Technology, particularly smartphone-based interventions, can help maximize the reach of these treatments while ensuring their effectiveness, although it comes with challenges, such as high dropout rates. Despite the potential
of this therapy, this is a field that requires considerably more research to fully explore the benefits that smartphones have to offer. Specifically, serious games, designed with a purpose beyond entertainment, have emerged as a promising treatment tool, leveraging advance smartphone capabilities, aligning with psychological treatment principles, and enhancing user engagement.
This dissertation introduces “Horizon: Resilience”, a smartphone-based Serious Game for depressive symptoms. It is a city builder game with a decision making narrative, in which the player (patient) manages a town. The objective is to make the town progress, ensuring the steady inflow of resources and fostering the psychological resilience of its inhabitants. The game is based on the Cognitive Behavioral Therapy (CBT) framework and includes Positive Psychology (PP) techniques. These psychological techniques are woven into the game’s gameplay, feedback, economy system, quests, graphics, and story. Noteworthy is the integration of promoting Physical Activity, detected using the phone’s motion sensors, as part of gameplay. The game draws on the findings of a scoping review on smartphone-based serious games in mental health, and was informed by consultations with therapists as part of a user-centered design. Therapists and patients furthermore provided a qualitative and quantitative evaluation of a Minimum Viable Product (MVP) of the game. Their positive impressions indicate high acceptance and positive expectation regarding the use of the game as an
intervention. Lastly, a pilot randomized controlled trial protocol is outlined to assess its preliminary effectiveness-},
note = {2023-33},
keywords = {mental health, Mobile apps, mobile computing, serious games, symptoms},
pubstate = {published},
tppubtype = {phdthesis}
}
Depression is the most prevalent mental issue in our society, leading to disability and suicide deaths. The COVID-19 pandemic has intensified the need for depression treatment and prevention. While effective, evidence-based psychological treatments for depression exists, only a small percentage of those in need actually receive them. Technology, particularly smartphone-based interventions, can help maximize the reach of these treatments while ensuring their effectiveness, although it comes with challenges, such as high dropout rates. Despite the potential
of this therapy, this is a field that requires considerably more research to fully explore the benefits that smartphones have to offer. Specifically, serious games, designed with a purpose beyond entertainment, have emerged as a promising treatment tool, leveraging advance smartphone capabilities, aligning with psychological treatment principles, and enhancing user engagement.
This dissertation introduces “Horizon: Resilience”, a smartphone-based Serious Game for depressive symptoms. It is a city builder game with a decision making narrative, in which the player (patient) manages a town. The objective is to make the town progress, ensuring the steady inflow of resources and fostering the psychological resilience of its inhabitants. The game is based on the Cognitive Behavioral Therapy (CBT) framework and includes Positive Psychology (PP) techniques. These psychological techniques are woven into the game’s gameplay, feedback, economy system, quests, graphics, and story. Noteworthy is the integration of promoting Physical Activity, detected using the phone’s motion sensors, as part of gameplay. The game draws on the findings of a scoping review on smartphone-based serious games in mental health, and was informed by consultations with therapists as part of a user-centered design. Therapists and patients furthermore provided a qualitative and quantitative evaluation of a Minimum Viable Product (MVP) of the game. Their positive impressions indicate high acceptance and positive expectation regarding the use of the game as an
intervention. Lastly, a pilot randomized controlled trial protocol is outlined to assess its preliminary effectiveness-
of this therapy, this is a field that requires considerably more research to fully explore the benefits that smartphones have to offer. Specifically, serious games, designed with a purpose beyond entertainment, have emerged as a promising treatment tool, leveraging advance smartphone capabilities, aligning with psychological treatment principles, and enhancing user engagement.
This dissertation introduces “Horizon: Resilience”, a smartphone-based Serious Game for depressive symptoms. It is a city builder game with a decision making narrative, in which the player (patient) manages a town. The objective is to make the town progress, ensuring the steady inflow of resources and fostering the psychological resilience of its inhabitants. The game is based on the Cognitive Behavioral Therapy (CBT) framework and includes Positive Psychology (PP) techniques. These psychological techniques are woven into the game’s gameplay, feedback, economy system, quests, graphics, and story. Noteworthy is the integration of promoting Physical Activity, detected using the phone’s motion sensors, as part of gameplay. The game draws on the findings of a scoping review on smartphone-based serious games in mental health, and was informed by consultations with therapists as part of a user-centered design. Therapists and patients furthermore provided a qualitative and quantitative evaluation of a Minimum Viable Product (MVP) of the game. Their positive impressions indicate high acceptance and positive expectation regarding the use of the game as an
intervention. Lastly, a pilot randomized controlled trial protocol is outlined to assess its preliminary effectiveness-
Matey-Sanz, Miguel; Torres-Sospedra, Joaquín; González-Pérez, Alberto; Casteleyn, Sven; Granell-Canut, Carlos
Analysis and Impact of Training Set Size in Cross-Subject Human Activity Recognition Proceedings Article
In: Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications, pp. 391–405, Springer, Cham, 2023, ISBN: 978-3-031-49018-7, (2023-26).
Abstract | Links | BibTeX | Tags: activity recognition, machine learning, smartphone app, smartwatch, symptoms
@inproceedings{Matey2023b,
title = {Analysis and Impact of Training Set Size in Cross-Subject Human Activity Recognition},
author = {Miguel Matey-Sanz and Joaquín Torres-Sospedra and Alberto González-Pérez and Sven Casteleyn and Carlos Granell-Canut},
doi = {https://doi.org/10.1007/978-3-031-49018-7_28},
isbn = {978-3-031-49018-7},
year = {2023},
date = {2023-12-01},
urldate = {2023-12-01},
booktitle = {Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications},
volume = {14469},
pages = {391–405},
publisher = {Springer, Cham},
series = {Lecture Notes in Computer Science},
abstract = {The ubiquity of consumer devices with sensing and computational capabilities, such as smartphones and smartwatches, has increased interest in their use in human activity recognition for healthcare monitoring applications, among others. When developing such a system, researchers rely on input data to train recognition models. In the absence of openly available datasets that meet the model requirements, researchers face a hard and time-consuming process to decide which sensing device to use or how much data needs to be collected. In this paper, we explore the effect of the amount of training data on the performance (i.e., classification accuracy and activity-wise F1-scores) of a CNN model by performing an incremental cross-subject evaluation using data collected from a consumer smartphone and smartwatch. Systematically studying the incremental inclusion of subject data from a set of 22 training subjects, the results show that the model’s performance initially improves significantly with each addition, yet this improvement slows down the larger the number of included subjects. We compare the performance of models based on smartphone and smartwatch data. The latter option is significantly better with smaller sizes of training data, while the former outperforms with larger amounts of training data. In addition, gait-related activities show significantly better results with smartphone-collected data, while non-gait-related activities, such as standing up or sitting down, were better recognized with smartwatch-collected data.},
note = {2023-26},
keywords = {activity recognition, machine learning, smartphone app, smartwatch, symptoms},
pubstate = {published},
tppubtype = {inproceedings}
}
The ubiquity of consumer devices with sensing and computational capabilities, such as smartphones and smartwatches, has increased interest in their use in human activity recognition for healthcare monitoring applications, among others. When developing such a system, researchers rely on input data to train recognition models. In the absence of openly available datasets that meet the model requirements, researchers face a hard and time-consuming process to decide which sensing device to use or how much data needs to be collected. In this paper, we explore the effect of the amount of training data on the performance (i.e., classification accuracy and activity-wise F1-scores) of a CNN model by performing an incremental cross-subject evaluation using data collected from a consumer smartphone and smartwatch. Systematically studying the incremental inclusion of subject data from a set of 22 training subjects, the results show that the model’s performance initially improves significantly with each addition, yet this improvement slows down the larger the number of included subjects. We compare the performance of models based on smartphone and smartwatch data. The latter option is significantly better with smaller sizes of training data, while the former outperforms with larger amounts of training data. In addition, gait-related activities show significantly better results with smartphone-collected data, while non-gait-related activities, such as standing up or sitting down, were better recognized with smartwatch-collected data.
Bravenec, Tomás; Torres-Sospedra, Joaquín; Gould, Michael; Fryza, Tomas
UJI Probes Revisited: Deeper Dive Into the Dataset of Wi-Fi Probe Requests Journal Article
In: IEEE Journal of Indoor and Seamless Positioning and Navigation, vol. 1, pp. 221-230, 2023, ISSN: 2832-7322, (2023-25).
Abstract | Links | BibTeX | Tags: A-wear, dataset, Wi-Fi
@article{Bravenec2023c,
title = {UJI Probes Revisited: Deeper Dive Into the Dataset of Wi-Fi Probe Requests},
author = {Tomás Bravenec and Joaquín Torres-Sospedra and Michael Gould and Tomas Fryza},
doi = {https://doi.org/10.1109/JISPIN.2023.3335882},
issn = {2832-7322},
year = {2023},
date = {2023-11-22},
urldate = {2023-11-22},
journal = {IEEE Journal of Indoor and Seamless Positioning and Navigation},
volume = {1},
pages = {221-230},
publisher = {IEEE},
abstract = {This article centers on the deeper presentation of a new and publicly accessible dataset comprising Wi-Fi probe requests. Probe requests fall within the category of management frames utilized by the 802.11 (Wi-Fi) protocol. Given the ever-evolving technological landscape and the imperative need for up-to-date data, research on probe requests remains essential. In this context, we present a comprehensive dataset encompassing a one-month probe request capture conducted in a university office environment. This dataset accounts for a diverse range of scenarios, including workdays, weekends, and holidays, accumulating over 1 400 000 probe requests. Our contribution encompasses a detailed exposition of the dataset, delving into its critical facets. In addition to the raw packet capture, we furnish a detailed floor plan of the office environment, commonly referred to as a radio map, to equip dataset users with comprehensive environmental information. To safeguard user privacy, all individual user information within the dataset has been anonymized. This anonymization process rigorously balances the preservation of users' privacy with the dataset's analytical utility, rendering it nearly as informative as raw data for research purposes. Furthermore, we demonstrate a range of potential applications for this dataset, including but not limited to presence detection, expanded assessment of temporal received signal strength indicator stability, and evaluation of privacy protection measures. Apart from these, we also include temporal analysis of probe request transmission frequency and period between Wi-Fi scans as well as a peak into possibilities with pattern analysis.},
note = {2023-25},
keywords = {A-wear, dataset, Wi-Fi},
pubstate = {published},
tppubtype = {article}
}
This article centers on the deeper presentation of a new and publicly accessible dataset comprising Wi-Fi probe requests. Probe requests fall within the category of management frames utilized by the 802.11 (Wi-Fi) protocol. Given the ever-evolving technological landscape and the imperative need for up-to-date data, research on probe requests remains essential. In this context, we present a comprehensive dataset encompassing a one-month probe request capture conducted in a university office environment. This dataset accounts for a diverse range of scenarios, including workdays, weekends, and holidays, accumulating over 1 400 000 probe requests. Our contribution encompasses a detailed exposition of the dataset, delving into its critical facets. In addition to the raw packet capture, we furnish a detailed floor plan of the office environment, commonly referred to as a radio map, to equip dataset users with comprehensive environmental information. To safeguard user privacy, all individual user information within the dataset has been anonymized. This anonymization process rigorously balances the preservation of users' privacy with the dataset's analytical utility, rendering it nearly as informative as raw data for research purposes. Furthermore, we demonstrate a range of potential applications for this dataset, including but not limited to presence detection, expanded assessment of temporal received signal strength indicator stability, and evaluation of privacy protection measures. Apart from these, we also include temporal analysis of probe request transmission frequency and period between Wi-Fi scans as well as a peak into possibilities with pattern analysis.
Chukhno, Nadezhda; Orsino, Antonino; Torsner, Johan; Iera, Antonio; Araniti, Giuseppe
5G NR Sidelink Multi-Hop Transmission in Public Safety and Factory Automation Scenarios Journal Article
In: IEEE Network, vol. 37, iss. 5, pp. 129-136, 2023, ISSN: 1558-156X, (2023-12).
Abstract | Links | BibTeX | Tags: 5G, A-wear, Indoor positioning, machine learning
@article{Chukhno2023e,
title = {5G NR Sidelink Multi-Hop Transmission in Public Safety and Factory Automation Scenarios},
author = {Nadezhda Chukhno and Antonino Orsino and Johan Torsner and Antonio Iera and Giuseppe Araniti},
doi = {https://doi.org/10.1109/MNET.124.2100765},
issn = {1558-156X},
year = {2023},
date = {2023-10-01},
urldate = {2023-10-01},
journal = {IEEE Network},
volume = {37},
issue = {5},
pages = {129-136},
publisher = {IEEE},
abstract = {The deployment of D2D communications (also known as ProSe or sidelink transmissions) in cellular networks benefits from proximity, multi-hop, and spatial reuse gains. In this article, we first describe the main advancements of NR sidelink compared to LTE-A sidelink. Then, we run a simulation campaign to test D2D-based ProSe for public safety and factory automation scenarios with their mission-critical requirements and ultra-reliable low-latency communications, respectively. A preliminary study on NR sidelink usage for both considered use cases is performed, aiming to identify the main advantages and disadvantages thereof. Finally, important future directions for the NR sidelink development from a standardization perspective are highlighted.},
note = {2023-12},
keywords = {5G, A-wear, Indoor positioning, machine learning},
pubstate = {published},
tppubtype = {article}
}
The deployment of D2D communications (also known as ProSe or sidelink transmissions) in cellular networks benefits from proximity, multi-hop, and spatial reuse gains. In this article, we first describe the main advancements of NR sidelink compared to LTE-A sidelink. Then, we run a simulation campaign to test D2D-based ProSe for public safety and factory automation scenarios with their mission-critical requirements and ultra-reliable low-latency communications, respectively. A preliminary study on NR sidelink usage for both considered use cases is performed, aiming to identify the main advantages and disadvantages thereof. Finally, important future directions for the NR sidelink development from a standardization perspective are highlighted.
Hammad, Sahibzada Saadoon; Iskandaryan, Ditsuhi; Trilles-Oliver, Sergio
An unsupervised TinyML approach applied to the detection of urban noise anomalies under the smart cities environment Journal Article
In: Internet of Things, vol. 23, pp. 100848, 2023, ISSN: 2542-6605, (2023-20).
Abstract | Links | BibTeX | Tags: environmental monitoring, machine learning, TinyML
@article{Saadoon2023a,
title = {An unsupervised TinyML approach applied to the detection of urban noise anomalies under the smart cities environment},
author = {Sahibzada Saadoon Hammad and Ditsuhi Iskandaryan and Sergio Trilles-Oliver},
doi = {https://doi.org/10.1016/j.iot.2023.100848},
issn = {2542-6605},
year = {2023},
date = {2023-10-01},
urldate = {2023-10-01},
journal = {Internet of Things},
volume = {23},
pages = {100848},
publisher = {Elsevier},
abstract = {Artificial Intelligence of Things (AIoT) is an emerging area of interest, and this can be used to obtain knowledge and take better decisions in the same Internet of Things (IoT) devices. IoT data are prone to anomalies due to various factors such as malfunctioning of sensors, low-cost devices, etc. Following the AIoT paradigm, this work explores anomaly detection in IoT urban noise sensor networks using a Long Short-Term Memory Autoencoder. Two autoencoder models are trained using normal data from two different sensors in the sensor network and tested for the detection of two different types of anomalies, i.e. point anomalies and collective anomalies. The results in terms of accuracy of the two models are 99.99% and 99.34%. The trained model is quantised, converted to TensorFlow Lite format and deployed on the ESP32 microcontroller (MCU). The inference time on the microcontroller is 4 ms for both models, and the power consumption of the MCU is 0.2693 W ± 0.039 and 0.3268 W ± 0.015. Heap memory consumption during the execution of the program for sensors TA120-T246187 and TA120-T246189 is 528 bytes and 744 bytes respectively.},
note = {2023-20},
keywords = {environmental monitoring, machine learning, TinyML},
pubstate = {published},
tppubtype = {article}
}
Artificial Intelligence of Things (AIoT) is an emerging area of interest, and this can be used to obtain knowledge and take better decisions in the same Internet of Things (IoT) devices. IoT data are prone to anomalies due to various factors such as malfunctioning of sensors, low-cost devices, etc. Following the AIoT paradigm, this work explores anomaly detection in IoT urban noise sensor networks using a Long Short-Term Memory Autoencoder. Two autoencoder models are trained using normal data from two different sensors in the sensor network and tested for the detection of two different types of anomalies, i.e. point anomalies and collective anomalies. The results in terms of accuracy of the two models are 99.99% and 99.34%. The trained model is quantised, converted to TensorFlow Lite format and deployed on the ESP32 microcontroller (MCU). The inference time on the microcontroller is 4 ms for both models, and the power consumption of the MCU is 0.2693 W ± 0.039 and 0.3268 W ± 0.015. Heap memory consumption during the execution of the program for sensors TA120-T246187 and TA120-T246189 is 528 bytes and 744 bytes respectively.
Esparza, Juan A. García; Altaba, Pablo; Huerta-Guijarro, Joaquín
Examining urban polarization in five Spanish historic cities through online datasets and onsite perceptions Journal Article
In: Habitat International, vol. 139, pp. 102900, 2023, ISSN: 0197-3975, (2023-28).
Abstract | Links | BibTeX | Tags: citizen participation, local participation
@article{Garcia2023a,
title = {Examining urban polarization in five Spanish historic cities through online datasets and onsite perceptions},
author = {Juan A. García Esparza and Pablo Altaba and Joaquín Huerta-Guijarro},
doi = {https://doi.org/10.1016/j.habitatint.2023.102900},
issn = {0197-3975},
year = {2023},
date = {2023-10-01},
urldate = {2023-10-01},
journal = {Habitat International},
volume = {139},
pages = {102900},
publisher = {Elsevier},
abstract = {At present, the planning and management of historic districts are faced with the challenge of striking a balance between the needs of residents and seasonal pressures from visitors. These socially bustling sites could also benefit from the data cross-referencing of cultural and social patterns in order to identify areas for improvement. This research analyses geo-referenced online datasets and data from social media applications, subsequently contrasting these with onsite data from in-person interviews. These specific variables highlight parallels and conflicts between districts designated World Heritage areas in five Spanish cities. The study provides a quantitative analysis of hotspots and coldspots within the built environment. This is followed by an examination of these two types of areas using qualitative data linked to the three most challenging issues: housing and the built environment; basic services; and cultural services. When analysing the future of historic districts three major challenges to management highlighted in the results should be considered. Firstly, even in socially active districts, imbalances and dysfunctional areas are highlighted by both online data and onsite perceptions. Secondly, the study of the dynamics of districts for observing how stakeholders adapt to this social, economic, and mobility-related polarization. Thirdly, while the study acknowledges the changes to the consumption of culture, there is still potential for improvement in hosting alternative or countercultural movements.},
note = {2023-28},
keywords = {citizen participation, local participation},
pubstate = {published},
tppubtype = {article}
}
At present, the planning and management of historic districts are faced with the challenge of striking a balance between the needs of residents and seasonal pressures from visitors. These socially bustling sites could also benefit from the data cross-referencing of cultural and social patterns in order to identify areas for improvement. This research analyses geo-referenced online datasets and data from social media applications, subsequently contrasting these with onsite data from in-person interviews. These specific variables highlight parallels and conflicts between districts designated World Heritage areas in five Spanish cities. The study provides a quantitative analysis of hotspots and coldspots within the built environment. This is followed by an examination of these two types of areas using qualitative data linked to the three most challenging issues: housing and the built environment; basic services; and cultural services. When analysing the future of historic districts three major challenges to management highlighted in the results should be considered. Firstly, even in socially active districts, imbalances and dysfunctional areas are highlighted by both online data and onsite perceptions. Secondly, the study of the dynamics of districts for observing how stakeholders adapt to this social, economic, and mobility-related polarization. Thirdly, while the study acknowledges the changes to the consumption of culture, there is still potential for improvement in hosting alternative or countercultural movements.
Matey-Sanz, Miguel; Torres-Sospedra, Joaquín; Moreira, Adriano
Temporal Stability on Human Activity Recognition based on Wi-Fi CSI Proceedings Article
In: 2023 IEEE 13th International Conference on Indoor Positioning and Indoor Navigation (IPIN), pp. 1-6, IEEE, 2023, ISBN: 979-8-3503-2012-1, (2023-24).
Abstract | Links | BibTeX | Tags: activity recognition, CSI, machine learning
@inproceedings{Matey2023a,
title = {Temporal Stability on Human Activity Recognition based on Wi-Fi CSI},
author = {Miguel Matey-Sanz and Joaquín Torres-Sospedra and Adriano Moreira},
doi = {https://doi.org/10.1109/IPIN57070.2023.10332214},
isbn = {979-8-3503-2012-1},
year = {2023},
date = {2023-09-25},
urldate = {2023-09-25},
booktitle = {2023 IEEE 13th International Conference on Indoor Positioning and Indoor Navigation (IPIN)},
pages = {1-6},
publisher = {IEEE},
abstract = {Over the last years, numerous studies have emerged using Wi-Fi channel state information, enabling device-free (passive) sensing for applications such as motion detection, indoor positioning or human activity recognition. More recently, the development framework for the low-cost ESP32 microcontrollers has added support for obtaining channel state information data. In this work, we collected channel state information data for human activity recognition, where activities are relatively localized with respect to the Wi-Fi infrastructure. The data was collected in several runs, duly spaced in time, and a convolutional neural network model was used for the classification of activities. Classification performance evaluation showed a clear degradation when a model evaluated with data collected 10 minutes after the data used for training showed a 52% relative loss in the accuracy of the classification.},
note = {2023-24},
keywords = {activity recognition, CSI, machine learning},
pubstate = {published},
tppubtype = {inproceedings}
}
Over the last years, numerous studies have emerged using Wi-Fi channel state information, enabling device-free (passive) sensing for applications such as motion detection, indoor positioning or human activity recognition. More recently, the development framework for the low-cost ESP32 microcontrollers has added support for obtaining channel state information data. In this work, we collected channel state information data for human activity recognition, where activities are relatively localized with respect to the Wi-Fi infrastructure. The data was collected in several runs, duly spaced in time, and a convolutional neural network model was used for the classification of activities. Classification performance evaluation showed a clear degradation when a model evaluated with data collected 10 minutes after the data used for training showed a 52% relative loss in the accuracy of the classification.
Bravenec, Tomás; Torres-Sospedra, Joaquín; Gould, Michael; Fryza, Tomas
UJI Probes: Dataset of Wi-Fi Probe Requests Proceedings Article
In: 2023 13th International Conference on Indoor Positioning and Indoor Navigation (IPIN), pp. 1-6, IEEE, 2023, ISBN: 979-8-3503-2012-1, (2023-25).
Abstract | Links | BibTeX | Tags: A-wear, dataset, Wi-Fi
@inproceedings{Bravenec2023b,
title = {UJI Probes: Dataset of Wi-Fi Probe Requests},
author = {Tomás Bravenec and Joaquín Torres-Sospedra and Michael Gould and Tomas Fryza},
doi = {https://doi.org/10.1109/IPIN57070.2023.10332508},
isbn = {979-8-3503-2012-1},
year = {2023},
date = {2023-09-25},
urldate = {2023-09-25},
booktitle = {2023 13th International Conference on Indoor Positioning and Indoor Navigation (IPIN)},
pages = {1-6},
publisher = {IEEE},
abstract = {This paper focuses on the creation of a new, publicly available Wi-Fi probe request dataset. Probe requests belong to the family of management frames used by the 802.11 (Wi-Fi) protocol. As the situation changes year by year, and technology improves probe request studies are necessary to be done on upto-date data. We provide a month-long probe request capture in an office environment, including work days, weekends, and holidays consisting of over 1 400 000 probe requests. We provide a description of all the important aspects of the dataset. Apart from the raw packet capture we also provide a Radio Map (RM) of the office to ensure the users of the dataset have all the possible information about the environment. To protect privacy, user information in the dataset is anonymized. This anonymization is done in a way that protects the privacy of users while preserving the ability to analyze the dataset to almost the same level as raw data. Furthermore, we showcase several possible use cases for the dataset, like presence detection, temporal Received Signal Strength Indicator (RSSI) stability, and privacy protection evaluation.},
note = {2023-25},
keywords = {A-wear, dataset, Wi-Fi},
pubstate = {published},
tppubtype = {inproceedings}
}
This paper focuses on the creation of a new, publicly available Wi-Fi probe request dataset. Probe requests belong to the family of management frames used by the 802.11 (Wi-Fi) protocol. As the situation changes year by year, and technology improves probe request studies are necessary to be done on upto-date data. We provide a month-long probe request capture in an office environment, including work days, weekends, and holidays consisting of over 1 400 000 probe requests. We provide a description of all the important aspects of the dataset. Apart from the raw packet capture we also provide a Radio Map (RM) of the office to ensure the users of the dataset have all the possible information about the environment. To protect privacy, user information in the dataset is anonymized. This anonymization is done in a way that protects the privacy of users while preserving the ability to analyze the dataset to almost the same level as raw data. Furthermore, we showcase several possible use cases for the dataset, like presence detection, temporal Received Signal Strength Indicator (RSSI) stability, and privacy protection evaluation.