2022
Quezada-Gaibor, Darwin; Klus, Lucie; Torres-Sospedra, Joaquín; Lohan, Elena Simona; Nurmi, Jari; Granell-Canut, Carlos; Huerta-Guijarro, Joaquín
Data Cleansing for Indoor Positioning Wi-Fi Fingerprinting Datasets Proceedings Article
In: 2022 23rd IEEE International Conference on Mobile Data Management (MDM), pp. 349-354, IEEE, 2022, ISBN: 978-1-6654-5176-5.
Abstract | Links | BibTeX | Tags: Data science, Indoor positioning, Wi-Fi fingerprint
@inproceedings{Quezada2022c,
title = {Data Cleansing for Indoor Positioning Wi-Fi Fingerprinting Datasets},
author = {Darwin Quezada-Gaibor and Lucie Klus and Joaquín Torres-Sospedra and Elena Simona Lohan and Jari Nurmi and Carlos Granell-Canut and Joaquín Huerta-Guijarro},
doi = {https://doi.org/10.1109/MDM55031.2022.00079},
isbn = {978-1-6654-5176-5},
year = {2022},
date = {2022-06-10},
booktitle = {2022 23rd IEEE International Conference on Mobile Data Management (MDM)},
pages = {349-354},
publisher = {IEEE},
abstract = {Wearable and IoT devices requiring positioning and localisation services grow in number exponentially every year. This rapid growth also produces millions of data entries that need to be pre-processed prior to being used in any indoor positioning system to ensure the data quality and provide a high Quality of Service (QoS) to the end-user. In this paper, we offer a novel and straightforward data cleansing algorithm for WLAN fingerprinting radio maps. This algorithm is based on the correlation among fingerprints using the Received Signal Strength (RSS) values and the Access Points (APs)'s identifier. We use those to compute the correlation among all samples in the dataset and remove fingerprints with low level of correlation from the dataset. We evaluated the proposed method on 14 independent publicly-available datasets. As a result, an average of 14% of fingerprints were removed from the datasets. The 2D positioning error was reduced by 2.7% and 3D positioning error by 5.3% with a slight increase in the floor hit rate by 1.2% on average. Consequently, the average speed of position prediction was also increased by 14%.},
keywords = {Data science, Indoor positioning, Wi-Fi fingerprint},
pubstate = {published},
tppubtype = {inproceedings}
}
Wearable and IoT devices requiring positioning and localisation services grow in number exponentially every year. This rapid growth also produces millions of data entries that need to be pre-processed prior to being used in any indoor positioning system to ensure the data quality and provide a high Quality of Service (QoS) to the end-user. In this paper, we offer a novel and straightforward data cleansing algorithm for WLAN fingerprinting radio maps. This algorithm is based on the correlation among fingerprints using the Received Signal Strength (RSS) values and the Access Points (APs)'s identifier. We use those to compute the correlation among all samples in the dataset and remove fingerprints with low level of correlation from the dataset. We evaluated the proposed method on 14 independent publicly-available datasets. As a result, an average of 14% of fingerprints were removed from the datasets. The 2D positioning error was reduced by 2.7% and 3D positioning error by 5.3% with a slight increase in the floor hit rate by 1.2% on average. Consequently, the average speed of position prediction was also increased by 14%.
Granell-Canut, Carlos; Mooney, Peter; Jirka, Simon; Rieke, Matthes; Ostermann, Frank O; Broecke, Just Van Den; Sarretta, Alessandro; Verhulst, Stefaan; Dencik, Lina; Oost, Hillen; Micheli, Marina; Minghini, Marco; Kotsev, Alexander; Schade, Sven
Emerging approaches for data-driven innovation in Europe Book
Publications Office of the European Union, Luxemburg, 2022, ISBN: 978-92-76-46937-7.
Abstract | Links | BibTeX | Tags: Data science, Data spaces, Europe, Geographic data
@book{Granell2022a,
title = {Emerging approaches for data-driven innovation in Europe},
author = {Carlos Granell-Canut and Peter Mooney and Simon Jirka and Matthes Rieke and Frank O Ostermann and Just Van Den Broecke and Alessandro Sarretta and Stefaan Verhulst and Lina Dencik and Hillen Oost and Marina Micheli and Marco Minghini and Alexander Kotsev and Sven Schade},
url = {https://publications.jrc.ec.europa.eu/repository/handle/JRC127730},
doi = {https://doi.org/10.2760/630723},
isbn = {978-92-76-46937-7},
year = {2022},
date = {2022-01-15},
number = {JRC127730},
publisher = {Publications Office of the European Union},
address = {Luxemburg},
abstract = {Europe’s digital transformation of the economy and society is one of the priorities of the current Commission and is framed by the European strategy for data. This strategy aims at creating a single market for data through the establishment of a common European data space, based in turn on domain-specific data spaces in strategic sectors such as environment, agriculture, industry, health and transportation. Acknowledging the key role that emerging technologies and innovative approaches for data sharing and use can play to make European data spaces a reality, this document presents a set of experiments that explore emerging technologies and tools for data-driven innovation, and also deepen in the socio-technical factors and forces that occur in data-driven innovation. Experimental results shed some light in terms of lessons learned and practical recommendations towards the establishment of European data spaces.},
keywords = {Data science, Data spaces, Europe, Geographic data},
pubstate = {published},
tppubtype = {book}
}
Europe’s digital transformation of the economy and society is one of the priorities of the current Commission and is framed by the European strategy for data. This strategy aims at creating a single market for data through the establishment of a common European data space, based in turn on domain-specific data spaces in strategic sectors such as environment, agriculture, industry, health and transportation. Acknowledging the key role that emerging technologies and innovative approaches for data sharing and use can play to make European data spaces a reality, this document presents a set of experiments that explore emerging technologies and tools for data-driven innovation, and also deepen in the socio-technical factors and forces that occur in data-driven innovation. Experimental results shed some light in terms of lessons learned and practical recommendations towards the establishment of European data spaces.
2018
Nüst, Daniel; Granell-Canut, Carlos; Hofer, Barbara; Konkol, Markus; Ostermann, Frank O; Sileryte, Rusne; Cerutti, Valentina
Reproducible research and GIScience: an evaluation using AGILE conference papers Journal Article
In: PeerJ, vol. 6, pp. e5072, 2018, ISSN: 2167-8359.
Links | BibTeX | Tags: AGILE, Data science, GIScience, Open access, Open science, Reproducible research
@article{Granell2018,
title = {Reproducible research and GIScience: an evaluation using AGILE conference papers},
author = {Daniel Nüst and Carlos Granell-Canut and Barbara Hofer and Markus Konkol and Frank O Ostermann and Rusne Sileryte and Valentina Cerutti},
url = {https://doi.org/10.7717/peerj.5072},
doi = {10.7717/peerj.5072},
issn = {2167-8359},
year = {2018},
date = {2018-01-01},
journal = {PeerJ},
volume = {6},
pages = {e5072},
keywords = {AGILE, Data science, GIScience, Open access, Open science, Reproducible research},
pubstate = {published},
tppubtype = {article}
}