2020
Torres-Sospedra, Joaquín; Quezada-Gaibor, Darwin; Mendoza-Silva, Germán Martín; Nurmi, Jari; Koucheryavy, Yevgeni; Huerta-Guijarro, Joaquín
New Cluster Selection and Fine-grained Search for k-Means Clustering and Wi-Fi Fingerprinting Proceedings Article
In: 2020 International Conference on Localization and GNSS (ICL-GNSS), Tampere, Finland, 2020, pp. 1-6, IEEE, 2020, ISBN: 978-1-7281-6455-7.
Abstract | Links | BibTeX | Tags: A-wear, Indoor positioning, Wi-Fi fingerprint
@inproceedings{Torres-Sospedra2020,
title = {New Cluster Selection and Fine-grained Search for k-Means Clustering and Wi-Fi Fingerprinting},
author = {Joaquín Torres-Sospedra and Darwin Quezada-Gaibor and Germán Martín Mendoza-Silva and Jari Nurmi and Yevgeni Koucheryavy and Joaquín Huerta-Guijarro},
doi = {http://www.doi.org/10.1109/ICL-GNSS49876.2020.9115419 },
isbn = {978-1-7281-6455-7},
year = {2020},
date = {2020-07-02},
booktitle = {2020 International Conference on Localization and GNSS (ICL-GNSS), Tampere, Finland, 2020},
pages = {1-6},
publisher = {IEEE},
abstract = {Wi-Fi fingerprinting is a popular technique for Indoor Positioning Systems (IPSs) thanks to its low complexity and the ubiquity of WLAN infrastructures. However, this technique
may present scalability issues when the reference dataset (radio map) is very large. To reduce the computational costs, k-Means Clustering has been successfully applied in the past. However, it is a general-purpose algorithm for unsupervised classification. This paper introduces three variants that apply heuristics based on radio propagation knowledge in the coarse and fine-grained searches. Due to the heterogeneity either in the IPS side (including radio map generation) and in the network infrastructure, we used an evaluation framework composed of 16 datasets. In terms of general positioning accuracy and computational costs, the best proposed k-means variant provided better general positioning
accuracy and a significantly better computational cost –around 40% lower– than the original k-means.},
keywords = {A-wear, Indoor positioning, Wi-Fi fingerprint},
pubstate = {published},
tppubtype = {inproceedings}
}
Wi-Fi fingerprinting is a popular technique for Indoor Positioning Systems (IPSs) thanks to its low complexity and the ubiquity of WLAN infrastructures. However, this technique
may present scalability issues when the reference dataset (radio map) is very large. To reduce the computational costs, k-Means Clustering has been successfully applied in the past. However, it is a general-purpose algorithm for unsupervised classification. This paper introduces three variants that apply heuristics based on radio propagation knowledge in the coarse and fine-grained searches. Due to the heterogeneity either in the IPS side (including radio map generation) and in the network infrastructure, we used an evaluation framework composed of 16 datasets. In terms of general positioning accuracy and computational costs, the best proposed k-means variant provided better general positioning
accuracy and a significantly better computational cost –around 40% lower– than the original k-means.
may present scalability issues when the reference dataset (radio map) is very large. To reduce the computational costs, k-Means Clustering has been successfully applied in the past. However, it is a general-purpose algorithm for unsupervised classification. This paper introduces three variants that apply heuristics based on radio propagation knowledge in the coarse and fine-grained searches. Due to the heterogeneity either in the IPS side (including radio map generation) and in the network infrastructure, we used an evaluation framework composed of 16 datasets. In terms of general positioning accuracy and computational costs, the best proposed k-means variant provided better general positioning
accuracy and a significantly better computational cost –around 40% lower– than the original k-means.
Furfari, Francesco; Crivello, Antonino; Baronti, Paolo; Barsocchi, Paolo; Girolami, Michele; Palumbo, Filippo; Quezada-Gaibor, Darwin; Mendoza-Silva, Germán Martín; Torres-Sospedra, Joaquín
Discovering location based services: A unified approach for heterogeneous indoor localization systems Journal Article
In: Internet of Things, vol. 13, pp. 100334, 2020, ISSN: 2542-6605.
Abstract | Links | BibTeX | Tags: A-wear, Indoor localization
@article{Furfari2020,
title = {Discovering location based services: A unified approach for heterogeneous indoor localization systems},
author = {Francesco Furfari and Antonino Crivello and Paolo Baronti and Paolo Barsocchi and Michele Girolami and Filippo Palumbo and Darwin Quezada-Gaibor and Germán Martín Mendoza-Silva and Joaquín Torres-Sospedra },
doi = {https://doi.org/10.1016/j.iot.2020.100334 },
issn = {2542-6605},
year = {2020},
date = {2020-02-04},
urldate = {2020-02-04},
journal = {Internet of Things},
volume = {13},
pages = {100334},
abstract = {The technological solutions and communication capabilities offered by the Internet of Things paradigm, in terms of raising availability of wearable devices, the ubiquitous internet connection, and the presence on the market of service-oriented solutions, have allowed a wide proposal of Location Based Services (LBS). In a close future, we foresee that companies and service providers will have developed reliable solutions to address indoor positioning, as basis for useful location based services. These solutions will be different from each other and they will adopt different hardware and processing techniques. This paper describes the proposal of a unified approach for Indoor Localization Systems that enables the cooperation between heterogeneous solutions and their functional modules. To this end, we designed an integrated architecture that, abstracting its main components, allows a seamless interaction among them. Finally, we present a working prototype of such architecture, which is based on the popular Telegram application for Android, as an integration demonstrator. The integration of the three main phases –namely the discovery phase, the User Agent self-configuration, and the indoor map retrieval/rendering– demonstrates the feasibility of the proposed integrated architecture.},
keywords = {A-wear, Indoor localization},
pubstate = {published},
tppubtype = {article}
}
The technological solutions and communication capabilities offered by the Internet of Things paradigm, in terms of raising availability of wearable devices, the ubiquitous internet connection, and the presence on the market of service-oriented solutions, have allowed a wide proposal of Location Based Services (LBS). In a close future, we foresee that companies and service providers will have developed reliable solutions to address indoor positioning, as basis for useful location based services. These solutions will be different from each other and they will adopt different hardware and processing techniques. This paper describes the proposal of a unified approach for Indoor Localization Systems that enables the cooperation between heterogeneous solutions and their functional modules. To this end, we designed an integrated architecture that, abstracting its main components, allows a seamless interaction among them. Finally, we present a working prototype of such architecture, which is based on the popular Telegram application for Android, as an integration demonstrator. The integration of the three main phases –namely the discovery phase, the User Agent self-configuration, and the indoor map retrieval/rendering– demonstrates the feasibility of the proposed integrated architecture.