TY - GEN
T1 - Supervised learning algorithms for indoor localization fingerprinting using BLE4.0 beacons
AU - Lovón-Melgarejo, Jesús
AU - Castillo-Cara, Manuel
AU - Bravo-Rocca, Gusseppe
AU - Orozco-Barbosa, Luis
AU - García-Varea, Ismael
N1 - Publisher Copyright:
© 2017 IEEE.
Copyright:
Copyright 2018 Elsevier B.V., All rights reserved.
PY - 2018/2/7
Y1 - 2018/2/7
N2 - The increasing interest on deploying ubiquitous context-based services has spurred the need of developing indoor localization mechanisms. Such systems should take advantage of the large amount of wireless networks and radio interfaces already incorporated in most mobile consumer devices. Among the existing radio interfaces, Bluetooth Low Energy (BLE) 4.0 is called to play a major role in the deployment of energy efficient ubiquitous services. In this paper, we first show that the high sensitivity of BLE4.0 to fast fading makes infeasible the use of radio propagation models to directly estimate the distance between a reference transmitter and the mobile device. We then explore the use of supervised learning algorithms towards the development of radio maps of beacons analysing in-depth two metrics accuracy and mean error. Our approach also explores two main parameters: (i) Transmission power (Tx) of the BLE4.0 beacons; and (ii) Physical characteristics of the area. Based on our results, we argue that the mean error can be improved up to 28% configuring the two main parameters.
AB - The increasing interest on deploying ubiquitous context-based services has spurred the need of developing indoor localization mechanisms. Such systems should take advantage of the large amount of wireless networks and radio interfaces already incorporated in most mobile consumer devices. Among the existing radio interfaces, Bluetooth Low Energy (BLE) 4.0 is called to play a major role in the deployment of energy efficient ubiquitous services. In this paper, we first show that the high sensitivity of BLE4.0 to fast fading makes infeasible the use of radio propagation models to directly estimate the distance between a reference transmitter and the mobile device. We then explore the use of supervised learning algorithms towards the development of radio maps of beacons analysing in-depth two metrics accuracy and mean error. Our approach also explores two main parameters: (i) Transmission power (Tx) of the BLE4.0 beacons; and (ii) Physical characteristics of the area. Based on our results, we argue that the mean error can be improved up to 28% configuring the two main parameters.
KW - Beacon
KW - Bluetooth
KW - Indoor localization
KW - signal processing
KW - supervised learning
UR - http://www.scopus.com/inward/record.url?scp=85050383658&partnerID=8YFLogxK
U2 - 10.1109/LA-CCI.2017.8285716
DO - 10.1109/LA-CCI.2017.8285716
M3 - Articulo (Contribución a conferencia)
AN - SCOPUS:85050383658
T3 - 2017 IEEE Latin American Conference on Computational Intelligence, LA-CCI 2017 - Proceedings
SP - 1
EP - 6
BT - 2017 IEEE Latin American Conference on Computational Intelligence, LA-CCI 2017 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2017 IEEE Latin American Conference on Computational Intelligence, LA-CCI 2017
Y2 - 8 November 2017 through 10 November 2017
ER -