Supervised learning algorithms for indoor localization fingerprinting using BLE4.0 beacons

Jesús Lovón-Melgarejo, Manuel Castillo-Cara, Gusseppe Bravo-Rocca, Luis Orozco-Barbosa, Ismael García-Varea

Producción científica: Capítulo del libro/informe/acta de congresoArticulo (Contribución a conferencia)revisión exhaustiva

8 Citas (Scopus)

Resumen

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.

Idioma originalInglés
Título de la publicación alojada2017 IEEE Latin American Conference on Computational Intelligence, LA-CCI 2017 - Proceedings
EditorialInstitute of Electrical and Electronics Engineers Inc.
Páginas1-6
Número de páginas6
ISBN (versión digital)9781538637340
DOI
EstadoPublicada - 7 feb. 2018
Publicado de forma externa
Evento2017 IEEE Latin American Conference on Computational Intelligence, LA-CCI 2017 - Arequipa, Perú
Duración: 8 nov. 201710 nov. 2017

Serie de la publicación

Nombre2017 IEEE Latin American Conference on Computational Intelligence, LA-CCI 2017 - Proceedings
Volumen2017-November

Conferencia

Conferencia2017 IEEE Latin American Conference on Computational Intelligence, LA-CCI 2017
País/TerritorioPerú
CiudadArequipa
Período8/11/1710/11/17

Huella

Profundice en los temas de investigación de 'Supervised learning algorithms for indoor localization fingerprinting using BLE4.0 beacons'. En conjunto forman una huella única.

Citar esto