Bibliographic citations
Lovón, J., (2018). Técnicas para la localización en interiores basado en Bluetooth-Fingerprinting mediante algoritmos de inteligencia artificial [Tesis, Universidad Nacional de Ingeniería]. http://hdl.handle.net/20.500.14076/15999
Lovón, J., Técnicas para la localización en interiores basado en Bluetooth-Fingerprinting mediante algoritmos de inteligencia artificial [Tesis]. : Universidad Nacional de Ingeniería; 2018. http://hdl.handle.net/20.500.14076/15999
@misc{renati/263425,
title = "Técnicas para la localización en interiores basado en Bluetooth-Fingerprinting mediante algoritmos de inteligencia artificial",
author = "Lovón Melgarejo, Jesús Enrique",
publisher = "Universidad Nacional de Ingeniería",
year = "2018"
}
Currently, geolocation allows to provide better services in a personalized way to each user, mainly through the use of ubiquitous technologies such as GPS. However, this is limited when it is not in the line of sight of satellites, losing accuracy and performance, being useless in problems such as determining the location of a user in a multi floor building. Due to the massive use of Smartphones in today’s society, which incorporate several peripherals such as Bluetooth technology, in this thesis we study in depth the problem of indoor localization; analyzing its characteristics, difficulties and variables. To this aim, the technology BLE4.0 is used, which is a lighter and energy-saving protocol compared to conventional Bluetooth; the position is determined using as source the RSSI, which is issued by devices known as Beacons. Trilateration techniques are applied under a radiopropagation model, based on the Rappaport equation; and fingerprinting, using Machine Learning algorithms to perform classification: SVM and k-NN. These techniques were applied and analyzed in different physical experimentation spaces, recognizing the criteria that play an important role when performing a deployment and configuration on the environment for indoor localization. Finally, a novel method is proposed to recognize the best configuration of the environment to be used in order to improve the precision of this technique.
This item is licensed under a Creative Commons License