Description
Date depot: 5 octobre 2020
Titre: Indoor localization with Internet of Things, Software Defined Radio, and Machine Learning
Directeur de thèse:
Bruce DENBY (Institut Langevin (EDITE))
Domaine scientifique: Sciences et technologies de l'information et de la communication
Thématique CNRS : Non defini
Resumé: Research on localization techniques in indoor environments, where GPS is not viable, continues to be an active area. Most approaches are based upon location-dependent variations in received signal strength, RSSI, or channel impulse response, CIR, arising in traditional ubiquitous terrestrial radio networks such as WiFi, Bluetooth and cellular communications networks. With the advent of the Internet of Things IoT and connected objects operating over a variety of norms, the indoor radio environment has today become far richer. At the same time, recent developments in software defined radio, SDR, have made this technology an available and attractive tool for exploring unknown and variable radio environments. Finally, over the past several years, the availability of sophisticated machine learning, ML, toolboxes, has transformed research in numerous fields including indoor localization. The thesis project proposes to enhance standard approaches with advances in the fields of IoT, SDR, and ML in order to develop a novel, data-driven, multi-norm system for practical, effective localization of mobile targets in indoor environments.
Doctorant.e: Yang Feifei