PROJECT TITLE :

Automatic Radio Map Adaptation for Indoor Localization Using Smartphones - 2018

ABSTRACT:

The proliferation of mobile computing has prompted WiFi-primarily based indoor localization to be one of the most enticing and promising techniques for ubiquitous applications. A primary concern for these technologies to be absolutely practical is to combat harsh indoor environmental dynamics, especially for long-term deployment. Despite varied research on WiFi fingerprint-based mostly localization, the matter of radio map adaptation has not been sufficiently studied and remains open. In this work, we propose AcMu, an automatic and continuous radio map self-updating service for wireless indoor localization that exploits the static behaviors of mobile devices. By accurately pinpointing mobile devices with a completely unique trajectory matching algorithm, we tend to employ them as mobile reference points to collect real-time RSS samples after they are static. With these contemporary reference information, we adapt the whole radio map by learning an underlying relationship of RSS dependency between completely different locations, that is anticipated to be comparatively constant over time. Extensive experiments for 20 days across six months demonstrate that AcMu effectively accommodates RSS variations over time and derives correct prediction of fresh radio map with average errors of less than 5dB, outperforming existing approaches. Moreover, AcMu provides 2x improvement on localization accuracy by maintaining an up-to-date radio map.