Multimode radio fingerprinting for localization

Abstract

We study the feasibility of multimode radio fingerprinting for indoor localization with smart phones. Leveraging the sensing capabilities of these devices (WiFi radio, cellular communications radio, accelerometer, magnetometer), we present an application integrating both offline and online phases of fingerprinting in the same smart phone, and delivering an accuracy of up to 1.5 meters. Moreover, a new approach for the statistical processing of radio signal strengths is utilized, showing that it can outperform existing deterministic techniques. We also examine the possibilities offered by Digital TV (DTV), with the intention to build a multimodal solution for localization.