WiFi Fingerprinting based Indoor Localization: When CSI Tensor meets Deep Residual Sharing Learning

Abstract

Location-based services (LBS) nowadays have several consumer applications such as indoor localization. Wi-Fi based indoor localization has attracted interest due to the ubiquitous access in indoor environments. In this paper, we propose ResLoc, a deep residual sharing learning based system for indoor localization with channel state information (CSI) tensor data. First, we introduce CSI data in wireless systems and discuss how to build CSI tensor data for indoor localization. Then, we design the ResLoc system, which employs two channels CSI tensor data to train the deep network by using the proposed deep residual sharing learning in the offline phase. For online test phase, we use newly received CSI tensor data to estimate the location of the mobile device based on the enhanced probabilistic method. Finally, the experimental results show the proposed ResLoc system can obtain the decimeter level localization accuracy.