Device-Free Indoor Localization Using Wi-Fi Channel State Information for Internet of Things

Abstract

This paper proposes an economical, nonintrusive, and high-precision indoor localization scheme based on Wi-Fi fingerprinting that requires only a single Wi- Fi access point and a single fixed-location receiver. A deep neural network (DNN) based classification model is trained with Wi-Fi channel state information (CSI) fingerprints for localizing the target without any device attached (i.e., device-free). CSI provides finer-grained information than received signal strength (RSS). CSI pre- processing based on singular value decomposition (SVD), as well as data augmentation based on noise injection and inter-person interpolation, are incorporated into the proposed DNN framework for enhanced robustness and performance. Real-world experiments examine two scenarios with different degrees of target similarity and show that the proposed DNN-based system can consistently improve the localization performance as compared to the original DNN model.