An Improved CSI Based Device Free Indoor Localization Using Machine Learning Based Classification Approach

Indoor positioning system (IPS) has shown great potentials with the growth of context-aware computing. Typical IPS requires the tracked subject to carry a physical device. In this study, we present MaLDIP, a novel, machine learning based, device free technique for indoor positioning. To design the device free setting, we exploited the Channel State Information (CSI) obtained from Multiple Input Multiple Output Orthogonal Frequency-Division Multiplexing (MIMO-OFDM). The system works by utilizing frequency diversity and spatial diversity properties of CSI at target location by correlating the impact of human presence to certain changes on the received signal features. However, accurate modeling of the effect of a subject on fine grained CSI is challenging due to the presence of multipaths. We propose a novel subcarrier selection method to remove the multipath affected subcarriers to improve the performance of localization. We select the most location-dependent features from channel response based upon the wireless propagation model and propose to apply a machine learning based approach for location estimation, where the localization problem is shifted to a cell identification problem using the Support Vector Machine (SVM) based classifier. Experimental results show that MaLDIP can estimate location in a passive device free setting with a high accuracy using MIMO-OFDM system.