Smartphone-Based Indoor Localization via Network Learning With Fusion of FTM/RSSI Measurements
Paulson Eberechukwu Numan, Hyunwoo Park, Christos Laoudias, Seppo Horsmanheimo, Sunwoo Kim
Abstract
This letter proposes a deep neural network (DNN)-based indoor localization approach that leverages WiFi Fine Timing Measurement (FTM) and Received Signal Strength Indicator (RSSI) as environment features to provide accurate location estimation. Our method uses DNN with raw FTM and RSSI measurements for self-learning and produces enhanced ranging information in the presence of measurement noise. Experimental data was obtained from real-world settings using commercial off-the-shelf devices in two different indoor office environments. The proposed solution was evaluated regarding the localization Mean Squared Error, demonstrating remarkable accuracy and outperforming state-of-the-art methods.