Convolutional neural network and dual-factor enhanced variational Bayes adaptive Kalman filter based indoor localization with Wi-Fi

Various research works have been proposed for Wi-Fi-based indoor localization, including Received Signal Strength Indicator (RSSI)-based fingerprint algorithm, Angle of Arrival (AoA)-based algorithm and so on. However, since RSSI value cannot accurately express the spatial features of emitted wireless signal, and the interfering noise in indoor environment makes the wireless signal distortion, RSSI-based localization algorithm cannot achieve an ideal accuracy. In this paper, we utilize Channel State Information (CSI) extracted from MIMO-OFDM PHY layer as fingerprint image to express the spatial and temporal features of Wi-Fi signal. At the same time, an indoor localization algorithm is also proposed, which is based on convolutional neural network and dual-factor enhanced variational Bayes adaptive Kalman filter, to achieve accurate position estimate with time-varying measurement noise and process noise in complex indoor environment. According to the simulation results, compared with existing methods, our proposed algorithm improves the positioning accuracy up to 51.8%. In the real indoor environment, our proposed algorithm improves the positioning accuracy up to 22% in LoS scenario, and 9.8% in NLoS scenario, respectively.