PLAP: CSI-Based Passive Localization with Amplitude and Phase Information Using CNN and BGRU

With the increasing popularization and development of WiFi devices, nowadays WiFi-based indoor localization has become a hot topic. Traditional Wi-Fi-based technologies which utilize received signal strength indication suffer from multi-path effects result in performance degradation. Therefore, choosing appropriate characteristic is crucial for localization. To improve accuracy, we propose PLAP, passive method using amplitude phase channel state information (CSI). Specifically, Hampel filter used to process signals linear transformation employed calibrating phases. extract representative features calibrated signals, developed deep learning framework combines convolutional neural network (CNN) bi-directional Gated recurrent unit (BGRU) estimate location an objective. The experimental results show that proposed PLAP outperforms other baselines with real-world evaluation.