WiAnti: an Anti-interference Activity Recognition System based on WiFi CSI

As an important technology in the field of Internet of Things, activity recognition is a well-researched topic. Due to its characteristics of no-invasion, no privacy leakage, high recognition rate, and good user experience, Channel State Information (CSI)-based is a great approach to solve the activity recognition problem. However, commodity WiFi devices for identification are usually in a complex electromagnetic environment, where the interference caused by WiFi devices from channel overlap is the most severe. To solve the above problem, we propose WiAnti, a CSI-based activity recognition system which is robust to cochannel Interference. By adaptive subcarrier selection, WiAnti can achieve activity recognition with high accuracy. As demonstrated by experimental results, in the same scenario with cochannel interference, WiAnti yields 95.865% activity recognition accuracy rate on average, which improve the recognition rate by 8% on average over WiFall.