Gesture recognition method based on misalignment mean absolute deviation and KL divergence

Abstract At present, it has become very convenient to collect channel state information (CSI) from ubiquitous commercial WiFi network cards, and the location or activity of a human who affects CSI can be recognized by analyzing change CSI. Therefore, wireless sensing technology based on received widespread attention. However, existing CSI-based gesture recognition methods still have some problems, which include that subcarrier selection is not optimized motion interval extraction accurate enough, so accuracy needs further improved. In response above method misalignment mean absolute deviation (MMAD) KL divergence proposed in paper, called MMAD-KL-GR method. This uses MMAD algorithm extract amplitude intervals containing information, then selects subcarriers comparing amplitude, finally subspace K-nearest neighbor (KNN) recognize gestures. Several experiments show effectively improve recognition.