WIS: A Technology of Wireless Non-Contact Incremental Training Sensing

Wireless contactless human activity sensing is a new type of sensing method that uses the propagation characteristics of wireless signals to accurately perceive and understand human behavior. However, facing the huge amount of newly generated data and expanding action categories in the sensing process, the traditional model needs to be retrained frequently. This model not only brings significant computational power overhead, but also seriously affects the real-time response speed of the system. To address this problem, this paper proposes a model, WIS (Wireless Incremental Sense), which is composed of two parts. The first part is the basic sensing module NFFCN (Nearest Neighbor Feature Fusion Classification). NFFCN is a fusion classification method based on Nearest Class Mean (NCM) classifier and Random Forest (RF). By combining the local feature extraction ability of NCM and the integrated learning advantage of RF, this method can efficiently extract human behavior features from wireless signals and achieve high-precision classification. The second part is the incremental learning module NFFCN-RTST, which uses the retraining subtree (RTST) incremental strategy to optimize the model. Unlike update leaf statistics (ULS) and the Incrementally Grow Tree (IGT) incremental strategy, RTST not only updates the statistical data of leaf nodes but also dynamically adjusts the previously learned splitting function, so as to better adapt to new data and categories. In the experimental validation on the rRuler and Stan WiFi datasets, the average recognition accuracy of NFFCN reaches 87.1% and 98.4%, respectively. In the class-incremental experimental validation, the recognition accuracy of WIS reaches 87% and 95%, respectively.