WiFi-Based Indoor Human Activity Sensing: A Selective Sensing Strategy and a Multilevel Feature Fusion Approach

Utilizing communication signals for indoor human activity sensing (HAS) is an important component of integrated sensing and communication (ISAC). The current majority HAS solutions adopt a single sensing strategy and only work in a simple environment. In this article, we propose a new HAS method named WiSMLF that can flexibly select multiple sensing strategies and then use multilevel feature fusion for sensing. We first use the high-frequency energy (HFE) method to categorize human activities into two types: 1) static activities (SAs) and 2) moving activities (MAs). Subsequently, for SAs, we adopt a joint localization and activity recognition sensing strategy, and use a multilevel feature fusion network based on visual geometry group (VGG). For MAs, we adopt a joint activity recognition and moving distance estimation sensing strategy, and use a multilevel feature fusion network based on long short-term memory (LSTM). The experimental results show that WiSMLF outperforms the existing methods especially in complex environments, and can obtain 92% higher accuracy in location, activity recognition, and distance estimation.