WiFi-based human activity recognition (HAR) leveraging channel state information (CSI) faces challenges due to multipath effects, leading to ambiguous feature representation. To address this, we propose AMCS-TCN, a model integrating dual attention mechanisms and a multi-channel, multi-scale temporal convolutional network (TCN). This model utilizes spatial diversity from MIMO systems to enhance feature representation. The dual attention module, comprising feature map fusion attention (FMFA) and Feature Channel Attention (FCA), adaptively focuses on discriminative information. Experimental results on a public dataset and real-world environments show an average accuracy of 98.85% and robust performance in complex settings. Our code and models are released at https://github.com/boyuanzhang759-rgb/AMCS-TCN-by-BoYuan for reproduction.
Zhang et al. (Tue,) studied this question.