Bing Li, Wei Cui, Wei Wang, Le Zhang, Zhenghua Chen and Min Wu
AAAI , 2021
Publication year: 2021

Recognition of human activities is an important task due to its far-reaching applications such as healthcare system, context-aware applications, and security monitoring. Recent- ly, WiFi based human activity recognition (HAR) is becom- ing ubiquitous due to its non-invasiveness. Existing WiFi- based HAR methods regard WiFi signals as a temporal se- quence of channel state information (CSI), and employ deep sequential models (e.g., RNN, LSTM) to automatically cap- ture channel-over-time features. Although being remarkably effective, they suffer from two major drawbacks. Firstly, the granularity of a single temporal point is blindly elementary for representing meaningful CSI patterns. Secondly, the time- over-channel features are also important, and could be a natu- ral data augmentation. To address the drawbacks, we propose a novel Two-stream Convolution Augmented Human Activi- ty Transformer (THAT) model. Our model proposes to uti- lize a two-stream structure to capture both time-over-channel and channel-over-time features, and use the multi-scale con- volution augmented transformer to capture range-based pat- terns. Extensive experiments on four real experiment datasets demonstrate that our model outperforms state-of-the-art mod- els in terms of both effectiveness and efficiency. Project page is available at


邮箱地址不会被公开。 必填项已用*标注