A lightweight attention deep learning method for human-vehicle recognition based on wireless sensing technology

Mingxin Song; Rensheng Zhu; Xinquan Chen; Chunlei Zheng; Liangliang Lou

doi:10.3389/fnins.2023.1135986

A lightweight attention deep learning method for human-vehicle recognition based on wireless sensing technology

Front Neurosci. 2023 Feb 9:17:1135986. doi: 10.3389/fnins.2023.1135986. eCollection 2023.

Authors

Mingxin Song^{1

2}, Rensheng Zhu³, Xinquan Chen^{1

2}, Chunlei Zheng⁴, Liangliang Lou¹

Affiliations

¹ Institute of Intelligent Information Processing, Taizhou University, Taizhou, Zhejiang, China.
² School of Science, Zhejiang University of Science and Technology, Hangzhou, Zhejiang, China.
³ China United Network Communications Co., Ltd., Taizhou Branch, Taizhou, Zhejiang, China.
⁴ Key Laboratory of Wireless Sensor Networks and Communications, Shanghai Institute of Microsystem and Information Technology, Shanghai, China.

Abstract

Wireless sensing-based human-vehicle recognition (WiHVR) methods have become a hot spot for research due to its non-invasiveness and cost-effective advantages. However, existing WiHVR methods shows limited performance and slow execution time on human-vehicle classification task. To address this issue, a lightweight wireless sensing attention-based deep learning model (LW-WADL) is proposed, which consists of a CBAM module and several depthwise separable convolution blocks in series. LW-WADL takes raw channel state information (CSI) as input, and extracts the advanced features of CSI by jointly using depthwise separable convolution and convolutional block attention mechanism (CBAM). Experimental results show that the proposed model achieves 96.26% accuracy on the constructed CSI-based dataset, and the model size is only 5.89% of the state of the art (SOTA) model. The results demonstrate that the proposed model achieves better performance on WiHVR tasks while reducing the model size compared to SOTA model.

Keywords: attention mechanism; channel status information; depthwise separable convolution; human-vehicle recognition; wireless sensing.

Grants and funding

This work was supported by Zhejiang Provincial National Science Foundation of China under Grant No. LGG22F030009 and partially supported by Taizhou Science and Technology Plan Project under Grant No. 21gya29.