电子测量与仪器学报

何育浪,赵志彪,李振,李珊珊.基于DSC-SGRU模型的Wi-Fi手势识别系统研究[J].电子测量与仪器学报,2024,38(10):97-108

基于DSC-SGRU模型的Wi-Fi手势识别系统研究

Research on Wi-Fi gesture recognition system based on DSC-SGRU model

DOI：

英文关键词:wireless sensing channel state information deep learning gesture recognition cross-domain

基金项目:国家自然科学基金（62103301）、天津市自然科学基金(22JCQNJC01100)、天津市教育委员会科研项目基金(2020KJ119)和天津市研究生科研创新项目(2022SKYZ296)资助

作者	单位
何育浪	1.天津职业技术师范大学自动化与电气工程学院天津300222； 2.天津市信息传感与智能控制重点实验室天津300222
赵志彪	1.天津职业技术师范大学自动化与电气工程学院天津300222； 2.天津市信息传感与智能控制重点实验室天津300222
李振	1.天津职业技术师范大学自动化与电气工程学院天津300222； 2.天津市信息传感与智能控制重点实验室天津300222
李珊珊	1.天津职业技术师范大学自动化与电气工程学院天津300222； 2.天津市信息传感与智能控制重点实验室天津300222

Author	Institution
He Yulang	1.School of Automation and Electrical Engineering, Tianjin University of Technology and Education, Tianjin 300222,China; 2.Tianjin Key Laboratory of Information Sensing and Intelligent Control, Tianjin 300222,China
Zhao Zhibiao	1.School of Automation and Electrical Engineering, Tianjin University of Technology and Education, Tianjin 300222,China; 2.Tianjin Key Laboratory of Information Sensing and Intelligent Control, Tianjin 300222,China
Li Zhen	1.School of Automation and Electrical Engineering, Tianjin University of Technology and Education, Tianjin 300222,China; 2.Tianjin Key Laboratory of Information Sensing and Intelligent Control, Tianjin 300222,China
Li Shanshan	1.School of Automation and Electrical Engineering, Tianjin University of Technology and Education, Tianjin 300222,China; 2.Tianjin Key Laboratory of Information Sensing and Intelligent Control, Tianjin 300222,China

摘要点击次数: 389

全文下载次数: 1255

中文摘要:

Wi-Fi无线感知技术已成为感知领域的研究热点，能够实现对人体活动和周围环境的智能感知。现有的无线感知模型参数量较大，在移动设备等算力有限的场景中难以实时感知。为此，提出了一种基于深度可分离卷积的轻量级特征提取模块和堆叠的门控循环单元混合的分类识别模型。首先基于深度可分离卷积构建了轻量的特征提取模块，用以捕获人体手势的空间特征，并保持特征的时序性不发生变化；然后使用双层堆叠的GRU网络学习人体手势的时空特征；最后使用开源数据集Widar对模型的性能进行验证，提取CSI信息中的BVP特征以提高跨域场景的识别准确率，并利用加权的损失函数来解决样本不均衡问题。结果表明，提出的模型在跨域场景下准确率达到77.6%，参数量仅有236.891 K。与现有的其他Wi Fi手势识别模型相比，提出的模型在性能基本保持不变的情况下，极大地降低了模型的参数和计算复杂度，为Wi-Fi无线感知技术在实际应用中的推广奠定了基础。

英文摘要:

Wi-Fi wireless sensing technology has become a research hotspot in the field of perception, which can realize intelligent perception of human activities and the surrounding environment. The existing wireless sensing models have a large number of parameters, which makes it difficult to sense in real-time in scenarios with limited computing power such as mobile devices. To this end, a classification and recognition model based on a mixture of a lightweight feature extraction module based on depth-separable convolution and a stacked gated recurrent unit is proposed. Firstly, a lightweight feature extraction module based on depth-separable convolution is constructed to capture the spatial features of human gestures and keep the temporal nature of the features unchanged; then the spatio-temporal features of human gestures are learned using a two-layer stacked GRU network; finally, the performance of the model is validated using the open-source dataset Widar, and the BVP features in the CSI information are extracted to improve the recognition of cross-domain scenes accuracy, and a weighted loss function is utilized to solve the sample imbalance problem. The results show that the proposed model achieves an accuracy of 77.6% in cross-domain scenarios with a parameter count of only 236.891 K. Compared with other existing Wi-Fi gesture recognition models, the proposed model greatly reduces the parameters and computational complexity of the model while its performance remains basically unchanged, which lays a foundation for the popularization of the Wi-Fi wireless sensing technology in practical applications.

查看全文查看/发表评论下载PDF阅读器