期刊
IEEE INTERNET OF THINGS JOURNAL
卷 8, 期 24, 页码 17345-17355出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/JIOT.2021.3080401
关键词
Generators; Internet of Things; Data models; Activity recognition; Training; Distributed databases; Boosting; Channel state information (CSI); convolutional neural network (CNN); generative adversarial networks (GANs); human behavior recognition; transfer learning
资金
- Agency for Science, Technology and Research, Singapore (A*STAR), under the A*STAR Graduate Scholarship scheme
The article proposes a multimodal channel state information-based activity recognition system, which uses generative adversarial networks and semi-supervised learning to address performance degradation in WiFi human recognition systems due to environmental dynamics. Experimental results demonstrate that the system performs well in multiple experimental settings, overcoming environmental dynamics and outperforming existing HAR systems.
Channel state information (CSI)-based human activity recognition (HAR) has received great attention in recent years due to its advantages in privacy protection, insensitivity to illumination, and no requirement for wearable devices. In this article, we propose a multimodal channel state information-based activity recognition (MCBAR) system that leverages existing WiFi infrastructures and monitors human activities from CSI measurements. MCBAR aims to address the performances degradation of WiFi-based human recognition systems due to environmental dynamics. Specifically, we address the issue of nonuniformly distributed unlabeled data with rarely performed activities by taking advantages of the generative adversarial network (GAN) and semisupervised learning. We apply a multimodal generator to approximate the CSI data distribution in different environment settings with limited measured CSI data. The generated CSI data using the multimodal generator can provide better diversity for knowledge transfer. This multimodal generator improves the ability of MCBAR to recognize specific activities with various CSI patterns caused by environmental dynamics. Compared to state-of-the-art CSI-based recognition systems, MCBAR is more robust as it is able to handle the nonuniformly distributed CSI data collected from a new environment setting. In addition, diverse generated data from the multimodal generator improves the stability of the system. We have tested MCBAR under multiple experimental settings at different places. The experimental results demonstrate that our algorithm overcomes environmental dynamics and outperforms existing HAR systems.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据