ZTE Communications ›› 2023, Vol. 21 ›› Issue (4): 60-68.DOI: 10.12142/ZTECOM.202304008

• Research Papers • Previous Articles     Next Articles

Research on Fall Detection System Based on Commercial Wi-Fi Devices

GONG Panyin1, ZHANG Guidong1, ZHANG Zhigang2,3, CHEN Xiao2,3, DING Xuan1()   

  1. 1.School of software, Tsinghua University, Beijing 100084, China
    2.ZTE Corporation, Shenzhen 518057, China
    3.State Key Laboratory of Mobile Network and Mobile Multimedia Technology, Shenzhen 518055, China
  • Received:2023-04-07 Online:2023-12-25 Published:2023-12-07
  • About author:GONG Panyin received his bachelor’s degree in software engineering from Huazhong University of Science and Technology, China in 2018 and is currently studying for a master’s degree in the School of Software, Tsinghua University, China. His research interests include the Internet of Things and wireless sensing.
    ZHANG Guidong received his BE degree from the Department of Electronic Engineering and Information Science, University of Science and Technology of China in 2018. He is currently working toward his PhD degree with the School of Software, Tsinghua University. His research interests include wireless sensing and mobile computing.
    ZHANG Zhigang graduated from Xi’an Jiaotong University, China. Currently, he is the planning director of the cable FM product team of ZTE Corporation. With more than 10 years of experience in research and planning of telecommunication products, he has accumulated and practiced for many years in home networks, smart homes, IP protocols, etc. He has participated in translating and publishing the textbook, Principles of Compilation, applied for three patents, and made several special speeches in technical forums.
    CHEN Xiao graduated from Nanjing University of Aeronautics and Astronautics, China. He is currently the director of the Wireline Architecture Department of ZTE Corporation. He has more than 20 years of experience in research and planning of telecommunication products and related technologies. He has organized many national science and technology projects, and published many papers in various publications. He is the leading inventor of many patents.
    DING Xuan (dingx04@gmail.com) received his bachelor’s degree from the School of Software, Tsinghua University, China in 2008, and PhD degree from the Department of Computer Science and Technology, Tsinghua University in 2014. He is currently a research assistant professor in the School of Software, Tsinghua University. His research interests include privacy-preserving computing, blockchain, RFID and wireless sensing.


Falls are a major cause of disability and even death in the elderly, and fall detection can effectively reduce the damage. Compared with cameras and wearable sensors, Wi-Fi devices can protect user privacy and are inexpensive and easy to deploy. Wi-Fi devices sense user activity by analyzing the channel state information (CSI) of the received signal, which makes fall detection possible. We propose a fall detection system based on commercial Wi-Fi devices which achieves good performance. In the feature extraction stage, we select the discrete wavelet transform (DWT) spectrum as the feature for activity classification, which can balance the temporal and spatial resolution. In the feature classification stage, we design a deep learning model based on convolutional neural networks, which has better performance compared with other traditional machine learning models. Experimental results show our work achieves a false alarm rate of 4.8% and a missed alarm rate of 1.9%.

Key words: fall detection, commercial Wi-Fi devices, discrete wavelet transform, deep learning model