WiPhase: A Human Activity Recognition Approach by Fusing of Reconstructed WiFi CSI Phase Features

被引:1
|
作者
Chen, Xingcan [1 ,2 ,3 ]
Li, Chenglin [1 ,2 ,3 ]
Jiang, Chengpeng [1 ,2 ,3 ]
Meng, Wei [4 ,5 ]
Xiao, Wendong [1 ,2 ,3 ]
机构
[1] Univ Sci & Technol Beijing, Sch Automat & Elect Engn, Beijing 100083, Peoples R China
[2] Beijing Engn Res Ctr Ind Spectrum Imaging, Beijing 100083, Peoples R China
[3] Univ Sci & Technol Beijing, Shunde Innovat Sch, Foshan 528399, Peoples R China
[4] Guangdong Univ Technol, Sch Automat, Guangzhou 510006, Peoples R China
[5] Guangdong Univ Technol, Guangdong Prov Key Lab Intelligent Decis & Coopera, Guangzhou 510006, Peoples R China
基金
中国国家自然科学基金;
关键词
Human activity recognition; Wireless fidelity; Feature extraction; Correlation; Computational modeling; Long short term memory; Fuses; Deep learning; human activity recognition (HAR); signal processing; wireless sensing; SYSTEM;
D O I
10.1109/TMC.2024.3461672
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Human activity recognition (HAR) is an important task in the field of human-computer interaction. Given the penetration of WiFi devices in our daily lives, HAR using WiFi channel state information (CSI) is a more cost-efficient and comfortable approach. However, most existing approaches ignore the correlation between CSI sub-carriers, which makes their models inefficient and need to rely on deeper and more complex networks to further improve performance. To solve these problems, we propose a reconstructed WiFi CSI phase based HAR approach (WiPhase), which contains a two-stream model to fuse both temporal features and sub-carrier correlation features of reconstructed CSI phase. Specifically, a gated pseudo-Siamese network (GPSiam) is designed to capture the temporal features of the reconstructed sparse CSI phase integration representation (CSI-PIR), and a dynamic resolution based graph attention network (DRGAT) is designed to capture the nonlinear correlation between CSI sub-carriers by the reconstructed CSI phase graph. Furthermore, dendrite network (DD) makes the final decision by combining the features output from GPSiam and DRGAT. Experimental results show that WiPhase outperforms the existing state-of-the-art approaches.
引用
收藏
页码:394 / 406
页数:13
相关论文
共 50 条
  • [41] Joint recognition for location and activity based on multidimensional features of CSI images
    Tian, Yong
    Gao, Fangting
    Yan, Shuyu
    Tong, Xin
    Zhang, Qiyue
    Ding, Xuejun
    INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS, 2025, 16 (01) : 625 - 638
  • [42] CSI-HC: A WiFi-Based Indoor Complex Human Motion Recognition Method
    Hao, Zhanjun
    Duan, Yu
    Dang, Xiaochao
    Zhang, Tong
    MOBILE INFORMATION SYSTEMS, 2020, 2020
  • [43] Joint frequency domain and reconstructed phase space features for speech recognition
    Lindgren, AC
    Johnson, MT
    Povinelli, RJ
    2004 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOL I, PROCEEDINGS: SPEECH PROCESSING, 2004, : 533 - 536
  • [44] Fusing magnitude and phase features with multiple face models for robust face recognition
    Yan Li
    Shiguang Shan
    Ruiping Wang
    Zhen Cui
    Xilin Chen
    Frontiers of Computer Science, 2018, 12 : 1173 - 1191
  • [45] A Novel Benchmark on Human Activity Recognition Using WiFi Signals
    Guo, Linlin
    Wang, Lei
    Liu, Jialin
    Zhou, Wei
    Lu, Bingxian
    Liu, Tao
    Li, Guangxu
    Li, Chen
    2017 IEEE 19TH INTERNATIONAL CONFERENCE ON E-HEALTH NETWORKING, APPLICATIONS AND SERVICES (HEALTHCOM), 2017,
  • [46] Human Activity Recognition Across Scenes and Categories Based on CSI
    Zhang, Yong
    Wang, Xinyuan
    Wang, Yujie
    Chen, Hongxin
    IEEE TRANSACTIONS ON MOBILE COMPUTING, 2022, 21 (07) : 2411 - 2420
  • [47] Understanding and Modeling of WiFi Signal Based Human Activity Recognition
    Wang, Wei
    Liu, Alex X.
    Shahzad, Muhammad
    Ling, Kang
    Lu, Sanglu
    MOBICOM '15: PROCEEDINGS OF THE 21ST ANNUAL INTERNATIONAL CONFERENCE ON MOBILE COMPUTING AND NETWORKING, 2015, : 65 - 76
  • [48] WISENSE: A DATASET FOR WIFI-BASED HUMAN ACTIVITY RECOGNITION
    Liao, Zhenlong
    Su, Jian
    Ye, Yinghui
    Hu, Rose Qingyang
    IEEE WIRELESS COMMUNICATIONS, 2024, 31 (05) : 232 - 237
  • [49] Fusing magnitude and phase features with multiple face models for robust face recognition
    Li, Yan
    Shan, Shiguang
    Wang, Ruiping
    Cui, Zhen
    Chen, Xilin
    FRONTIERS OF COMPUTER SCIENCE, 2018, 12 (06) : 1173 - 1191
  • [50] An improved hybrid approach to face recognition by fusing local and global discriminant features
    Sing, Jamuna Kanta
    Chowdhury, Shiladitya
    Basu, Dipak Kumar
    Nasipuri, Mita
    INTERNATIONAL JOURNAL OF BIOMETRICS, 2012, 4 (02) : 144 - 164