skip to main content
10.1145/3650400.3650536acmotherconferencesArticle/Chapter ViewAbstractPublication PageseitceConference Proceedingsconference-collections
research-article

Human similarity behaviour classification based on through-wall radar

Authors Info & Claims
Published:17 April 2024Publication History

ABSTRACT

The study of Through Wall Radar Human Similar Behaviour Classification aims to classify and identify human behaviours through the use of Through Wall Radar technology. This study defines a metric for evaluating the network's ability to classify similar behaviours. In our experiments, we first collected a large amount of through-the-wall radar data and built a comprehensive and diverse database of human behaviours. Subsequently, we perform a simple data preprocessing on the data using MTI. Finally, we tested and evaluated the collected data with CNN, RNN, GRU, and LSTM. The results show that the metric can well evaluate the network's ability in classifying similarity data. In addition, we explored the similarities and differences between different human behaviours, analysed the similarities between such behaviours with different metrics, and added different similarity metrics to the network as regular terms for network training, and concluded that simple similarity metrics can often achieve good positive results.

References

  1. Naranjo-Hernandez, D., Roa, L. M., Reina-Tosina, J., & Estudillo-Valderrama, M. A. 2012. SoM: a smart sensor for human activity monitoring and assisted healthy ageing. IEEE transactions on biomedical engineering, 59(11), 3177-3184.Google ScholarGoogle Scholar
  2. Zhang, X., He, Y., Li, Q., & Zhou, B. 2023. A Spatiotemporal Detection and Tracing Framework for Human Contact Behavior Using Multicamera Sensors. IEEE Internet of Things Journal.Google ScholarGoogle Scholar
  3. Ahmad, F., & Amin, M. G. 2006, April. A noncoherent approach to radar localization through unknown walls. In 2006 IEEE Conference on Radar (pp. 7-pp). IEEE.Google ScholarGoogle ScholarCross RefCross Ref
  4. Kim, Y., & Ling, H. 2007, June. Tracking a moving target with multiple Doppler sensors using an artificial neural network. In 2007 IEEE Antennas and Propagation Society International Symposium (pp. 1477-1480). IEEE.Google ScholarGoogle Scholar
  5. Lai, C. P., Narayanan, R. M., Ruan, Q., & Davydov, A. 2008. Hilbert–Huang transform analysis of human activities using through-wall noise and noise-like radar. IET Radar, Sonar & Navigation, 2(4), 244-255.Google ScholarGoogle ScholarCross RefCross Ref
  6. Kwon, J., & Kwak, N. 2017, May. Human detection by neural networks using a low-cost short-range Doppler radar sensor. In 2017 IEEE Radar Conference (RadarConf) (pp. 0755-0760). IEEE.Google ScholarGoogle ScholarCross RefCross Ref
  7. Amin, M. G., & Erol, B. 2018, April. Understanding deep neural networks performance for radar-based human motion recognition. In 2018 IEEE Radar Conference (RadarConf18) (pp. 1461-1465). IEEE.Google ScholarGoogle ScholarCross RefCross Ref
  8. Plötz, T., Hammerla, N. Y., & Olivier, P. L. 2011, June. Feature learning for activity recognition in ubiquitous computing. In Twenty-second international joint conference on artificial intelligence.Google ScholarGoogle Scholar
  9. Wang, M., Cui, G., Huang, H., Gao, X., Chen, P., Li, H., ... & Kong, L. 2019, April. Through-wall human motion representation via autoencoder-self organized mapping network. In 2019 IEEE Radar Conference (RadarConf) (pp. 1-6). IEEE.Google ScholarGoogle ScholarCross RefCross Ref
  10. Li, Z., Ma, J., Li, X., & Pan, X. 2021, December. DFNM: Dynamic Fusion Network of Intra-and Inter-modalities for Multimodal Sentiment Analysis. In 2021 International Conference on Asian Language Processing (IALP) (pp. 346-351). IEEE.Google ScholarGoogle Scholar
  11. Wang, Z., Ren, A., Zhang, Q., Zahid, A., & Abbasi, Q. H. 2023. Recognition of Approximate Motions of Human Based on Micro-Doppler Features. IEEE Sensors Journal.Google ScholarGoogle Scholar
  12. Tibshirani, R. 1996. Regression shrinkage and selection via the lasso. Journal of the Royal Statistical Society Series B: Statistical Methodology, 58(1), 267-288.Google ScholarGoogle ScholarCross RefCross Ref

Index Terms

  1. Human similarity behaviour classification based on through-wall radar

    Recommendations

    Comments

    Login options

    Check if you have access through your login credentials or your institution to get full access on this article.

    Sign in
    • Published in

      cover image ACM Other conferences
      EITCE '23: Proceedings of the 2023 7th International Conference on Electronic Information Technology and Computer Engineering
      October 2023
      1809 pages
      ISBN:9798400708305
      DOI:10.1145/3650400

      Copyright © 2023 ACM

      Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].

      Publisher

      Association for Computing Machinery

      New York, NY, United States

      Publication History

      • Published: 17 April 2024

      Permissions

      Request permissions about this article.

      Request Permissions

      Check for updates

      Qualifiers

      • research-article
      • Research
      • Refereed limited

      Acceptance Rates

      Overall Acceptance Rate508of972submissions,52%
    • Article Metrics

      • Downloads (Last 12 months)7
      • Downloads (Last 6 weeks)7

      Other Metrics

    PDF Format

    View or Download as a PDF file.

    PDF

    eReader

    View online with eReader.

    eReader

    HTML Format

    View this article in HTML Format .

    View HTML Format