대한임베디드공학회논문지 (IEMEK Journal of Embedded Systems and Applications)

대한임베디드공학회 (Institute of Embedded Engineering of Korea)
권호 표지
DOI QR코드

DOI QR Code

mmWave 레이더 기반 사람 행동 인식 딥러닝 모델의 경량화와 자원 효율성을 위한 하이퍼파라미터 최적화 기법

Hyperparameter optimization for Lightweight and Resource-Efficient Deep Learning Model in Human Activity Recognition using Short-range mmWave Radar

  • 투고 : 2023.06.28
  • 심사 : 2023.11.14
  • 발행 : 2023.12.31
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

In this study, we proposed a method for hyperparameter optimization in the building and training of a deep learning model designed to process point cloud data collected by a millimeter-wave radar system. The primary aim of this study is to facilitate the deployment of a baseline model in resource-constrained IoT devices. We evaluated a RadHAR baseline deep learning model trained on a public dataset composed of point clouds representing five distinct human activities. Additionally, we introduced a coarse-to-fine hyperparameter optimization procedure, showing substantial potential to enhance model efficiency without compromising predictive performance. Experimental results show the feasibility of significantly reducing model size without adversely impacting performance. Specifically, the optimized model demonstrated a 3.3% improvement in classification accuracy despite a 16.8% reduction in number of parameters compared th the baseline model. In conclusion, this research offers valuable insights for the development of deep learning models for resource-constrained IoT devices, underscoring the potential of hyperparameter optimization and model size reduction strategies. This work contributes to enhancing the practicality and usability of deep learning models in real-world environments, where high levels of accuracy and efficiency in data processing and classification tasks are required.

키워드

참고문헌

  1. C. Yu, Z. Xu, K. Yan, Y. R. Chien, S. H. Fang, H. C. Wu, "Noninvasive Human Activity Recognition Using Millimeter-Wave Radar," IEEE Systems Journal, Vol. 16, No 2, pp. 3036-3047, 2022. https://doi.org/10.1109/JSYST.2022.3140546
  2. A. Shastri, N. Valecha, E. Bashirov, H. Trtaria, M. Lentmaier, F. Tufvesson, M. Rossi, P. Casari, "A Review of Millimeter Wave Device-Based Localization and Device-Free Sensing Technologies and Applications," IEEE Communications Surveys & Tutorials, Vol. 24, No. 3, pp. 1708-1749, 2022. https://doi.org/10.1109/COMST.2022.3177305
  3. B. Liu, K. Ma, H. Fu, K. Wang, F. Meng, "IRecent Progress of Silicon-Based Millimeter-Wave SoCs for Short-Range Radar Imaging and Sensing," IEEE Transactions on Circuits and Systems II: Express Briefs, Vol. 69, No. 6, pp. 2667-2671, 2022.
  4. Y. Rong, I. Lenz, D. W. Bliss, "Vital Signs Detection Based on High-Resolution 3-D mmWave Radar Imaging," 2022 IEEE International Symposium on Phased Array Systems & Technology.
  5. S. Lyer, L. Zhao, M. P. Mohan, J. Jimenno, M. Y. Siyal, A. Alphones, M. F. Karim, "mm-Wave Radar-Based Vital Signs Monitoring and Arrhythmia Detection Using Machine Learning," Sensors, Vol. 22, No. 9, 2022.
  6. A. D. Singh, S. S. Sandha, L. Garcia, M. Srivastava, "RadHAR: Human Activity Recognition from Point Clouds Generated through a Millimeter-wave Radar," Proceedings of the 3rd ACM Workshop on Millimeter-wave Networks and Sensing Systems, pp. 51-56, 2019.
  7. H. Arab, I. Ghaffari, L. Chioukh, S. O. Tatu, StevenDufour, "A Convolutional Neural Network for Human Motion Recognition and Classification Using a dxMillimeter-Wave Doppler Radar," IEEE Sensors Journal, Vol. 22, No. 5, pp. 4494-4502, 2022.
  8. P. P. Ray, "A review on TinyML: State-of-the-art and Prospects," Journal of King Saud University - Computer and Information Sciences, Vol. 34, No. 4, pp. 1595-1623, 2022. https://doi.org/10.1016/j.jksuci.2021.11.019
  9. F. J. Adbu, Y. Zhang, M. Fu, Y. Li, Z. Deng, "Application of Deep Learning on Millimeter-Wave Radar Signals: A Review," Sensors, Vol. 21, No. 6, 2021.
  10. T. Stadelmayer, M. Standelmayer, A. Santra, R. Weigel, F. Lurz, "Human Activity Classification Using mm-Wave FMCW Radar by Improved Representation Learning," Proceedings of the 4th ACM Workshop on Millimeter-Wave Networks and Sensing Systems, Vol. 1, No. 1, pp. 1-6, 2020.
  11. H. Zhou, Y. Zhao, Y. Liu, S. Lu, X. An, Q. Liu, "Multi-Sensor Data Fusion and CNN-LSTM Model for Human Activity Recognition System," Sensors, Vol. 23, No. 10, 2023.
  12. X. Huang, N. Patel, K. P. Tsoi, "Application of mmWave Radar Sensor for People Identification and Classification," Sensors, Vol. 23, No. 8, 2023.
  13. S. Bai, J. Z. Kolter, V. Koltun, "An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling," arXiv:1803.01271, 2018.
  14. C. R. Qi, H. Su, K. Mo, L. J. Guibas, "PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation," Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 652-660, 2017.