로봇학회논문지 (The Journal of Korea Robotics Society)

  • 제19권2호
  • /
  • Pages.203-212
  • /
  • 2024
  • /
  • 1975-6291(pISSN)
  • /
  • 2287-3961(eISSN)
한국로봇학회 (Korea Robotics Society)
권호 표지
DOI QR코드

DOI QR Code

근육 활성화 모델 기반의 데이터 증강을 활용한 동시 동작 인식 프레임워크

Simultaneous Motion Recognition Framework using Data Augmentation based on Muscle Activation Model

  • 투고 : 2024.03.14
  • 심사 : 2024.04.13
  • 발행 : 2024.05.31
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

Simultaneous motion is essential in the activities of daily living (ADL). For motion intention recognition, surface electromyogram (sEMG) and corresponding motion label is necessary. However, this process is time-consuming and it may increase the burden of the user. Therefore, we propose a simultaneous motion recognition framework using data augmentation based on muscle activation model. The model consists of multiple point sources to be optimized while the number of point sources and their initial parameters are automatically determined. From the experimental results, it is shown that the framework has generated the data which are similar to the real one. This aspect is quantified with the following two metrics: structural similarity index measure (SSIM) and mean squared error (MSE). Furthermore, with k-nearest neighbor (k-NN) or support vector machine (SVM), the classification accuracy is also enhanced with the proposed framework. From these results, it can be concluded that the generalization property of the training data is enhanced and the classification accuracy is increased accordingly. We expect that this framework reduces the burden of the user from the excessive and time-consuming data acquisition.

키워드

과제정보

This research was supported by Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Education (No.2020R1I1A2074953).

참고문헌

  1. A. Dwivedi, Y. Kwon, and M. Liarokapis, "Emg-based decoding of manipulation motions in virtual reality: Towards immersive interfaces," 2020 IEEE Systems, Man, and Cybernetics(SMC), Toronto, ON, Canada, pp. 3296-3303, 2020, DOI: 10.1109/SMC42975.2020.9283270.
  2. D. Leonardis, M. Barsotti, C. Loconsole, M. Solazzi, M. Troncossi, C. Mazzotti, V. P. Castelli, C. Procopio, G. Lamola, C. Chisari, M. Bergamasco, and A. Frisoli, "An EMG-controlled robotic hand exoskeleton for bilateral rehabilitation," IEEE Transactions on Haptics, vol. 8, no. 2, pp. 140-151, Apr.-Jun., 2015, DOI: 10.1109/TOH.2015.2417570.
  3. S. R. Chang, N. Hofland, Z. Chen, C. Tatsuoka, L. G. Richards, M. Bruestle, H. Kovelman, and J. Naft, "Myoelectric Arm Orthosis Assists Functional Activities: A 3-Month Home Use Outcome Report," Archives of Rehabilitation Research and Clinical Translation, vol. 5, no. 3, Sept, 2023, DOI: 10.1016/j.arrct.2023.100279.
  4. K. Z. Zhuang, N. Sommer, V. Mendez, S. Aryan, E. Formento, E. D' Anna, F. Artoni, F. Petrini, G. Granata, G. Cannaviello, W. Raffoul, A. Billard, and S. Micera, "Shared human-robot proportional control of a dexterous myoelectric prosthesis," Nature Machine Intelligence, vol. 1, no. 9, pp. 400-411, Sept, 2019, DOI: 10.1038/s42256-019-0093-5.
  5. N. Jiang, K. B. Englehart, and P. A. Parker, "Extracting simultaneous and proportional neural control information for multiple-DOF prostheses from the surface electromyographic signal," IEEE Transactions on Biomedical Engineering, vol. 56, no. 4, pp. 1070-1080, Apr., 2009, DOI: 10.1109/TBME.2008.2007967.
  6. X. Yang, Y. Zhou, and H. Liu, "Wearable ultrasound-based decoding of simultaneous wrist/hand kinematics," IEEE Transactions on Industrial Electronics, vol. 68, no. 9, pp. 8667-8675, Sept, 2021, DOI: 10.1109/TIE.2020.3020037.
  7. X. Yang, J. Yan, Y. Fang, D. Zhou, and H. Liu, "Simultaneous prediction of wrist/hand motion via wearable ultrasound sensing," IEEE Transactions on Neural Systems and Rehabilitation Engineering, vol. 28, no. 4, pp. 970-977, Apr., 2020, DOI: 10.1109/TNSRE.2020.2977908.
  8. C. Chen, Y. Yu, X. Sheng, D. Farina, and X. Zhu, "Simultaneous and proportional control of wrist and hand movements by decoding motor unit discharges in real time," Journal of Neural Engineering, vol. 18, no. 5, Apr., 2021, DOI: 10.1088/1741-2552/abf186.
  9. F. Leone, C. Gentile, F. Cordella, E. Gruppioni, E. Guglielmelli, and L. Zollo, "A parallel classification strategy to simultaneous control elbow, wrist, and hand movements," Journal of NeuroEngineering and Rehabilitation, vol. 19, no. 1, pp. 1-17, Jan., 2022, DOI: 10.1186/s12984-022-00982-z.
  10. A. J. Young, L. H. Smith, E. J. Rouse, and L. J. Hargrove, "Classification of simultaneous movements using surface EMG pattern recognition," IEEE Transactions on Biomedical Engineering, vol. 60, no. 5, pp. 1250-1258, May, 2013, DOI: 10.1109/TBME.2012.2232293.
  11. L. H. Smith, T. A. Kuiken, and L. J. Hargrove, "Evaluation of linear regression simultaneous myoelectric control using intramuscular EMG," IEEE Transactions on Biomedical Engineering, vol. 63, no. 4, pp. 737-746, Apr., 2016, DOI: 10.1109/TBME.2015.2469741.
  12. W. Yang, D. Yang, Y. Liu, and H. Liu, "Decoding simultaneous multi-DOF wrist movements from raw EMG signals using a convolutional neural network," IEEE Transactions on HumanMachine Systems, vol. 49, no. 5, pp. 411-420, Oct., 2019, DOI: 10.1109/THMS.2019.2925191.
  13. C. Shorten and T. M. Khoshgoftaar, "A survey on image data augmentation for deep learning," Journal of Big Data, vol. 6, pp. 1-48, Jul., 2019, DOI: 10.1186/s40537-019-0197-0.
  14. X. Jiang, X. Liu, J. Fan, X. Ye, C. Dai, E. A. Clancy, M. Akay, and W. Chen, "Open access dataset, toolbox and benchmark processing results of high-density surface electromyogram recordings," IEEE Transactions on Neural Systems and Rehabilitation Engineering, vol. 29, pp. 1035-1046, May, 2021, DOI:10.1109/TNSRE.2021.3082551.
  15. A. Merlo, D. Farina, and R. Merletti. "A fast and reliable technique for muscle activity detection from surface EMG signals," IEEE Transactions on Biomedical Engineering, vol. 50, no. 3, pp. 316-323, Mar., 2003, DOI: 10.1109/TBME.2003.808829.
  16. K. Englehart and B. Hudgins, "A robust, real-time control scheme for multifunction myoelectric control," IEEE Transactions on Biomedical Engineering, vol. 50, no. 7, pp. 848-854, Jul., 2003, DOI: 10.1109/TBME.2003.813539.
  17. M. A. Oskoei and H. Hu, "Myoelectric Control Systems-a survey," Biomedical Signal Processing and Control, vol. 2, no. 4, pp. 275-294, Oct., 2007, DOI: 10.1016/j.bspc.2007.07.009.
  18. D. Brunet, E. R. Vrscay, and Z. Wang, "On the mathematical properties of the structural similarity index," IEEE Transactions on Image Processing, vol. 21, no. 4, pp. 1488-1499, Apr., 2012, DOI: 10.1109/TIP.2011.2173206.
  19. Z. Wang and A. C. Bovik, "Mean squared error: Love it or leave it? A new look at signal fidelity measures," IEEE Signal Processing Magazine, vol. 26, no. 1, pp. 98-117, Jan., 2009, DOI: 10.1109/MSP.2008.930649.
  20. E. Bergil, C. Oral, and E. U. Ergul, "Efficient hand movement detection using k-means clustering and k-nearest neighbor algorithms," Journal of Medical and Biological Engineering, vol. 41, pp. 11-24, May, 2020, DOI: 10.1007/s40846-020-00537-4.
  21. M. Tavakoli, C. Benussi, P. A. Lopes, L. B. Osorio, and A. T. D. Almeida, "Robust hand gesture recognition with a double channel surface EMG wearable armband and SVM classifier," Biomedical Signal Processing and Control, vol. 46, pp. 121-130, Sept., 2018, DOI: 10.1016/j.bspc.2018.07.010.