로봇학회논문지 (The Journal of Korea Robotics Society)

  • 제19권2호
  • /
  • Pages.213-220
  • /
  • 2024
  • /
  • 1975-6291(pISSN)
  • /
  • 2287-3961(eISSN)
한국로봇학회 (Korea Robotics Society)
권호 표지
DOI QR코드

DOI QR Code

베이지안 기반의 근전도 발화 측정을 이용한 낙상의 예측

Bayesian Onset Measure of sEMG for Fall Prediction

  • Seongsik Park (Division of Advanced Engineering, Korea National Open University) ;
  • Keehoon Kim (Department of Mechanical Engineering, POSTECH)
  • 투고 : 2024.03.26
  • 심사 : 2024.05.07
  • 발행 : 2024.05.31
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

Fall detection and prevention technologies play a pivotal role in ensuring the well-being of individuals, particularly those living independently, where falls can result in severe consequences. This paper addresses the challenge of accurate and quick fall detection by proposing a Bayesian probability-based measure applied to surface electromyography (sEMG) signals. The proposed algorithm based on a Bayesian filter that divides the sEMG signal into transient and steady states. The ratio of posterior probabilities, considering the inclusion or exclusion of the transient state, serves as a scale to gauge the dominance of the transient state in the current signal. Experimental results demonstrate that this approach enhances the accuracy and expedites the detection time compared to existing methods. The study suggests broader applications beyond fall detection, anticipating future research in diverse human-robot interface benefiting from the proposed methodology.

키워드

참고문헌

  1. R. Rajagopalan, I. Litvan, and T.-P. Jung, "Fall prediction and prevention systems: Recent trends, challenges, and future research directions," Sensors, vol. 17, no. 11, pp. 2509, Nov., 2017, DOI: 10.3390/s17112509.
  2. B. Kwolek and M. Kepski, "Human fall detection on embedded platform using depth maps and wireless accelerometer," Computer Methods and Programs in Biomedicine, vol. 117, no. 3, pp. 489-501, Dec., 2014, DOI: 10.1016/j.cmpb.2014.09.005.
  3. L. Martinez-Villasenor, H. Ponce, J. Brieva, E. Moya-Albor, J. Nunez-Martinez, and C. Penafort-Asturiano, "Up-fall detection dataset: A multimodal approach," Sensors, vol. 19, no. 9, pp. 1988, Apr., 2019, DOI: 10.3390/s19091988.
  4. E. Casilari, J. A. Santoyo-Ramon, and J. M. Cano-Garcia, "Umafall: A multisensor dataset for the research on automatic fall detection," Procedia Computer Science, vol. 110, pp. 32-39, 2017, DOI: 10.1016/j.procs.2017.06.110.
  5. J. Cheng, X. Chen, and M. Shen, "A framework for daily activity monitoring and fall detection based on surface electromyography and accelerometer signals," IEEE Journal of Biomedical and Health Informatics, vol. 17, no. 1, pp. 38-45, Jan., 2013, DOI: 10.1109/TITB.2012.2226905.
  6. X. Xi, M. Tang, S. M. Miran, and Z. Luo, "Evaluation of feature extraction and recognition for activity monitoring and fall detection based on wearable sEMG sensors," Sensors, vol. 17, no. 6, pp. 1229, May, 2017, DOI: 10.3390/s17061229.
  7. X. Liu, H. Li, C. Lou, T. Liang, X. Liu, and H. Wang, "A new approach to fall detection based on improved dual parallel channels convolutional neural network," Sensors, vol. 19, no. 12, pp. 2814, Jun., 2019, DOI: 10.3390/s19122814.
  8. N. Sharma, C. M. Gregory, and W. E. Dixon, "Predictor-based compensation for electromechanical delay during neuromuscular electrical stimulation," IEEE Transactions on Neural Systems and Rehabilitation Engineering, vol. 19, no. 6, pp. 601-611, Dec., 2011, DOI: 10.1109/TNSRE.2011.2166405.
  9. H. Begovic, G.-Q. Zhou, T. Li, Y. Wang, and Y.-P. Zheng, "Detection of the electromechanical delay and its components during voluntary isometric contraction of the quadriceps femoris muscle," Frontiers in Physiology, vol. 5, Dec., 2014, DOI: 10.3389/fphys.2014.00494.
  10. S. U. Yavuz, A. Sendemir-Urkmez, and K. S. Turker, "Effect of gender, age, fatigue and contraction level on electromechanical delay," Clinical Neurophysiology, vol. 121, no. 10, pp. 1700-1706, Oct., 2010, DOI: 10.1016/j.clinph.2009.10.039.
  11. E. N. Kamavuako, E. J. Scheme, and K. B. Englehart, "Determination of optimum threshold values for emg time domain features; a multi-dataset investigation," Journal of Neural Engineering, vol. 13, no. 4, pp. 046011, Jun., 2016, DOI: 10.1088/1741-2560/13/4/046011.
  12. I. J. R. Martinez, A. Mannini, F. Clemente, A. M. Sabatini, and C. Cipriani, "Grasp force estimation from the transient emg using high-density surface recordings," Journal of Neural Engineering, vol. 17, no. 1, pp. 016052, Feb., 2020, DOI: 10.1088/1741-2552/ab673f.
  13. I. Conradsen, S. Beniczky, K. Hoppe, P. Wolf, and H. B. D. Sorensen, "Automated algorithm for generalized tonic-clonic epileptic seizure onset detection based on sEMG zero-crossing rate," IEEE Transactions on Biomedical Engineering, vol. 59, no. 2, pp. 579-585, Feb., 2012, DOI: 10.1109/TBME.2011.2178094.
  14. X. Li, P. Zhou, and A. S. Aruin, "Teager-kaiser energy operation of surface emg improves muscle activity onset detection," Annals of Biomedical Engineering, vol. 35, no. 9, pp. 1532-1538, May,2007, DOI: 10.1007/s10439-007-9320-z.
  15. S. E. Selvan, D. Allexandre, U. Amato, and G. H. Yue, "Unsupervised stochastic strategies for robust detection of muscle activation onsets in surface electromyogram," IEEE Transactions on Neural Systems and Rehabilitation Engineering, vol. 26, no. 6, pp. 1279-1291, Jun., 2018, DOI: 10.1109/TNSRE.2018.2833742.
  16. Q. Xu, Y. Quan, L. Yang, and J. He, "An adaptive algorithm for the determination of the onset and offset of muscle contraction by emg signal processing," IEEE Transactions on Neural Systems and Rehabilitation Engineering, vol. 21, no. 1, pp. 65-73, Jan., 2013, DOI: 10.1109/TNSRE.2012.2226916.
  17. E. S. Suviseshamuthu, D. Allexandre, U. Amato, B. D. Vecchia, and G. H. Yu, "Prolific: A fast and robust profile-likelihood-based muscle onset detection in electromyogram using discrete fibonacci search," IEEE Access, vol. 8, pp. 105362-105375, 2020, DOI: 10.1109/ACCESS.2020.3000693.
  18. N. M. Lopez, E. Orosco, and F. D. Sciascio, "Surface electromyographic onset detection based on statistics and information content," Journal of Physics: Conference Series, vol. 332, pp. 012043, 2011, DOI: 10.1088/1742-6596/332/1/012043.
  19. Y. Kuroda, I. Nisky, Y. Uranishi, M. Imura, A. M. Okamura, and O. Oshiro, "Novel algorithm for real-time onset detection of surface electromyography in step-tracking wrist movements," 2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Osaka, Japan, pp. 2056-2059, 2013, DOI: 10.1109/EMBC.2013.6609936.
  20. J. Liu, D. Ying, W. Z. Rymer, and P. Zhou, "Robust muscle activity onset detection using an unsupervised electromyogram learning framework," PloS one, vol. 10, no. 6, pp. e0127990, Jun., 2015, DOI: 10.1371/journal.pone.0127990.
  21. I. Conradsen, S. Beniczky, K. Hoppe, P. Wolf, T. Sams, and H. B. D. Sorensen, "Seizure onset detection based on one semg channel," 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, Boston, MA, USA, pp. 7715-7718, 2011, DOI: 10.1109/IEMBS.2011.6091901.
  22. T. D. Sanger, "Bayesian filtering of myoelectric signals," Journal of neurophysiology, vol. 97, no. 2, pp. 1839-1845, Feb., 2007, DOI: 10.1152/jn.00936.2006.
  23. S. Park, W. K. Chung, and K. Kim, "Training-Free Bayesian Self-Adaptive Classification for sEMG Pattern Recognition Including Motion Transition," IEEE Transactions on Biomedical Engineering, vol. 67, no. 6, pp. 1775-1786, Jun., 2020, DOI: 10.1109/TBME.2019.2947089.