Journal of Biomedical Engineering Research (대한의용생체공학회:의공학회지)

The Korean Society of Medical and Biological Engineering (대한의용생체공학회)
권호 표지
DOI QR코드

DOI QR Code

Development and Usability Evaluation of Hand Rehabilitation Training System Using Multi-Channel EMG-Based Deep Learning Hand Posture Recognition

다채널 근전도 기반 딥러닝 동작 인식을 활용한 손 재활 훈련시스템 개발 및 사용성 평가

  • Ahn, Sung Moo (Department of Biomedical Engineering, Konyang University) ;
  • Lee, Gun Hee (Department of Biomedical Engineering, Konyang University) ;
  • Kim, Se Jin (Department of Biomedical Engineering, Konyang University) ;
  • Bae, So Jeong (Department of Physical Therapy, Konyang University) ;
  • Lee, Hyun Ju (Department of Physical Therapy, Konyang University) ;
  • Oh, Do Chang (Department of Biomedical Engineering, Konyang University) ;
  • Tae, Ki Sik (Department of Biomedical Engineering, Konyang University)
  • Received : 2022.09.30
  • Accepted : 2022.10.21
  • Published : 2022.10.31
Download PDF
⟨ Previous Next ⟩

Abstract

The purpose of this study was to develop a hand rehabilitation training system for hemiplegic patients. We also tried to find out five hand postures (WF: Wrist Flexion, WE: Wrist Extension, BG: Ball Grip, HG: Hook Grip, RE: Rest) in real-time using multi-channel EMG-based deep learning. We performed a pre-processing method that converts to Spider Chart image data for the classification of hand movement from five test subjects (total 1,500 data sets) using Convolution Neural Networks (CNN) deep learning with an 8-channel armband. As a result of this study, the recognition accuracy was 92% for WF, 94% for WE, 76% for BG, 82% for HG, and 88% for RE. Also, ten physical therapists participated for the usability evaluation. The questionnaire consisted of 7 items of acceptance, interest, and satisfaction, and the mean and standard deviation were calculated by dividing each into a 5-point scale. As a result, high scores were obtained in immersion and interest in game (4.6±0.43), convenience of the device (4.9±0.30), and satisfaction after treatment (4.1±0.48). On the other hand, Conformity of intention for treatment (3.90±0.49) was relatively low. This is thought to be because the game play may be difficult depending on the degree of spasticity of the hemiplegic patient, and compensation may occur in patient with weakened target muscles. Therefore, it is necessary to develop a rehabilitation program suitable for the degree of disability of the patient.

Keywords

Acknowledgement

본 연구는 2021년도 정부(과학기술정보통신부)의 재원으로 한국연구재단 기초연구사업의 과제의 지원을 받아 수행하였음(No. 2021R1I1A304391111).

References

  1. Roh GH. The Effect of Aerobic Walking Exercise Program on Walking, Balancing, Performance of Daily Activities, and Depression in Stroke Patients. The Korean Journal of Rehabilitation Nursing. 2002;5(3):193-204.
  2. Lee KH. Correlation among the stroke patient familie's health status, burden and of life. J Korean Acad Nurs. 2001; 31(4):669-80. https://doi.org/10.4040/jkan.2001.31.4.669
  3. Park SJ, Song KS, Lee HJ, Tae KS. Development and Usability Evaluation of a Functional Game Based on Inertial Sensor for Knee Rehabilitation in Total Knee Arthroplasty Patient. Journal of Rehabilitation Welfare Engineering & Assistive Technology. 2019;13(2):127-33. https://doi.org/10.21288/resko.2019.13.2.127
  4. Lee CJ. A Serious Game for Language/Cognitive Rehabilitation Therapy of Stroke Patients. Journal of Koen. 2011;5(1):73-80.
  5. Aenderson F, Annett M, Bischof WF. Lean on wii: physical rehabilitation with virtualreality wii peripherals. Studies in healthtechnology and informatics. 2010;154:229-234.
  6. Tagliapietra L, Vivian M, Sartori M, Farina D, Reggiani M. Estimating EMG signals to drive neuromusculoskeletal models in cyclic rehabilitation movements. 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). 2015;3611-3614.
  7. Kim KS, Choi HH, Mun CW. Comparison of k-nearest neighbor, quadraticdiscriminant and linear discriminant analysisin classification of electromyogram signalsbased on the wrist-motion directions. Current applied physics. 2011;11(3): 740-745. https://doi.org/10.1016/j.cap.2010.11.051
  8. Scheme E, Englehart K. Training Strategies for Mitigating the Effect of Proportion al Control on Classification in Pattern Recognition-Based Myo electric Control. JP O Journal of Prosthetics and Orthotics. 2013;25(2):76-83. https://doi.org/10.1097/JPO.0b013e318289950b
  9. Phinyomark A, Quaine F, Charbonnier S, Serviere C, TarpinBernard F, Laurillau Y. EMG Feature Evaluation for Improving Myoelectric Pattern Recognition Robustness. Expert Syst. 2013;40(12):4832-40. https://doi.org/10.1016/j.eswa.2013.02.023
  10. Tkach D, Huang H, Kuiken TA. Study of Stability of TimeDomain Features for Electromyographic Pattern Recognition. Journal of neuroengineering and rehabilitation, 2010;7(1):21. https://doi.org/10.1186/1743-0003-7-21
  11. Ren JL, Chien YH, Chia EY, Fu LC, Lai JS. Deep Learning based Motion Prediction for Exoskeleton Robot Control in Upper Limb Rehabilitation. 2019 International Conference on Robotics and Automation (ICRA). 2019;5076-5082.
  12. Yousefi, Hamilton-Wright J. Characterizing EMG data using machine-learning tool.Computers in biology and medicine. 2014;51:1-13. https://doi.org/10.1016/j.compbiomed.2014.04.018
  13. Schmidhuber J. Deep learning in neural networks: An overview. Neural Networks. 2015;61:85-117. https://doi.org/10.1016/j.neunet.2014.09.003
  14. Park KH, Lee SW. Movement intention decoding based on deep learning for multiuser myoelectric interfaces. In Proceedings of the 2016 4th International Winter Conference on Brain-Computer Interface(BCI). 2016.
  15. Atzori M, Cognolato M, Muller H. Deep learning with convolutional neural networks applied to electromyography data. A resource for the classification of movements for prosthetic hands. 2016.
  16. Cote-Allard U, Fall CL, Campeau-Lecours A, Gosselin C, Laviolette F, Gosselin B. Transfer learning for sEMG hand gestures recognition using convolutional neural networks. In Proceedings of the 2017 IEEE International Conference on Systems. 2017;1663-1668.
  17. Ozdemir MA, Kisa DH, Guren O, Onan A. EMG based Hand Gesture Recognition using Deep Learning. 2020 Medical Technologies Congress. 2020.
  18. Nahid N, Rahman A, Ahad MAR. Deep Learning Based Surface EMG Hand Gesture Classification for Low-Cost Myoelectric Prosthetic Hand. 2020 Joint 9th International Conference on Informatics. Electronics & Vision (ICIEV). 2020.
  19. http://www.relayhealth.com, accessed on Oct. 10, 2022.
  20. R. Laezza, "Deep Neural Networks for Myoelectric Pattern Recognition An Implementation for Multifunctional Control," 2018.
  21. Asif AR. Performance Evaluation of Convolutional Neural Network for Hand Gesture Recognition Using EMG. Sensors. 2020;20(6):1642. https://doi.org/10.3390/s20061642