대한의용생체공학회:의공학회지 (Journal of Biomedical Engineering Research)

  • 제46권4호
  • /
  • Pages.319-333
  • /
  • 2025
  • /
  • 1229-0807(pISSN)
  • /
  • 2288-9396(eISSN)
대한의용생체공학회 (The Korean Society of Medical and Biological Engineering)
권호 표지
DOI QR코드

DOI QR Code

근전도 신호를 이용한 방향키 입력 기반 천지인 스펠러 시스템 개발

Development of an EMG-Based Chunjiin Speller System Using Directional Input

  • 유기연 (연세대학교 미래캠퍼스 의공학부) ;
  • 안지원 (연세대학교 미래캠퍼스 의공학부) ;
  • 유도현 (연세대학교 미래캠퍼스 의공학부) ;
  • 최승호 (연세대학교 미래캠퍼스 의공학부)
  • Gi Yeon Yu (Department of Biomedical Engineering, Yonsei University) ;
  • Ji Won Ahn (Department of Biomedical Engineering, Yonsei University) ;
  • Do Hyun Yoo (Department of Biomedical Engineering, Yonsei University) ;
  • Seung Ho Choi (Department of Biomedical Engineering, Yonsei University)
  • 투고 : 2025.05.23
  • 심사 : 2025.06.30
  • 발행 : 2025.08.31
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

Traditional Human-Machine Interfaces (HMIs), such as keyboards and mice, have long facilitated efficient digital communication through hand movements. To address this limitation, electromyography (EMG)-based interfaces offer intuitive control through muscle activity with high signal amplitude and ease of acquisition. This study proposes an EMG-based Chunjiin speller system designed for users with limited hand mobility. The system incorporates a directional input method (up, down, left, right, and select) and a Korean keyboard layout to support accessible and efficient character input. EMG signals were collected using four surface electrodes attached to the extensor digitorum and flexor carpi radialis muscles on both forearms. After real-time preprocessing, three time-domain features-root mean square, slope sign change, and peak amplitude-were extracted to determine user intent. In Experiment 1, five discrete input commands were classified with an average accuracy of 94.67%. In Experiment 2, which involved continuous input for actual word construction, the system maintained an average accuracy of 93.87%. Notably, these performances were achieved without the use of deep learning models, relying solely on simple time-domain features, making it viable for real-time use in low-resource environments. The proposed system demonstrates practical usability and real-time performance, highlighting its potential for augmentative and alternative communication (AAC) applications. Its lightweight architecture and direction-based design further support flexible deployment for users with motor impairments across diverse contexts.

키워드

과제정보

This work was carried out with the support of "Research Program for Agriculture Science & Technology Development (Project No. RS-2024-00399478)" Rural Development Administration, Republic of Korea. This work was supported by the National Research Foundation of Korea (NRF), grant funded by the Korean government (MSIT) (No. 2022R1C1C1011328). The authors would like to thank Kyeong-tae Seo for his participation as a subject in the experiment.

참고문헌

  1. Cannan J, Hu H. Human-machine interaction (HMI): A survey. University of Essex. 2011;27:46-64.
  2. Lee YH, Lee KK, Seo JS, Hwang KH. Design of a human-machine interface using multi-channel EMG pattern analysis. Conf Proc Korean Institute of Electrical Engineers Annual Conference. 2003;2895-8.
  3. Kim JS, Kim HK, Jung H, Kim KH, Lim SH, Son UH. User Interface Technology Based on Biosignals. Electron Telecommun Trends. 2005;20(4):67-81.
  4. Naydenov C, Yordanova A, Mancheva V. Methodology for EEG and reference values of the software analysis. Open Access Macedonian Journal of Medical Sciences. 2022;10(B):2351-4. https://doi.org/10.3889/oamjms.2022.10751
  5. Merino M, Rivera O, Gómez I, Molina A, Dorronzoro E. A method of EOG signal processing to detect the direction of eye movements. Conf Proc 2010 First International Conference on Sensor Device Technologies and Applications. 2010;100-5.
  6. Nishikawa D, Yu W, Yokoi H, Kakazu Y. EMG prosthetic hand controller using real-time learning method. Conf Proc IEEE SMC'99 Conference Proceedings 1999 IEEE International Conference on Systems, Man, and Cybernetics (Cat No 99CH37028). 1999;153-8.
  7. Moon IH, Lee MJ, Mun MS. A novel EMG-based human-computer interface for persons with disability. Conf Proc Proceedings of the IEEE International Conference on Mechatronics, 2004 ICM'04. 2004;519-24.
  8. Naves E, Rocha L, Pino P. Alternative communication system for people with severe motor disabilities using myoelectric signal control. Conf Proc 2012 ISSNIP Biosignals and Biorobotics Conference: Biosignals and Robotics for Better and Safer Living (BRC). 2012;1-4.
  9. Vasiljevas M, Turčinas R, Damaševičius R. EMG Speller with adaptive stimulus rate and dictionary support. Conf Proc 2014 Federated Conference on Computer Science and Information Systems. 2014;227-34.
  10. Rezeika A, Benda M, Stawicki P, Gembler F, Saboor A, Volosyak I. Surface electromyographic control of a three-steps speller interface. Conf Proc 2018 IEEE International Conference on Systems, Man, and Cybernetics (SMC). 2018;147-52.
  11. Xiong D, Zhang D, Zhao X, Zhao Y. Deep learning for EMG-based human-machine interaction: A review. IEEE/CAA Journal of Automatica Sinica. 2021;8(3):512-33. https://doi.org/10.1109/JAS.2021.1003865
  12. García-Vellisca M, Matran-Fernandez A, Poli R, Citi L. Hand-movement prediction from EMG with LSTM-recurrent neural networks. Conf Proc 2021 Global Medical Engineering Physics Exchanges/Pan American Health Care Exchanges (GMEPE/PAHCE). 2021;1-5.
  13. Kenge R. Machine learning, its limitations, and solutions over IT. Int J Adv Trends Comput Sci Eng. 2020;11(2):73-83. https://doi.org/10.5958/0975-8089.2020.00009.3
  14. https://docs.openbci.com/Ganglion/GanglionSpecs/. Accessed on 12 Jun 2025.
  15. Microchip Technology Inc. MCP3912-3V Four-Channel Analog Front End. Microchip Technology. 2020. Report No. DS20005348C.
  16. Bhattacharya A, Sarkar A, Basak P. Time domain multi-feature extraction and classification of human hand movements using surface EMG. Conf Proc 2017 4th international conference on advanced computing and communication systems (ICACCS). 2017;1-5.
  17. Singh P, Singh N, Singh KK, Singh A. Diagnosing of disease using machine learning. In: Krishna Kant Singh, Mohamed Elhoseny, Akansha Singh, Ahmed A. Elngar, eds. Machine learning and the internet of medical things in healthcare. 1sted. Amsterdam: Elsevier; 2021;89-111.
  18. Awujoola OJ, Ogwueleka FN, Odion PO, Awujoola AE, Adelegan OR. Genomic data science systems of prediction and prevention of pneumonia from chest X-ray images using a two-channel dual-stream convolutional neural network. In: Amit Kumar Tyagi, Ajith Abraham, eds. Data Science for Genomics. 1st ed. Cambridge, MA: Elsevier; 2023;217-228.
  19. Chicco D, Jurman G. The advantages of the Matthews correlation coefficient (MCC) over F1 score and accuracy in binary classification evaluation. BMC genomics. 2020;21:1-13. https://doi.org/10.1186/s12864-019-6419-1
  20. Sadeghi S, Maleki A. Accurate estimation of information transfer rate based on symbol occurrence probability in brain-computer interfaces. Biomedical Signal Processing and Control. 2019;54:101607. https://doi.org/10.1016/j.bspc.2019.101607
  21. Rezeika A, Benda M, Stawicki P, Gembler F, Saboor A, Volosyak I. Brain–computer interface spellers: A review. Brain sciences. 2018;8(4):57. https://doi.org/10.3390/brainsci8040057
  22. Lin K, Chen X, Huang X, Ding Q, Gao X. A Hybrid BCI speller based on the combination of EMG envelopes and SSVEP. Conf Proc Applied informatics. 2015;1-12.
  23. Han H, Choi C, Lee Y, Ha S, Kim J. Development of a Wireless Wearable Computer Interface Based on Electromyography (EMG). Conf Proc Korea HCI Conference. 2008;240-4.
  24. Kim DH, Kwon YJ, Kim YH, Shin YJ, Choi SI, Kim JH. Performance Comparison of Elbow Angle Classification Using sEMG Signals with Random Forest, SVM, and XGBoost. J Biomed Eng Res. 2024;45(6):300-9.