The Journal of the Convergence on Culture Technology (문화기술의 융합)

The International Promotion Agency of Culture Technology (국제문화기술진흥원)
권호 표지
DOI QR코드

DOI QR Code

Low-cost Prosthetic Hand Model using Machine Learning and 3D Printing

머신러닝과 3D 프린팅을 이용한 저비용 인공의수 모형

  • 신동욱 (을지대학교 의료공학과) ;
  • 염호준 (을지대학교 의료공학과) ;
  • 박상수 (을지대학교 의료공학과)
  • Received : 2023.10.04
  • Accepted : 2023.11.05
  • Published : 2024.01.31
Download PDF
⟨ Previous Next ⟩

Abstract

Patients with amputations of both hands need prosthetic hands that serve both cosmetic and functional purposes, and research on prosthetic hands using electromyography of remaining muscles is active, but there is still the problem of high cost. In this study, an artificial prosthetic hand was manufactured and its performance was evaluated using low-cost parts and software such as a surface electromyography sensor, machine learning software Edge Impulse, Arduino Nano 33 BLE, and 3D printing. Using signals acquired with surface electromyography sensors and subjected to digital signal processing through Edge Impulse, the flexing movement signals of each finger were transmitted to the fingers of the prosthetic hand model through training to determine the type of finger movement using machine learning. When the digital signal processing conditions were set to a notch filter of 60 Hz, a bandpass filter of 10-300 Hz, and a sampling frequency of 1,000 Hz, the accuracy of machine learning was the highest at 82.1%. The possibility of being confused between each finger flexion movement was highest for the ring finger, with a 44.7% chance of being confused with the movement of the index finger. More research is needed to successfully develop a low-cost prosthetic hand.

양손 절단 환자들에게 미용적 목적과 함께 기능적 목적을 갖춘 의수가 필요하며 잔존 근육의 근전도를 이용한 인공 의수에 대한 연구가 활발하나 아직도 비싼 비용의 문제가 있다. 본 연구에서는 저비용의 부품과 소프트웨어인 표면 근전도 센서, 머신러닝 소프트웨어 Edge Impulse, Arduino Nano 33 BLE, 그리고 3D 프린팅을 이용하여 인공의수를 제작하고 성능을 평가하였다. 표면 근전도 센서로 획득하고 Edge Impulse에서 디지털 시그널 프로세싱 과정을 거친 신호들을 이용하여 머신러닝으로 손가락 운동의 종류를 판단하는 훈련을 통해 각 손가락의 굽힘 운동신호를 의수 모델의 손가락들에 전달하였다. 디지털 시그널 프로세싱 조건을 노치 필터 60 Hz, 대역필터 10-300 Hz, 그리고 샘플링 주파수 1,000 Hz로 했을 때, 머신 러닝의 정확도가 82.1%로 가장 높았다. 각 손가락 굴곡 운동간에 혼동될 수 있는 가능성은 약지가 가장 높아서 검지의 운동으로 혼동될 가능성이 44.7 %이었다. 저비용 인공의수의 성공적인 개발을 위해서는 더 많은 연구가 필요하다.

Keywords

Acknowledgement

본 연구는 2023년도 을지대학교 교육혁신지원사업으로 연구되었음

References

  1. Cha, G. C., Choi, K., Lee, S., Park, S. "Development of Gripping force and Durability Test Standard for Myoelectric Prosthetic Hand," The Journal of the Convergence on Culture Technology (JCCT), Vol. 9, No. 4, pp. 393-399, 2023. doi.org/10.17703/JCCT.2023.9.4.389. 
  2. Ann, K., Ohm, S. "A COVID-19 Chest X-ray Reading Technique based on Deep Learning," The Journal of the Convergence on Culture Technology (JCCT), Vol. 6, No. 4, pp. 789-795, 2020. doi.org/10.17703/JCCT.2020 .6.4.789 
  3. Kim, K., Kim. S.. "Grade Analysis and Two-Stage Evaluation of Beef Carcass Image Using Deep Learning," The Journal of the Convergence on Culture Technology (JCCT), Vol. 8, No. 2, pp. 385-391, 2022. doi.org/10.17703/JCCT.2022.8.2.373 
  4. Park, J. H., Ha, B. J., Park, S. (2022). "Prediction of Hair Owners' Age using Hair Mineral Content and Artificial Intelligence," The Journal of the Convergence on Culture Technology (JCCT), Vol. 8, No. 6, pp. 155-159, 2022. doi.org/10.17703 /JCCT.2022.8.6.155  https://doi.org/10.17703/JCCT.2022.8.6.155
  5. So, J. H. Jeon. Y. "Using 3D image-based body shape Measurement to increase the accuracy of body shape Measurement," The Journal of the Convergence on Culture Technology (JCCT), Vol. 6, No. 4, pp. 803-806, 2020. doi.org/10.17703/JCCT.2020 .6.4.797. 
  6. Yoo, H. J., Lee, S., Kim, J., Park, C., & Lee, B. "Development of 3D-printed Myoelectric Hand Orthosis for Patients with Spinal Cord Injury," Journal of neuroengineering and rehabilitation, Vol. 16, No. 1, pp. 1-14, 2019.  https://doi.org/10.1186/s12984-018-0454-z
  7. Lee, S., Sung, M., & Choi, Y. "Wearable Fabric Sensor for Controlling Myoelectric Hand Prosthesis via Classification of Foot Postures," Smart Materials and Structures, Vol. 29, No. 3, 035004., 2020 
  8. Ju, N., Lee, K. H., Kim, M. O., & Choi, Y. "A User-driven Approach to Prosthetic Upper Limb Development in Korea In Healthcare," Vol. 9, No. 7, p. 839, 2021. 
  9. Kim, J. J., Kim, J., Lee, J., & Shin, J. (2022). "Influence of Lifestyle Pattern on Preference for Prosthetic Hands: Understanding the Development Pathway for 3D-printed Prostheses," Journal of Cleaner Production, 379, 134599. https://doi.org/10.1016/j.jclepro.2022.134599