Journal of the Korea Society of Computer and Information (한국컴퓨터정보학회논문지)

Korean Society of Computer Information (한국컴퓨터정보학회)
권호 표지
DOI QR코드

DOI QR Code

A Design and Implementation of a Worker Musculoskeletal Assessment Platform Based on Machine Learning

  • Sejong Lee (Dept. of Computer Science & Engineering, Hanyang University)
  • Received : 2024.10.02
  • Accepted : 2024.10.18
  • Published : 2024.10.31
Download PDF
⟨ Previous Next ⟩

Abstract

In this paper, we design and implement a worker musculoskeletal assessment platform. The three core components of this platform are the Mobile App, the Modeling Server, and the Web Platform. The Mobile App is an Android application developed in Kotlin, targeting Android platform 12 (S) and Android API Level 31 devices. The app utilizes the camera to capture various worker motion data and transmits it to the Modeling Server. The Modeling Server is implemented using Node.js. This server converts the worker's motion data-such as points, skeleton, and x, y, z coordinate data, measured by the mobile app-into multidimensional arrays. It then applies machine learning frameworks like TensorFlow and Keras to predict the worker's posture. The worker posture learning model is built using Teachable Machine. The Web Platform is developed using React and visualizes the worker's movements as 3D animations along a timeline. The machine learning-based worker musculoskeletal assessment platform developed in this paper aims to contribute to minimizing musculoskeletal disorders in workers at industrial sites.

본 논문에서는 작업자 근골격계 평가 플랫폼을 설계하고 구현한다. 이 작업자 근골격계 평가 플랫폼을 구성하는 3가지 핵심 구성요소는 Mobile App, Modeling Server, Web Platform이다. Mobile App은 Android platform 기반의 애플리케이션으로 Android platform 12(S)와 Android API Level 31 디바이스를 대상으로 Kotlin 언어로 구현한다. 이 App은 카메라를 사용하여 작업자의 다양한 동작 데이터를 측정하여 Modeling server로 전송한다. Modeling Server는 node.js를 사용하여 구현한다. 이 Modeling Server는 모바일 앱에서 측정한 작업자의 동작 데이터인 포인트와 스켈레톤, x, y, z 좌표 데이터를 다차원 배열로 변환하고, TensorFlow와 Keras 등의 머신러닝 프레임워크를 적용하여 작업자의 자세를 예측한다. 그리고 작업자 자세 학습 모델 구축은 Teachable Machine을 사용한다. Web Platform은 React로 구현하며, 작업자의 동작을 타임라인에 따라 3D 애니메이션으로 시각화하도록 구현한다. 본 논문에서 구현한 머신러닝 기반의 작업자 근골격계 평가 플랫폼은 산업체 현장에서 발생하는 작업자 근골격계질환을 최소화하는 데 이바지할 것이다.

Keywords

References

  1. https://www.kosha.or.kr/kosha/business/musculoskeletal_a_a.do 
  2. N.S. Kim, Y.B. Kim, "Analysis of Trends in Patients with Work-related Musculoskeletal Disorders and Literature Review of Risk Factors and Prevalence," Journal of Korean Society of Occupational and Environmental Hygiene, Vol. 33 No. 3, pp. 298-307, Sept. 2023 https://doi.org/10.15269/JKSOEH.2023.33.3.298 
  3. https://oshri.kosha.or.kr/kosha/data/industrialDisasterStatistics.do? mode=view&articleNo=450460&article.offset=0&articleLimit=10 
  4. O. Karhu, R. Harkonen, P. Sorvali, P. Vepsalainen, "Observing working postures in industry: Examples of OWAS application," Applied Ergonomics, Vol. 12, Issue 1, pp. 13-17, Mar. 1981 https://doi.org/10.1016/0003-6870(81)90088-0 
  5. W. H. Cheon, K. H. Jung, "Analysis of Accuracy and Reliability for OWAS, RULA, and REBA to Assess Risk Factors of Work-related Musculoskeletal Disorders," Journal of the Korea Safety Management & Science, Vol. 22 Issue. 2, pp. 31-38, June 2020 http://dx.doi.org/10.12812/ksms.2020.22.2.031 
  6. Lynn McAtamney, E. Nigel Corlett, "RULA: a survey method for the investigation of work-related upper limb disorders," Applied Ergonomics, Vol. 24 Issue. 2, pp. 91-99, Apr. 1993 https://doi.org/10.1016/0003-6870(93)90080-S 
  7. https://www.TensorFlow.org 
  8. https://scikit-learn.org 
  9. https://www.TensorFlow.org 
  10. https://pytorch.org/ 
  11. https://developer.android.com/studio 
  12. https://teachablemachine.withgoogle.com/