Design and Make a Work Study Simulation Model Using MediaPipe Holistic
Article Sidebar
Main Article Content
Abstract
This research aimed to design and develop a work simulation set using MediaPipe Holistic to assess fatigue, improve the accuracy of time recording, and measure body movement angles during task performance, thereby addressing issues of manual timing errors and limitations in fatigue evaluation. Testing was conducted in two configurations: Configuration 1 used a tray positioned 42 cm away with a chair height of 62.8 cm, while Configuration 2 used a tray positioned 27.5 cm away with a chair height of 54.8 cm. The study found that Configuration 1 was more effective at reducing fatigue than Configuration 2, primarily due to minimizing torso twisting; however, both configurations still resulted in shoulder and arm pain with continuous work. Standard time analysis with MediaPipe Holistic revealed that Configuration 1 had an average of 9.89 seconds per piece and demonstrated more continuous movement, whereas Configuration 2 had an average of 9.91 seconds per piece and emphasized greater shoulder flexibility. This finding is valuable for designing ergonomic workstations to enhance efficiency and reduce fatigue.
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
Copyright belongs to Srinakharinwirot University Engineering Journal
References
G. Kanawaty, Work Study, 3rd (Revised) ed., trans. by W. Tantasut, C. Mahitthaphonkul, and C. Chansangawet. Bangkok, Thailand: Chulalongkorn University Press, 2007.
M. P. N. K. Rajapaksha, G. G. T. D. Rathnayake and H. M. C. K. Herath, “Skeleton Detection Using MediaPipe as a Tool for Musculoskeletal Disorders Analysis,” Int. J. Res. Eng. Appl. Sci., vol. 14, no. 2, pp. 45–50, 2024.
E. Alpaydin, Introduction to Machine Learning, 3rd ed. Cambridge, MA, USA: MIT Press, 2014.
K. Beltrán Martínez, “Risk assessment for work-related musculoskeletal injury using wearable sensors,” M.S. thesis, Dept. Mech. Eng., Univ. of Alberta, Edmonton, Canada, 2021.
J. Dul and B. Weerdmeester, Ergonomics for Beginners: A Quick Reference Guide, 3rd ed. Boca Raton, FL, USA: CRC Press, 2017.
JORPOR TODAY. (2024). Ergonomics healthy postures [Online]. Available: https://www.jorportoday.com/workplace-ergonomics-benefits/.
S. Pheasant, Bodyspace: Anthropometry, Ergonomics and the Design of Work, London, U.K.: Taylor & Francis/CRC Press, 1996.
F. E. Meyers and J. R. Stewart Jr., Motion and Time Study for Lean Manufacturing, 3rd ed. Upper Saddle River, NJ, USA: Prentice Hall, 2002.
V. K. Singh and S. Verma, “Feature Scaling and Normalization in Machine Learning: A Review,” J. Eng. Res. Appl., vol. 8, no. 4, pp. 24–29, 2018.
V. Bazarevsky and I. Grishchenko, “On-device, Real-time Body Pose Tracking with MediaPipe BlazePose,” Google Research Blog, Aug. 2020.
D. C. Montgomery and G. C. Runger, Applied Statistics and Probability for Engineers, 8th ed. Hoboken, NJ, USA: John Wiley & Sons, 2021.
K. Beltrán Martinez, M. Nazarahari, and H. Rouhani, “K-score: A novel scoring system to quantify fatigue-related ergonomic risk based on joint angle measurements via wearable inertial measurement units,” Appl. Ergon., vol. 104, p. 103804, 2022.
K. M. Lee, M. Nazarahari, and H. Rouhani, “K-score: A novel scoring system to quantify fatigue-related ergonomic risk based on joint angle measurements via wearable inertial measurement units,” Appl. Ergon., vol. 100, p. 103657, 2022.
Simtec Institute, “Introducing SOLIDWORKS for industrial designers,” Simtec Blog, Mar. 14, 2022.
L. Lu, M. Robinson, Y. Tan, K. Goonewardena, X. Guo, I. Mareels, and D. Oetomo, “Effective Assessments of a Short-Duration Poor Posture on Upper Limb Muscle Fatigue Before Physical Exercise,” Front. Physiol., vol. 11, p. 610216, 2020.
