Abstract
In Industry 5.0, worker well-being is paramount for organizational resilience and sustainability. Physical fatigue, work-life balance, and job competency significantly impact worker welfare and, therefore, efficiency and effectiveness. This study collects data in different industrial scenarios using non-invasive wearable devices for dynamic data and questionnaires for quasi-static data. Using Machine Learning algorithms, including Random Forest and Feedforward Neural Network models, the study predicts the physical fatigue of workers across multi-class and binary classifications. The developed Fatigue Monitoring System software integrates these models to monitor fatigue and improve worker well-being.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call