EMG-BASED DETECTION OF PERFORMANCE FATIGUE IN MULTI-ACTIVITY MANUAL HANDLING TASKS
Authors
Armin Bonakdara, Negar Riahia, Maryam Shakourisalima, Linda Millerb,c, Mahdi Tavakolid, Hossein Rouhania,e, Ali Golabchic,f
aDepartment of Mechanical Engineering, University of Alberta, Canada
bFaculty of Medicine & Dentistry, University of Alberta, Canada
cEWI Works International Inc., Canada
dDepartment of Electrical and Computer Engineering, University of Alberta, Canada
eGlenrose Rehabilitation Hospital, Canada
fDepartment of Civil and Environmental Engineering, University of Alberta, Canadaa
Abstract
Performance fatigue is a major contributor to work-related musculoskeletal disorders during manual material handling tasks. This study investigated whether surface electromyography (EMG) can reliably detect fatigue progression during prolonged, multi-activity manual handling tasks involving lifting, carrying, and lowering actions.
Five able-bodied participants performed repetitive material handling tasks until reaching severe fatigue. Muscle activation patterns were analyzed using EMG root mean square (RMS) and median frequency features. The results demonstrated consistent increases in RMS and decreases in median frequency with increasing fatigue, particularly during lifting and lowering phases. These findings indicate that EMG-based features can capture task-specific fatigue dynamics in realistic, multi-activity scenarios.
This work supports the use of wearable EMG systems for objective fatigue monitoring in real-world industrial tasks, with potential applications in ergonomic risk assessment and injury prevention.