Presentation
CANCELED - Predicting Perceived Back Fatigue During Exoskeleton Supported Trunk Bending Tasks Using Machine Learning
SessionOE12: Exoskeletons IV
DescriptionRepetitive trunk flexion tasks over prolonged periods can increase risk of low-back injury, wherein Back Support Industrial Exoskeletons (BSIEs) can be beneficial. While BSIEs have shown effectiveness in lab assessments, real-world outcomes have shown variation based on task complexity, necessitating monitoring of physical demands. We recruited fourteen young male adults to perform repetitive trunk BSIE-assisted bending/retraction, without fatigue and then at medium-high fatigue. We recorded muscle activity in low-back and thigh muscles using Electromyography (EMG) and whole-body stability using force plates. Classification algorithms, namely, Support Vector Machine (SVM), Random Forest (RF), and XGBoost (XGB) were utilized to predict perceived back fatigue using sensor data. Outcomes demonstrate efficacy of XGB using data from a single low-back EMG sensor (Accuracy: 86.1%, Recall: 86%), and force plate (93.5, 94.1%). The general outcomes of our study can be helpful in developing a fatigue monitoring system, benefiting ergonomists in properly implementing BSIEs in industrial scenarios.
Event Type
Lecture
TimeFriday, September 13th9am - 9:01am MST
LocationFLW Salon H
Occupational Ergonomics