The main ob
jective of the study was to model the electromyographic (EMG) responses for 10 trunk muscles in manual-lifting tasks using the fuzzy relational rule network (FRRN). The FRRN utilized trunk-related variables, including sagittal and lateral trunk moments, pelvic tilt and pelvic rotation angles, and sagittal, lateral, and twist trunk angles as model inputs. The EMG data for model training and testing were randomly selected from a set collected for 20 college students. The data represented a total of 24 combinations of weight lifted (15, 30, 50 lbs), asymmetry (0°, 60°), and the origin and destination of lift (floor-waist, floor-102 cm, knee-waist, knee-102 cm), with two replications of each condition. The primary data-driven fuzzy model with relational input partition was trained using the laboratory EMG data for 10 sub
jects, and was then tested based on the EMG data for another 10 sub
jects. The model allowed for estimating EMG responses for the 10 trunk muscles with the average value of mean absolute error (MAE) of 9.9 % (SD=1.44 % ). This study demonstrates that application of fuzzy modeling techniques allows for estimating time domain EMG responses of trunk muscles due to manual lifting under limited task conditions.
Relevance to industry
Estimation of EMG responses using the proposed fuzzy-based system opens new opportunities for biomechanical modeling of manual-lifting tasks aimed at prevention of low back disorders at the workplace.