A Machine Learning–Based Ergonomic Assessment of Wireless Hand Control System for Lower-Limb Disabled Tractor Operators and Abled Female Agricultural Workers

Tractor being the most used power source for agricultural operations needs hand control (HC) and foot control (FC) to maneuver it. FCs restrict lower-limb disabled agricultural workers from participating in tractor operation, and high requirement of actuation forces to operate FCs may create overexertion and early fatigue to female agricultural workers. Therefore, a sensor-based HC system has been developed to assist them in tractor operation with minimal actuating force. This study focuses on ergonomic assessment of the HC system to assess the suitability for the abled and disabled agricultural workers, including physiological, psychophysical, and muscle fatigue parameters. Heart rate (HR) of abled male and female, and disabled male and female was observed in the range of 83–118, 85–117, 93–118, and 92–114 beats/min, respectively, during tractor operation. Energy expenditure rate (EER) during tractor operation with FCs (9.7–17.4 kJ/min) was observed higher than with the HC system (7.3–16.5 kJ/min). Body parts discomfort was observed highest for the right hand of all the subjects (4.9–5.3) and maximum overall discomfort was experienced by abled females during the operation with FCs (5.4) as they have to exert higher force. The root mean square (RMS) value of the electromyography signal obtained for extensor digitorum muscle was found to be higher for all the subjects and with both HC and FC (abled male, 17.37–40.43 µV; abled female, 14.76–45.29 µV; disabled male, 15.49–40.23 µV; disabled female, 30.32–54.29 µV) than other upper arm muscles middle deltoid, flexor carpi radialis, and brachioradialis. Muscle workload for all the selected muscles of all the subjects was observed within the recommended limit during the tractor operation with a developed HC system (< 30%). Categorization of overall discomfort rating (ODR) of the subjects using HR, EER, and RMS through machine learning algorithms such as k-nearest neighbor (KNN), random forest classifier, and support vector machine predicted the ODR with accuracies in the range of 77%–83%. KNN algorithm was found to be most accurate with prediction accuracy of 83%. The developed HC system provides assistantship to the lower-limb disabled agricultural workers (1%–100% disability of lower limbs) and allows female workers to operate the tractor with minimal physical exertion.