Statistical Prediction of Hand Force Exertion Levels in a Simulated Push Task using Posture Kinematics

摘要

This study explored the use of body posture kinematics derived from wearable inertial sensors tornestimate force exertion levels in a two-handed isometric pushing and pulling task. A predictionrnmodel was developed grounded on the hypothesis that body postures predictably changerndepending on the magnitude of the exerted force. Five body postural angles, viz., torso flexion,rnpelvis flexion, lumbar flexion, hip flexion, and upper arm inclination, collected from 15 malernparticipants performing simulated isometric pushing and pulling tasks in the laboratory were usedrnas predictor variables in a statistical model to estimate handle height (shoulder vs. hip) and forcernintensity level (low vs. high). Individual anthropometric and strength measurements were alsornincluded as predictors. A Random Forest algorithm implemented in a two-stage hierarchyrncorrectly classified 77.2% of the handle height and force intensity levels. Results represent earlyrnwork in coupling unobtrusive, wearable instrumentation with statistical learning techniques tornmodel occupational activities and exposures to biomechanical risk factors in situ.