BiomacEMG: A Pareto-Optimized System for Assessing and Recognizing Hand Movement to Track Rehabilitation Progress

One of the most difficult components stroke therapy is regaining hand mobility. This research describes a preliminary approach to robot-assisted motion therapy. Our objectives were twofold: First, we used machine learning approaches determine and describe patterns in healthy people. Surface electrodes collect electromyographic (EMG) data from forearm’s flexion extension muscles. The time frequency characteristics as parameters algorithms recognize seven gestures track rehabilitation progress. Eight EMG sensors capture each contraction arm muscles during one actions. Feature selection was performed using Pareto front. system able reconstruct kinematics hand/finger movement simulate behaviour every pattern. Analysis has revealed that gesture categories substantially overlap feature space. correlation computed joint trajectories based on monitored 0.96 average. Moreover, statistical conducted various setups 92% accuracy measuring precision finger patterns.