Development of a model for sEMG based joint-torque estimation using Swarm techniques

Abstract

Over the years, numerous researchers have explored the relationship between surface electromyography (sEMG) signal with joint torque that would be useful to develop a suitable controller for rehabilitation robot. This research focuses on the transformation of sEMG signal by adopting a mathematical model to find the estimated joint torque of knee extension. Swarm techniques such as Particle Swarm Optimization (PSO) and Improved Particle Swarm Optimization (IPSO) were adapted to optimize the mathematical model for estimated joint torque. The correlation between the estimated joint torque and actual joint torque were determined by Coefficient of Determination (R2) and fitness value of Sum Squared Error (SSE). The outcome of the research shows that both the PSO and IPSO have yielded promising results.