Position/force estimation using Hill muscle model incorporating AdaBoost with SVM-based component classifiers

The objective of this paper is to estimate the joint angle and the force from a moving elbow joint based on the SEMG. An AdaBoost with SVM-based compoment classifier is proposed to discriminate different movements based on SEMG of the forearm. Then, the average integral EMG(AIEMG) variables collecting by an EMG measurement device is introduced to estimating joint angles. Through the estimated joint angle, we can use the Hill muscle model to predict the force of the moving elbow joint. The extensive experiments are conducted to verify the effectiveness of the estimated position and force.