Estimation of hand grasp force based on forearm surface EMG

Abstract

In the force control of multi-functional prosthetic hands, it is important to extract grasp force information besides mode specifications directly from the myoelectric signals. In this paper, a force sensor is adopted to record the hand's enveloping force when the hand is performing several grasp modes, synchronously with 6 channels surface electromyography (EMG) which are extracting from the subject's forearm. Three pattern regression methods, locally weighted projection regression (LWPR), artificial neural network (ANN) and support vector machine (SVM) are used to find the best representative relationship of these two kinds of signals. Experimental results show that the SVM method is better than LWPR and ANN, especially in the case of cross-session validation. Also, the force regression performance is better when grasping within several specific modes than grasping randomly. Based on these results, an efficient online prediction of the hand grasp force is present finally, with an accuracy of around 0.9 in squared correlation coefficient (SCC) and 5--10N error over a range of 60N. It can be utilized for the prosthetic hand's control to provide a reasonable exerting force reference.

Electrotactile Feedback in a Virtual Hand Rehabilitation Platform: Evaluation and Implementation

“…Grasping force estimation lies on the basis of force prediction in [35], which utilises the EMG signals to fit the exerted force. The model was tuned by the locally captured data of ten subjects.…”

Estimation of hand force from surface Electromyography signals using Artificial Neural Network

“…Mobasser et al [4] used multilayer perceptron ANN for hand force estimation from surface EMG signals for applications in sports activities. Yang et al [5] demonstrated the use of ANN, Locally Weighted Projection Regression (LWPR) and SVM to estimate hand grasp force from surface EMG signals for force control of multi-functional prosthetic hands. In this work, we propose an idea of estimating force from the surface EMG signals using a feed-forward ANN in real-time.…”

Modified EMG-based handgrip force prediction using extreme learning machine

“…Marta et al (2012) developed a valid biomechanical model with artificial neural networks to compute the grasping posture related to handgrip force; artificial neural networks enhanced the model capability. Yang et al (2009) presented an efficient grip force prediction using support vector machine (SVM) when different hand fingers performed several grasp modes synchronously with six sEMG channels from the participants forearm. Mojgan (2010) investigated whether multi-class SVM could effectively predict hand orientation and torque from myoelectric signals when the wrists radial and ulnar deviations were increased gradually.…”