EMG-based lumbosacral joint compression force prediction using a support vector machine

Real-Time Prediction of Joint Forces by Motion Capture and Machine Learning

“…Artificial neural networks are commonly used to predict lower limb joint angles and moments [40][41][42][43][44], ground reaction forces [45], joint forces or impulses [46][47][48][49] and contact pressures [50][51][52]. On the other hand, support vector machines have also demonstrated promising prediction performance in various regression biomechanical problems, such as electromyography (EMG)-based prediction of lumbosacral joint loads [53] and optical marker-based prediction of lower limb joint angles and moments [54,55], standing out for their substantial generalization ability to unseen datasets [56]. For an analytic review on ML applications in human movement biomechanics, including also unsupervised learning techniques, we refer to the survey of Halilaj et al [57].…”

Deep Neural Network Approach in EMG-Based Force Estimation for Human–Robot Interaction

“…This proposal can project the original data to a lower dimensional feature space to match the real-time relationship between sEMG signals and motion state. A sEMGbased support vector machine approach [23] was presented to predict joint compression force, and the result of comparative experiments showed that it was a favourable estimator with low bias and high efficiency. Artificial neural network (ANN) was also used to extract the features of raw EMG signals in the time and frequency domains [24].…”

Improving robotic hand control via adaptive Fuzzy-PI controller using classification of EMG signals

“…SVM [50] , [51] , [52] , [53] is a classifier with a solid mathematical base and good performance with a small training data set [54] . The kernel function in an SVM classifier is usually a polynomial, Gaussian or sigmoid function [55] .…”