Pattern classification of time-series EMG signals using neural networks

Abstract

This paper proposes a pattern classification method of time‐series EMG signals for prosthetic control. To achieve successful classification for non‐stationary EMG signals, a new neural network structure that combines a common back‐propagation neural network with recurrent neural filters is used. A convergence time of the network learning can be regulated by a new learning method based on dynamics of a terminal attractor. The experiments of pattern classification and prosthetic control are carried out for several subjects including an amputee. It is shown from the results that the proposed method improves learning/classification ability for stationary and non‐stationary EMG signals during a series of continuous motions. Copyright © 2000 John Wiley & Sons, Ltd.

A recurrent log-linearized gaussian mixture network

“…It was, however, too difficult for only use of them to achieve high classification accuracy because of the considerable time-varying characteristics of EEG signals. To overcome this difficulty, Tsuji et al [8], [9], [13], [25] investigated the pattern classification problem of EEG (EMG) signals using a static probabilistic NN, LLGMN, and a recurrent neural filter (RNF). Although this method attained relatively high classification rates, it is necessary to train two different types of NNs, that is, LLGMN and RNF, therefore the learning procedure becomes quite complicated and general optimization is almost impossible.…”

A recurrent log-linearized gaussian mixture network

“…It was, however, too difficult for only use of them to achieve high classification accuracy because of the considerable time-varying characteristics of EEG signals. To overcome this difficulty, Tsuji et al [8], [9], [13], [25] investigated the pattern classification problem of EEG (EMG) signals using a static probabilistic NN, LLGMN, and a recurrent neural filter (RNF). Although this method attained relatively high classification rates, it is necessary to train two different types of NNs, that is, LLGMN and RNF, therefore the learning procedure becomes quite complicated and general optimization is almost impossible.…”

Myoelectric control of prosthetic hands: state-of-the-art review

“……”

A two-dimensional matrix image based feature extraction method for classification of sEMG: A comparative analysis based on SVM, KNN and RBF-NN

“…Some other algorithms were used for sEMG classification by researchers, such as particle swarm optimization (PSO) [4], neural network [13,20,21], support vector machine (SVM) [4,15,21]. Subasi [4] used PSO optimized SVM to classify sEMG signals while Lucas et al [15] used discrete wavelet transform and SVM.…”

A recurrent log-linearized gaussian mixture network

“…It was, however, too difficult for only use of them to achieve high classification accuracy because of the considerable time-varying characteristics of EEG signals. To overcome this difficulty, Tsuji et al [8], [9], [13], [25] investigated the pattern classification problem of EEG (EMG) signals using a static probabilistic NN, LLGMN, and a recurrent neural filter (RNF). Although this method attained relatively high classification rates, it is necessary to train two different types of NNs, that is, LLGMN and RNF, therefore the learning procedure becomes quite complicated and general optimization is almost impossible.…”

Myoelectric control of prosthetic hands: state-of-the-art review

“……”

A two-dimensional matrix image based feature extraction method for classification of sEMG: A comparative analysis based on SVM, KNN and RBF-NN

“…Some other algorithms were used for sEMG classification by researchers, such as particle swarm optimization (PSO) [4], neural network [13,20,21], support vector machine (SVM) [4,15,21]. Subasi [4] used PSO optimized SVM to classify sEMG signals while Lucas et al [15] used discrete wavelet transform and SVM.…”

A recurrent log-linearized gaussian mixture network

“…It was, however, too difficult for only use of them to achieve high classification accuracy because of the considerable time-varying characteristics of EEG signals. To overcome this difficulty, Tsuji et al [8], [9], [13], [25] investigated the pattern classification problem of EEG (EMG) signals using a static probabilistic NN, LLGMN, and a recurrent neural filter (RNF). Although this method attained relatively high classification rates, it is necessary to train two different types of NNs, that is, LLGMN and RNF, therefore the learning procedure becomes quite complicated and general optimization is almost impossible.…”

Myoelectric control of prosthetic hands: state-of-the-art review

“……”

A two-dimensional matrix image based feature extraction method for classification of sEMG: A comparative analysis based on SVM, KNN and RBF-NN

“…Some other algorithms were used for sEMG classification by researchers, such as particle swarm optimization (PSO) [4], neural network [13,20,21], support vector machine (SVM) [4,15,21]. Subasi [4] used PSO optimized SVM to classify sEMG signals while Lucas et al [15] used discrete wavelet transform and SVM.…”