EMG-Based Motion Discrimination Using a Novel Recurrent Neural Network

Authors:
Nan Bu;Osamu Fukuda;Toshio Tsuji
Affiliations:
Department of Artificial Complex Systems Engineering, Hiroshima University, Higashi-Hiroshima, 739-8527, Japan. bu@bsys.hiroshima-u.ac.jp;National Institute of Advanced Industrial Science and Technology, Tsukuba, 305-8564, Japan. fukuda.o@aist.go.jp;Department of Artificial Complex Systems Engineering, Hiroshima University, Higashi-Hiroshima, 739-8527, Japan. tsuji@bsys.hiroshima-u.ac.jp
Venue:
Journal of Intelligent Information Systems
Year:
2003

Citing 2
Cited 2

A log-linearized Gaussian mixture network and its application toEEG pattern classification

IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews
A recurrent log-linearized Gaussian mixture network

IEEE Transactions on Neural Networks

A hybrid motion classification approach for EMG-based human-robot interfaces using Bayesian and neural networks

IEEE Transactions on Robotics - Special issue on rehabilitation robotics
An Automated Workforce Clustering Method for Business Process Reengineering in Research and Development Organizations

International Journal of Information Technology Project Management

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents a pattern discrimination method for electromyogram (EMG) signals for application in the field of prosthetic control. The method uses a novel recurrent neural network based on the hidden Markov model. This network includes recurrent connections, which enable modeling time series, such as EMG signals. Weight coefficients in the network can be learned using a well-known back-propagation through time algorithm. Pattern discrimination experiments were conducted to demonstrate the feasibility and performance of the proposed method. We were able to successfully discriminate forearm motions using the EMG signals, and achieved considerably high discrimination performance compared with other discrimination methods.