Title:	REAL-TIME WHEELCHAIR CONTROL SYSTEM USING SURFACE ELECTROMYOGRAPHIC SIGNAL ANALYSIS
Author(s):	Sruthi Sahebjada, Jay O’Connor, Hans Weghorn, Sridhar P. Arjunan, Dinesh K. Kumar
ISBN:	978-972-8939-67-0
Editors:	Piet Kommers and Pedro Isaías
Year:	2012
Edition:	Single
Keywords:	Gesture Identification, Surface Electromyogram, Wavelet analysis, Artificial Neural Network, Bio-signal Processing
Type:	Full Paper
First Page:	409
Last Page:	416
Language:	English
Cover:
Full Contents:	click to dowload
Paper Abstract:	In this research, a novel end-to-end system for real-time identification of finger gestures was investigated. In first stage, surface electromyography signals from the forearm are used during muscle onset activation for an extraction of frequency/time domain features. For achieving this, the volume conduction model is applied. In the second stage, a multilayer perceptron artificial neural network (ANN) is applied for feature classification. This method of Gesture identification can be used to, e.g., control a wheelchair (modeled here in miniature) on base of finger movements. The combination of wavelet decomposition singularities in conjunction with an ANN classifier is found to successfully discriminate between individual finger contractions with a high degree of sensitivity, which makes the system suitable for real world applications. The project is especially targeted towards amputees, who can benefit from controlling the movements of a wheel chair. This new method would require less effort than the usual chin operated joystick control.
	Go Back