Multi-layer perceptron training algorithms for pattern recognition of myoelectric signals
Paper i proceeding, 2013

A challenge in using myoelectric signals in control of motorised prostheses is achieving effective signal pattern recognition and robust classification of intended motions. In this paper, the performance of Matlab's Multi-layer Perceptron (MLP) backpropogation training algorithms in motion classification were assessed. The test and evaluation platform used was 'BioPatRec', a Matlab-based open-source prosthetic control development environment, together with algorithms sourced from Matlab's neural network toolbox. The algorithms were used to interpret multielectrode myoelectric signals for motion classification, with the aim of finding the best performing algorithm and network model. The results showed that Matlab's trainlm and trainrp algorithms could achieve a higher accuracy than other tested MLP training algorithms (94.13 ± 0.037% and 91.09 ± 0.047%, respectively). Discussion of these results investigates significant features to obtain the highest performance.

neural network

pattern recognition

myoelectric signals

prosthetic control


L.M.D. Khong

University of Tasmania

T.J. Gale

University of Tasmania

D. Jiang

University of Tasmania

J.C. Olivier

University of Tasmania

Max Jair Ortiz Catalan

Signaler och system, Signalbehandling och medicinsk teknik, Medicinska signaler och system

BMEiCON 2013 - 6th Biomedical Engineering International Conference



Elektroteknik och elektronik