A Study on Multi-motion Pattern Recognition of EMG Based on Genetic Algorithm

Author

Zhang Qingju ; Shi Kai

Author_Institution

Dept. of Inf. Eng., Shandong Univ. of Sci. & Technol., Taian, China

fYear

2012

fDate

8-10 Dec. 2012

Firstpage

168

Lastpage

171

Abstract

The traditional neural network has the uncertain shortcomings on structures and the genetic algorithm has the optimization ability. So the improved adaptive genetic algorithm is used to optimize the numbers and value of hidden nodes of neural network. And then LMS algorithm is used to optimize the weight and threshold value of the neural network. The nueral network is trainned by much groups of training samples and the ultimate neural network system is got. Afterwards, using the improved power spectrum K value method to extract the characteristic value of the collected surface emg signals;Finally, the characteristic values of six kinds of hand motions is input into RBF neural network classifier for pattern recognition. This trial gets good results and 6 kinds of action recognition rate to 75%.

Keywords

biomechanics; electromyography; genetic algorithms; learning (artificial intelligence); least mean squares methods; medical signal processing; pattern classification; radial basis function networks; signal classification; LMS algorithm; RBF neural network classifier; action recognition rate; adaptive genetic algorithm; electromyography; hand motions; multimotion pattern recognition; neural network system; nueral network hidden nodes; optimization; power spectrum K value method; surface EMG signal; Electromyography; Encoding; Genetic algorithms; Genetics; Neural networks; Training; Wrist; RBF neural network; Signal; Surface Electromyography; genetic algorithm; pattern recognition;

fLanguage

English

Publisher

ieee

Conference_Titel

Instrumentation, Measurement, Computer, Communication and Control (IMCCC), 2012 Second International Conference on

Conference_Location

Harbin

Print_ISBN

978-1-4673-5034-1

Type

conf

DOI

10.1109/IMCCC.2012.46

Filename

6428878