DocumentCode :
550215
Title :
Epileptic EEG signals recognition based on wavelet package and least square support vector machine
Author :
Zhou Hongbiao
Author_Institution :
Fac. of Electron. & Electr. Eng., Huaiyin Inst. of Technol., Huaiyin, China
fYear :
2011
fDate :
22-24 July 2011
Firstpage :
3015
Lastpage :
3018
Abstract :
In order to extract the feature of epileptic EEG efficiently, and to improve the classification accuracy, a nonlinear feature extraction method based on wavelet packet Transform(WPT) and support vector machine(SVM) is proposed. The Samples are composed of five hundred EEG Public datum which include the Period of epileptic seizures. Character vectors which reflect different state of EEG signals are extracted from different frequency segments with the technology of wavelet packet decomposition which have the trait of arbitrary distinction and decomposition. The classifier is composed of the least square SVM(LSSVM) which trained by the characteristic vectors,its parameters are optimized by genetic algorithm(GA) and particle swarm optimization(PSO). Experimental results demonstrate that the classifier has good classification and generalization abilities, the identification rate of SVM which parameters are optimized by PSO algorithm reaches 91.50%.
Keywords :
electroencephalography; least squares approximations; medical signal processing; support vector machines; wavelet transforms; EEG public datum; epileptic EEG signals recognition; genetic algorithm; least square support vector machine; particle swarm optimization; wavelet packet transform; Classification algorithms; Electroencephalography; Feature extraction; Support vector machine classification; Wavelet packets; Epileptic EEG; Genetic Algorithm; Least Squares Support Vector Machine; Particle Swarm Optimization; Wavelet Package;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Control Conference (CCC), 2011 30th Chinese
Conference_Location :
Yantai
ISSN :
1934-1768
Print_ISBN :
978-1-4577-0677-6
Electronic_ISBN :
1934-1768
Type :
conf
Filename :
6000552
Link To Document :
بازگشت