The recognition methodology study of epileptic EEGs based on support vector machine.
- Author:
Ruimel HUANG
1
;
Shouhong DU
2
;
Ziyi CHEN
3
;
Zhangzhen
1
;
Zhouyi
1
Author Information
1. Department of Biomedical Engineering, Zhongshan School of Medicine, Sun Yat-Sen University, Guangzhou 510080, China.
2. College of Medical Engineering and Technology, Xinjiang Medical University, Urumqi 830011, China.
3. Department of Neurology, the First Affiliated Hospital, Sun Yat-Sen University, Guangzhou 510080, China.
- Publication Type:Journal Article
- MeSH:
Algorithms;
Artifacts;
Electroencephalography;
methods;
Epilepsy;
diagnosis;
physiopathology;
Humans;
Nonlinear Dynamics;
Signal Processing, Computer-Assisted;
Support Vector Machine
- From:
Journal of Biomedical Engineering
2013;30(5):919-924
- CountryChina
- Language:Chinese
-
Abstract:
EEG recordings contain valuable physiological and pathological information in the process of seizure. The dynamic changes of brain electrical activity provide foundation and possibility for research and development of automatic detection system about epilepsy. In this paper, a nonlinear dynamic method is presented for analysis of the nonlinear dynamic characteristics of EEGs and delta, theta, alpha, and beta sub-bands of EEGs based on wavelet transform. The extracted feature is used as the input vector of a support vector machine (SVM) to construct classifiers. The results showed that the classification accuracy of SVM classifier based on nonlinear dynamic characteristics to classify the EEG into interictal EEGs and ictal EEGs reached 90% or higher. The support vector machine has good generalization in detecting the epilepsy EEG signals as a nonlinear classifier.
