Author/Authors :
Ma, Yuliang Hangzhou Dianzi University - Hangzhou - Zhejiang, China , Ding, Xiaohui Hangzhou Dianzi University - Hangzhou - Zhejiang, China , She, Qingshan Hangzhou Dianzi University - Hangzhou - Zhejiang, China , Luo, Zhizeng Hangzhou Dianzi University - Hangzhou - Zhejiang, China , Potter, Thomas Department of Biomedical Engineering - University of Houston - Houston, USA , Zhang, Yingchun Department of Biomedical Engineering - University of Houston - Houston, USA
Abstract :
Support vector machines are powerful tools used to solve the small sample and nonlinear classification problems, but their ultimate
classification performance depends heavily upon the selection of appropriate kernel and penalty parameters. In this study, we
propose using a particle swarm optimization algorithm to optimize the selection of both the kernel and penalty parameters in order
to improve the classification performance of support vector machines. The performance of the optimized classifier was evaluated
with motor imagery EEG signals in terms of both classification and prediction. Results show that the optimized classifier can
significantly improve the classification accuracy of motor imagery EEG signals.
