ECoG recognition of motor imagery based on SVM ensemble

Authors:
Mingai Li;Jinfu Yang;Dongmei Hao;Songmin Jia
Affiliations:
Institution of Artificial Intelligence and Robot, Beijing University of Technology, Beijing, China;Institution of Artificial Intelligence and Robot, Beijing University of Technology, Beijing, China;College of Life Science and Bio-engineering, Beijing University of Technology, Beijing, China;Institution of Artificial Intelligence and Robot, Beijing University of Technology, Beijing, China
Venue:
ROBIO'09 Proceedings of the 2009 international conference on Robotics and biomimetics
Year:
2009

Citing 2
Cited 0

A Tutorial on Support Vector Machines for Pattern Recognition

Data Mining and Knowledge Discovery
Ensemble of SVMs for improving brain computer interface p300 speller performances

ICANN'05 Proceedings of the 15th international conference on Artificial Neural Networks: biological Inspirations - Volume Part I

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, a method of ECoG identification based on SVM Ensemble was proposed to solve the problems of low classification accuracy and weak robustness for ECoG collection during different period of time. Common Spatial Pattern (CSP) algorithm is used for feature extraction, and Support Vector Machine (SVM) Ensemble is applied for classification of ECoG. Besides, Bagging algorithm and Cross-Validation technique are adopted in individual generation of the SVM Ensemble. The experiment results verified that the accuracy of SVM Ensemble is better than that of single SVM for ECoG collection in different period of time, and the Cross-Validated technique has good performance than that of Bagging. Therefore, SVM Ensemble has stronger robustness and generalization ability compared with individual SVMs, and will improve classification of ECoG signals.