TITLE:
Comparison of SVM and ANN for classification of eye events in EEG
AUTHORS:
Rajesh Singla, Brijil Chambayil, Arun Khosla, Jayashree Santosh
KEYWORDS:
ANN; BCI; EEG; Eye Event; Kurtosis; SVM
JOURNAL NAME:
Journal of Biomedical Science and Engineering,
Vol.4 No.1,
January
30,
2011
ABSTRACT: The eye events (eye blink, eyes close and eyes open) are usually considered as biological artifacts in the electroencephalographic (EEG) signal. One can con-trol his or her eye blink by proper training and hence can be used as a control signal in Brain Computer Interface (BCI) applications. Support vector ma-chines (SVM) in recent years proved to be the best classification tool. A comparison of SVM with the Artificial Neural Network (ANN) always provides fruitful results. A one-against-all SVM and a multi-layer ANN is trained to detect the eye events. A com-parison of both is made in this paper.