Multiclass support vector machines for EEG-signals classification.

@article{citeulike:2782726, abstract = {In this paper, we proposed the multiclass support vector machine (SVM) with the error-correcting output codes for the multiclass electroencephalogram (EEG) signals classification problem. The probabilistic neural network (PNN) and multilayer perceptron neural network were also tested and benchmarked for their performance on the classification of the EEG signals. Decision making was performed in two stages: feature extraction by computing the wavelet coefficients and the Lyapunov exponents and classification using the classifiers trained on the extracted features. The purpose was to determine an optimum classification scheme for this problem and also to infer clues about the extracted features. Our research demonstrated that the wavelet coefficients and the Lyapunov exponents are the features which well represent the EEG signals and the multiclass SVM and PNN trained on these features achieved high classification accuracies.}, address = {Department of Electronics and Computer Education, Faculty of Technical Education, Gazi University, 06500 Teknikokullar, Ankara, Turkey.}, author = {G\"{u}ler, I. and Ubeyli, E. D. }, citeulike-article-id = {2782726}, issn = {1089-7771}, journal = {IEEE transactions on information technology in biomedicine : a publication of the IEEE Engineering in Medicine and Biology Society}, keywords = {mdds, svm}, month = {March}, number = {2}, pages = {117--126}, posted-at = {2008-05-10 12:14:15}, priority = {1}, title = {Multiclass support vector machines for EEG-signals classification.}, url = {http://view.ncbi.nlm.nih.gov/pubmed/17390982}, volume = {11}, year = {2007} }

TY - JOUR ID - citeulike:2782726 L3 - citeulike-article-id:2782726 N2 - In this paper, we proposed the multiclass support vector machine (SVM) with the error-correcting output codes for the multiclass electroencephalogram (EEG) signals classification problem. The probabilistic neural network (PNN) and multilayer perceptron neural network were also tested and benchmarked for their performance on the classification of the EEG signals. Decision making was performed in two stages: feature extraction by computing the wavelet coefficients and the Lyapunov exponents and classification using the classifiers trained on the extracted features. The purpose was to determine an optimum classification scheme for this problem and also to infer clues about the extracted features. Our research demonstrated that the wavelet coefficients and the Lyapunov exponents are the features which well represent the EEG signals and the multiclass SVM and PNN trained on these features achieved high classification accuracies. IS - 2 JF - IEEE transactions on information technology in biomedicine : a publication of the IEEE Engineering in Medicine and Biology Society SN - 1089-7771 AD - Department of Electronics and Computer Education, Faculty of Technical Education, Gazi University, 06500 Teknikokullar, Ankara, Turkey. EP - 126 TI - Multiclass support vector machines for EEG-signals classification. VL - 11 SP - 117 KW - mdds KW - svm AU - Güler, I AU - Ubeyli, ED PY - 2007/03// UR - http://view.ncbi.nlm.nih.gov/pubmed/17390982 ER -