Using Combination of μ,β and γ Bands in Classi.cation of EEG Signals

• Main Authors: Mina Mirnaziri, Masoomeh Rahimi, Sepidehsadat Alavikakhaki, Reza Ebrahimpour
• Format: Article
• Language: English
• Published: Iran University of Medical Sciences 2013-02-01
• Series: Basic and Clinical Neuroscience
• Subjects: Brain – Computer Interface (BCI); Electroencephalogram (EEG); Common Spatial Pattern (CSP); Multi – Layer Perceptron (MLP); Linear Discriminant Analysis (LDA); Radial Basis Function (RBF).
• Online Access: http://bcn.iums.ac.ir/browse.php?a_code=A-10-1-146&slc_lang=en&sid=1
• ISSN: 2008-126X; 2228-7442

Introduction: In most BCI articles which aim to separate movement imaginations, µ and &beta frequency bands have been used. In this paper, the effect of presence and absence of &gamma band on performance improvement is discussed since movement imaginations affect &gamma frequency band as well. Methods: In this study we used data set 2a from BCI Competition IV. In this data set, 9 healthy subjects have performed left hand, right hand, foot and tongue movement imaginations. Time and frequency intervals are computed for each subject and then are classi.ed using Common Spatial Pattern (CSP) as a feature extractor. Finally, data is classi.ed by LDA1, RBF2 MLP3, SVM4and KNN 5 methods. In all experiments, accuracy rate of classi.cation is computed using 4 fold validation method. Results: It is seen that most of the time, combination of &mu,&beta and &gamma bands would have better performance than just using combination of &mu and &beta bands or &gamma band alone. In general, the improvement rate of the average classi.cation accuracy is computed 2.91%. Discussion: In this study, it is shown that using combination of µ, &beta and &gamma frequency bands provides more information than only using combination of µ and &beta in movement imagination separations.