Performance Analysis of Multiclass Common Spatial Patterns in Brain-Computer Interface Soumyadip Chatterjee 1 , Saugat Bhattacharyya 1 , Amit Konar 1 , D.N. Tibarewala 2 , Anwesha Khasnobish 2 , and R. Janarthanan 3 1 Department of Electronics and Telecommunication Engineering Jadavpur University, Kolkata, India 2 School of Bioscience and Engineering Jadavpur University, Kolkata, India 3 Department of Computer Science TJS Engineering College, Chennai, India {soumyadipc7,biomed.ju,anweshakhasno}@gmail.com, saugatbhattacharyya@live.com,konaramit@yahoo.co.in,srmjana_73@yahoo.com Abstract. Brain-Computer Interfacing (BCI) aims to assist, enhance, or repair human cognitive or sensory-motor functions. The classification of EEG signals plays a crucial role in BCI implementation. In this paper we have implemented a multi-class CSP Mutual Information Feature Se- lection (MIFS) algorithm to classify our EEG data for three class Motor Imagery BCI and have presented a comparative study of different classi- fication algorithms including k-nearest neighbor (kNN) and Fuzzy kNN algorithm, linear discriminant analysis (LDA), Quadratic discriminant analysis (QDA), support vector machine (SVM), radial basis function (RBF) SVM and Naive Bayesian (NB) classifiers algorithms. It is ob- served that Fuzzy kNN and kNN algorithm provides the highest classifi- cation accuracy of 92.65% and 92.29% which surpasses the classification accuracy of the other algorithms. Keywords: Brain-Computer Interfacing, Electroencephalography, Common Spatial Pattern, Mutual Information Features Selection, k-Nearest Neighbor, Fuzzy k-Nearest Neighbor, Linear Discriminant Analysis, Quadratic Discriminant Analysis, Support Vector Machine, Nave-Bayesian. 1 Introduction The main function of Brain-computer Interfacing (BCI) is to process and decode the brain signals and send the resulting commands to an external assistive device, thus implementing a real-time interface between the user and his environment. This interface may be a word processor, wheel chair or a prosthetic limb [1, 2]. In this technique, the subjects use their brain signals for communication and control of objects in their environment, thereby bypassing their impaired neuromuscular system [3, 4]. P. Maji et al. (Eds.): PReMI 2013, LNCS 8251, pp. 115–120, 2013. c  Springer-Verlag Berlin Heidelberg 2013