Effects of Hidden Unit Sizes and Autoregressive Features in Mental Task Classification

Classification of electroencephalogram (EEG) signals extracted during mental tasks is a technique that is actively pursued for Brain Computer Interfaces (BCI) designs. In this paper, we compared the classification performances of univariate- autoregressive (AR) and multivariate autoregressive (MAR) models for representing EEG signals that were extracted during different mental tasks. Multilayer Perceptron (MLP) neural network (NN) trained by the backpropagation (BP) algorithm was used to classify these features into the different categories representing the mental tasks. Classification performances were also compared across different mental task combinations and 2 sets of hidden units (HU): 2 to 10 HU in steps of 2 and 20 to 100 HU in steps of 20. Five different mental tasks from 4 subjects were used in the experimental study and combinations of 2 different mental tasks were studied for each subject. Three different feature extraction methods with 6 th order were used to extract features from these EEG signals: AR coefficients computed with Burg's algorithm (ARBG), AR coefficients computed with stepwise least square algorithm (ARLS) and MAR coefficients computed with stepwise least square algorithm. The best results were obtained with 20 to 100 HU using ARBG. It is concluded that i) it is important to choose the suitable mental tasks for different individuals for a successful BCI design, ii) higher HU are more suitable and iii) ARBG is the most suitable feature extraction method.

[1]  S. Nishida,et al.  A new brain-computer interface design using fuzzy ARTMAP , 2002, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[2]  J. Pineda,et al.  Learning to control brain rhythms: making a brain-computer interface possible , 2003, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[3]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[4]  M. Osaka,et al.  Peak alpha frequency of EEG during a mental task: task difficulty and hemispheric differences. , 1984, Psychophysiology.

[5]  Ronald Fante.  Signal Analysis and Estimation , 1988 .

[6]  Keiichi Tokuda,et al.  RLS algorithms for adaptive AR spectrum analysis based on multi-band decomposition of the linear prediction error , 1996, Proceedings of Digital Processing Applications (TENCON '96).

[7]  G.E. Birch,et al.  A general framework for brain-computer interface design , 2003, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[8]  G. Pfurtscheller,et al.  Information transfer rate in a five-classes brain-computer interface , 2001, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[9]  M. Stokes,et al.  Cognitive tasks for driving a brain-computer interfacing system: a pilot study , 2004, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[10]  Z. Keirn,et al.  A new mode of communication between man and his surroundings , 1990, IEEE Transactions on Biomedical Engineering.

[11]  E Donchin,et al.  The mental prosthesis: assessing the speed of a P300-based brain-computer interface. , 2000, IEEE transactions on rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society.

[12]  E Donchin,et al.  Brain-computer interface technology: a review of the first international meeting. , 2000, IEEE transactions on rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society.

[13]  G Pfurtscheller,et al.  Current trends in Graz Brain-Computer Interface (BCI) research. , 2000, IEEE transactions on rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society.

[14]  S. Sengupta.  Introduction to Applied Statistical Signal Analysis , 1991 .

[15]  E. Donchin,et al.  EEG-based communication: prospects and problems. , 1996, IEEE transactions on rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society.

[16]  Arnold Neumaier,et al.  Estimation of parameters and eigenmodes of multivariate autoregressive models , 2001, TOMS.

[17]  E. A. Stolz,et al.  Multivariate Autoregressive Models for Classification of Spontaneous Electroencephalogram During Mental Tasks1 , 1998 .

[18]  Rescxidc.  RLS Algorithms for Adaptive AR Spectrum Analysis Based on Multi-Band Decomposition of the Linear Prediction Error , 1996 .

[19]  C.W. Anderson,et al.  Multivariate autoregressive models for classification of spontaneous electroencephalographic signals during mental tasks , 1998, IEEE Transactions on Biomedical Engineering.

[20]  H. Jasper,et al.  The ten-twenty electrode system of the International Federation. The International Federation of Clinical Neurophysiology. , 1999, Electroencephalography and clinical neurophysiology. Supplement.