Abstract
Translation of human intentions into control signals for a computer, so called Brain-Computer Interface (BCI), has been a growing research field during the last years. In this way, classification of mental tasks is under investigation in the BCI society as a basic research. In this paper, a Weighted Distance Nearest Neighbor (WDNN) classifier is presented to improve the classification rate between the left and right imagery tasks in which a weight is assigned to each stored instance. The specified weight of each instance is then used for calculating the distance of a test pattern to that instance. We propose an iterative learning algorithm to specify the weights of training instances such that the error rate of the classifier on training data is minimized. ElectroEncephaloGram (EEG) signals are caught from four familiar subjects with the cue-based BCI. The proposed WDNN classifier is applied to the band power and fractal dimension features, which are extracted from EEG signals to classify mental tasks. Results show that our proposed method performs better in some subjects in comparison with the LDA and SVM, as well-known classifiers in the BCI field.
Chapter PDF
Similar content being viewed by others
References
Pfurtscheller, G., Neuper, C.: Motor imagery and direct brain-computer communication. In: Proc. IEEE, pp. 1123–1134. IEEE Computer Society Press, Los Alamitos (2001)
Pfurtscheller, G., Lopes, S.: Event related desynchronization: Hand book of electroenceph. And clininical Neurophisiology. Revised edition, vol. 6. Elsevier, Amsterdam (1999)
Bozorgzadeh, Z., Birch, G.E., Mason, S.G.: The LF-ASD brain computer interface: on-line identification of imagined finger flexions in the spontaneous EEG of able-bodied subjects. In: IEEE Intern. Conf. Acous. Speech proc., vol. 6, pp. 2385–2388 (2000)
Boostani, R., Moradi, M.H.: A new approach in the BCI research based on fractal dimension as feature and Adaboost as classifier. Journ. Neural Eng. 1, 4 (2004)
Boostani, R., Graimann, B., Moradi, M.H., Pfurtscheller, G.: A Comparison Approach toward Finding the Best Feature and Classifier in Cue-Based BCI. Journ. Medic. Bio. Eng. Comp. 6 (2007)
Schlögl, A., Flotzinger, D., Pfurtscheller, G.: Adaptive Autoregressive Modeling used for Single-trial EEG Classification. Biomediz. Tech. 42, 162–167 (1997)
Graimann, B., Huggins, J.E., Levine, S.P., Pfurtscheller, G.: Toward a direct brain interface based on human subdural recordings and wavelet-packet analysis. IEEE Trans. Biomed. Eng. 51, 954–962 (2004)
Pfurtscheller, G., Neuper, C., Schlogl, A., Lugger, K.: Separability of EEG signals recorded during right and left motor imagery using adaptive autoregressive parameters. IEEE Trans. Rehab. Eng. 6, 316–328 (1998)
Haselsteiner, E., Pfurtscheller, G.: Using time-dependent neural networks for EEG classification. IEEE Trans. on Rehab. Eng. 8, 457–463 (2000)
Kalcher, J., Flotzinger, D., Pfurtscheller, G.: A New Approach to a Brain-Computer-Interface (BCI) based on Learning Vector Quantization (LVQ3). In: Proceed. Ann. Intern. Conf. IEEE, vol. 4, pp. 1658–1659 (1992)
Flotzinger, D., Pregenzer, M., Pfurtscheller, G.: Feature selection with distinction sensitive learning vector quantisation and genetic algorithms. IEEE Intern. Conf. Comp. Intell. 6, 3448–3451 (1994)
Deriche, M., Al-Ani, A.: A new algorithm for EEG feature selection using mutual information. In: IEEE Intern. Conf. Acous. Speech, Signal Proc. ICASSP, vol. 2, pp. 1057–1060 (2001)
Cover, T.M., Hart, P.E.: Nearest Neighbor Pattern Classification. IEEE Trans. on Info. Theo. 13, 21–27 (1967)
Dasarathy, B.V.: Nearest Neighbor (NN) Norms: NN Pattern Classification Techniques. IEEE Computer Society Press, Los Ala. CA (1991)
Goldberger, J., Roweis, S., Hinton, G., Salakhutdinov, R.: Neighbourhood component analysis. Neur. Info. Proc. Sys (NIPS) 17, 513–520 (2004)
Weinberger, K., Blitzer, J., Saul, L.: Distance metric learning for large margin nearest neighbor classification. In: Weiss, B.S., Platt, J. (eds.) Advances in Neural Information Processing Systems, p. 18 (2005)
Wang, J., Neskovic, P., Cooper, L.N.: Neighbourhood selection in the k-nearest neighbor rule using statistical confidence. Patt. Recog. 39, 417–423 (2006)
Wang, J., Neskovic, P., Cooper, L.N.: Improving nearest neighbor rule with a simple adaptive distance measure. Pattern Recognition Letters 28, 207–213 (2007)
Xiao-Yuan, J., David, Z., Yuan-Yan, T.: An improved LDA Approach. IEEE Trans. Sys. Man Cyber. 34, 5 (2004)
Esteller, R.: Detection of Seizure Onset in Epileptic Patients from Intracranial EEG Signals. Ph. D. thesis, School of Electrical and Computer Engineering Georgia Institute of Technology (2000)
Higuchi, T.: Approach to an Irregular Time Series on the Basis of Fractal Theory. Physica D 31, 277–283 (1988)
Fawcett, T.: ROC Graphs: Notes and Practical Considerations for Researchers, Technical Report HPL-2003-4, HP Labs (2003)
Lachiche, N., Flach, P.: Improving accuracy and cost of two-class and multi-class probabilistic classifiers using ROC curves. In: 20th Intern. Conf. Machine Learning (ICML 2003), pp. 416–423 (2003)
Vapnic, V.N.: Statistical learning theory. John Wiley and Sons, New York (1998)
Fukunaga, K.: Introduction to Statistical Pattern Classification. Academic Press, San Diego, Calif. (1999)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2007 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Dehzangi, O., Jahromi, M.Z., Taheri, S. (2007). High Performance Classification of Two Imagery Tasks in the Cue-Based Brain Computer Interface. In: Rajapakse, J.C., Schmidt, B., Volkert, G. (eds) Pattern Recognition in Bioinformatics. PRIB 2007. Lecture Notes in Computer Science(), vol 4774. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-75286-8_36
Download citation
DOI: https://doi.org/10.1007/978-3-540-75286-8_36
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-75285-1
Online ISBN: 978-3-540-75286-8
eBook Packages: Computer ScienceComputer Science (R0)