Abstract
In this study, we compare various feature extraction methods for BrainComputer Interface (BCI) systems based on Electroencephalogram (EEG). BCI systems in general are executed in three major steps. In the first step, called preprocessing, we use certain normalization techniques to improve the accuracy of the results. As for the second step, we use various feature extraction techniques and compare their implications. In the third step we use K-nearest neighbor (kNN) algorithm for classification purposes. In our analysis, we use a data set presented in BCI Competition in 2003, which was obtained by performing a data collection technique performed on a healthy person. The data set was generated using six electrodes attached to that personwhile moving a cursor up and down on a computer screen. In this study, we describe how to perform feature extraction methods and suggest which one is the most suitable for this particular data set
Keywords
References
- Blankertz, B., Dornhege, G., Schafer, C., Krephi, R., Kohlmorgen, J., Müller, K.R., Kunzmann, V., Losch, F., and Curio, G., 2003. Boosting bit rates and error detection for the classfication of fast-paced motor commands based on single-trial EEG analysis, IEEE Trans. Neural Sys. R. Eng., 11(2), 127-131.
- Blankertz, B., Müller, K-R., Curio, G., Vaughan, T.M., Schalk, G., Wolpaw, J.R., Schlögl, A., Neuper, C., Pfurtscheller, G., Hinterberger, T., Schröder, M., Birbaumer, N., 2004. The BCI Competition 2003: Progress and Perspectives in Detection and Discrimination of EEG Sİngle Trials. , IEEE Transaction on Biomedical Engineering
- Chen, G. 2014. Are electroencephalogram (EEG) signals pseudo-random number generators? Journal of Computational and Applied Mathematics, 268, 1-4. Collura, T. F. 1993. History and evolution of electroencephalographic instruments and techniques. Journal of Clinical Neurophysiology, 10(4), 476–504.
- Kayikcioglu, T., Aydemir, O. 2010. A polynomial fitting and k-NN based approach for improving classification of motor imagery BCI data, Pattern Recognition Letters, 31, 1207-1215.
- Kotchoubey, B., Schheichert, H., Lutzenberger, W., and Birbaumer, N., 1997. A new method for self-regulation of slow cortical potentials in a timed paradigm, Appl. Psyhophysiol. Biofeedback, 22,(2), 77-93.
- Şeker, Ş.E., 2008. KNN (K Nearest neighborhood, en yakın k komşu).
- http://bilgisayarkavramlari.sadievrenseker.com/200 8/11/17/knn-k-nearest-neighborhood-en-yakin-k
- komsu/ (Erişim Tarihi:26.08.2014).
- Tapramaz, R., 2009. Sayısal Çözümleme, Literatür Yayıncılık.
- Xu, B-G., Song, A-G., 2008. Pattern recognition of motor imagery EEG using wavelet transform, J. Biomedical Science and Engineering, 1, 64-67.
- Vaughan, T. M., Miner, L.A., McFarland, D.J., and Wolpaw, J.R., 1998. EEG-based communication: analysis
- Electroencephalogr. Clin. Neurophysiol, 107, 428-433. EMG activity,
Abstract
Bu çalışmada Elektroensefalogram (EEG) tabanlı Beyin-Bilgisayar Arayüzü (BBA) sistemlerinde çeşitli öznitelik çıkarma yöntemleri karşılaştırılmıştır. BBA sistemleri genelde 3 temel aşamadan oluşur. Ön işleme aşamasında sınıflandırmada daha iyi sonuç elde etmek için normalizasyon yöntemi kullanılmıştır. Öznitelik çıkarmada çeşitli yöntemler kullanılmış ve karşılaştırılmıştır. Sınıflandırmada ise k-en yakın komşuluk (kNN) algoritması kullanılmıştır. Bu çalışmada, BCI Competition 2003 yarışmasında sunulan sağlıklı bir insandan alınmış veri seti kullanılmıştır. Bu veri seti, kişinin bilgisayar ekranında imleci yukarı ve aşağı yönde hareket ettirmesi esnasında altı adet elektrot ile kaydedilerek elde edilmiştir. Bu veri setinden alınan EEG tabanlı BBA verileri ön işleme yapıldıktan sonra, öznitelik çıkarma yöntemleri anlatılmış ve bu veri seti için uygun yöntem önerilmiştir.
Keywords
References
- Blankertz, B., Dornhege, G., Schafer, C., Krephi, R., Kohlmorgen, J., Müller, K.R., Kunzmann, V., Losch, F., and Curio, G., 2003. Boosting bit rates and error detection for the classfication of fast-paced motor commands based on single-trial EEG analysis, IEEE Trans. Neural Sys. R. Eng., 11(2), 127-131.
- Blankertz, B., Müller, K-R., Curio, G., Vaughan, T.M., Schalk, G., Wolpaw, J.R., Schlögl, A., Neuper, C., Pfurtscheller, G., Hinterberger, T., Schröder, M., Birbaumer, N., 2004. The BCI Competition 2003: Progress and Perspectives in Detection and Discrimination of EEG Sİngle Trials. , IEEE Transaction on Biomedical Engineering
- Chen, G. 2014. Are electroencephalogram (EEG) signals pseudo-random number generators? Journal of Computational and Applied Mathematics, 268, 1-4. Collura, T. F. 1993. History and evolution of electroencephalographic instruments and techniques. Journal of Clinical Neurophysiology, 10(4), 476–504.
- Kayikcioglu, T., Aydemir, O. 2010. A polynomial fitting and k-NN based approach for improving classification of motor imagery BCI data, Pattern Recognition Letters, 31, 1207-1215.
- Kotchoubey, B., Schheichert, H., Lutzenberger, W., and Birbaumer, N., 1997. A new method for self-regulation of slow cortical potentials in a timed paradigm, Appl. Psyhophysiol. Biofeedback, 22,(2), 77-93.
- Şeker, Ş.E., 2008. KNN (K Nearest neighborhood, en yakın k komşu).
- http://bilgisayarkavramlari.sadievrenseker.com/200 8/11/17/knn-k-nearest-neighborhood-en-yakin-k
- komsu/ (Erişim Tarihi:26.08.2014).
- Tapramaz, R., 2009. Sayısal Çözümleme, Literatür Yayıncılık.
- Xu, B-G., Song, A-G., 2008. Pattern recognition of motor imagery EEG using wavelet transform, J. Biomedical Science and Engineering, 1, 64-67.
- Vaughan, T. M., Miner, L.A., McFarland, D.J., and Wolpaw, J.R., 1998. EEG-based communication: analysis
- Electroencephalogr. Clin. Neurophysiol, 107, 428-433. EMG activity,
Details
| Primary Language | Turkish |
|---|---|
| Journal Section | SI: BioMechanics2014 |
| Authors | |
| Publication Date | December 30, 2014 |
| Submission Date | January 2, 2015 |
| Published in Issue | Year 2014 Volume: 2 Issue: 3 |
