Classification-guided feature selection for NIRS-based BCI
作者： Vikas Gottemukkula , Reza Derakhshani
关键词:
摘要: Motor movements induce distinct patterns in the hemodynamics of motor cortex, which may be captured by Near-Infrared Spectroscopy (NIRS) for Brain Computer Interfaces (BCI). We present a classification-guided (wrapper) method time-domain NIRS feature extraction to classify left and right hand movements. Four different wrapper methods, based on univariate multivariate ranking sequential forward backward selection, along with three classifiers (k-Nearest neighbor, Bayes, Support Vector Machines) were studied. Using data from two subjects we show that rank-based conjunction polynomial SVMs can achieve 100% sensitivity specificity separating (5-fold cross validation). Results promise methods classifying signals BCI applications.
sci-hub.se 参考文章(11)
Takayuki Nozawa, Toshiyuki Kondo, A Comparison of Artifact Reduction Methods for Real-Time Analysis of fNIRS Data Lecture Notes in Computer Science. pp. 413- 422 ,(2009) , 10.1007/978-3-642-02559-4_45
Randall L. Barbour, Harry L. Graber, Yong Xu, Yaling Pei, Glenn R. Wylie, Gerald T. Voelbel, John DeLuca, Andrei V. Medvedev, Systems and Strategies for Accessing the Information Content of fNIRS Imaging in Support of Noninvasive BCI Applications Foundations of Augmented Cognition. Neuroergonomics and Operational Neuroscience. pp. 709- 718 ,(2009) , 10.1007/978-3-642-02812-0_80
Yuich Fukui, Yusaku Ajichi, Eiji Okada, Monte Carlo Prediction of Near-Infrared Light Propagation in Realistic Adult and Neonatal Head Models Applied Optics. ,vol. 42, pp. 2881- 2887 ,(2003) , 10.1364/AO.42.002881
Brendan Z Allison, Elizabeth Winter Wolpaw, Jonathan R Wolpaw, Brain–computer interface systems: progress and prospects Expert Review of Medical Devices. ,vol. 4, pp. 463- 474 ,(2007) , 10.1586/17434440.4.4.463
Ranganatha Sitaram, Haihong Zhang, Cuntai Guan, Manoj Thulasidas, Yoko Hoshi, Akihiro Ishikawa, Koji Shimizu, Niels Birbaumer, Temporal classification of multichannel near-infrared spectroscopy signals of motor imagery for developing a brain-computer interface. NeuroImage. ,vol. 34, pp. 1416- 1427 ,(2007) , 10.1016/J.NEUROIMAGE.2006.11.005
T.J. Huppert, R.D. Hoge, S.G. Diamond, M.A. Franceschini, D.A. Boas, A temporal comparison of BOLD, ASL, and NIRS hemodynamic responses to motor stimuli in adult humans NeuroImage. ,vol. 29, pp. 368- 382 ,(2006) , 10.1016/J.NEUROIMAGE.2005.08.065
Shirley M Coyle, Tomás E Ward, Charles M Markham, Brain-computer interface using a simplified functional near-infrared spectroscopy system. Journal of Neural Engineering. ,vol. 4, pp. 219- 226 ,(2007) , 10.1088/1741-2560/4/3/007
Björn Waske, Sebastian Schiefer, Matthias Braun, None, Random Feature Selection for Decision Tree Classification of Multi-temporal SAR Data international geoscience and remote sensing symposium. pp. 168- 171 ,(2006) , 10.1109/IGARSS.2006.48
T. Cover, P. Hart, Nearest neighbor pattern classification IEEE Transactions on Information Theory. ,vol. 13, pp. 21- 27 ,(1967) , 10.1109/TIT.1967.1053964
Shirley Coyle, Tomás Ward, Charles Markham, Gary McDarby, On the suitability of near-infrared (NIR) systems for next-generation brain?computer interfaces Physiological Measurement. ,vol. 25, pp. 815- 822 ,(2004) , 10.1088/0967-3334/25/4/003