SUN Hong-yu (孙红雨)1,2, XIANG Yang (向阳)2, SUN Yao-ru (孙杳如)2,DAI Yi-wen (戴宜雯)1
(1. College of Information and Electrical Engineering, Shandong University of Science and Technology, Qingdao 266510, China; 2. School of Electronics and Information Engineering, Tongji University, Shanghai 200092, China)
Abstract:This paper presents the application of an effective electroencephalogram (EEG) based brain-computer interface (BCI) for controlling a remote car in a practical environment. The BCI uses the motor imaginary to translate the subject's motor intention into a control signal through classifying EEG patterns of different imaginary tasks. The system is composed of a remote car, a digital signal processor and a wireless data transfer module. The performance of the BCI was found to be robust to distract motor imaginary in the remote car controlling and need a short training time. The experimental results indicate that the successful ternary-control by using motor imaginry may be practicable in an uncontrolled environment.
Key words:electroencephalogram (EEG);brain-computer interface (BCI);motor imaginary;online classification
CLD number: TN911.71 Document code: A
Article ID: 1674-8042(2012)02-0200-05doi: 10.3969/j.issn.1674-8042.2012.02.020
References
[1] Wolpaw J R, Birbaumer N, McFarland D, et al. Brain-computer interfaces (BCIs) for communication and control: current status. Clin Neurophysiol, 2002, 113: 767-791.
[2] GUAN Cun-tai, Thulasidas M, WU Jian-kang. High performance P300 speller for brain-computer interface. Proc. of IEEE International Workshop on Biomedical Circuits and Systems, 2004: S3-5/INV-13-16.
[3] Sutter E E. The visual evoked response as a communication channel. Proc. of IEEE/NSF Symposium on Biosensors, Los Angeles, Calif, USA, 1984: 95-100.
[4] Lalor E, Kelly S, Finucane C, et al. Steady-state VEP-based brain-computer interface control in an immersive 3D gaming environment. EURASIP Journal on Applied Signal Processing, 2005, (19): 3156-3164.
[5] Birbaumer N, Hinterberger T, Iversen I, et al. A spelling device for the paralysed. Nature, 1999, 398:297-298.
[6] Pfurtscheller G, Neuper C. Motor imaginary and direct braincomputer communication. Proc. of the IEEE, 2001,89(7): 1123-1134.
[7] Wolpaw J R, McFarland D J. Control of a two-dimensional movement signal by a noninvasive brain-computer interface in humans. Proc. of the National Academy of Sciences (PNAS), 2004, 101(51): 17849-17854.
[8] Pfurtscheller G, Guger C, Müller G, et al. Brain oscillations control hand orthosis in a tetraplegic. Neuroscience Letters, 2000, 292: 211-214.
[9] Birbaumer N, Ghanayim N, Hinterberger T, et al. A spelling device for the paralysed. Nature, 1999, 398: 297-298.
[10] Millan J R, Buttfield A, Vidaurre C, et al. Adaptation in brain-computer interfaces. Toward brain-computer interfacing, Neural information processing series, MIT Press, 2007: 303-326.
[11] Buttfield A, Ferrez P W, Millan J R. Towards a robust bci: error potentials and online learning. IEEE Trans. on Neural System Rehabilitation Engineering, 2006, 14(2): 164-168.
[12] Sharbrough F, Chatrian G E, Lesser R P, et al. American electroencephalographic society guide lines for standard electrode position nomenclature. Clinical Neurophysiology, 1991, 8(2): 200-202.
[13] Jung T P, Humphries C, Lee T W, et al. Removing electroencephalographic artifacts: comparison between ICA and PCA. Neural Networks Signal Processing 1998, 8: 63-72.
[14] Vigario R, Sarela J, Jousmaki V, et al. Independent component approach to the analysis of EEG and MEG recordings. IEEE Trans. on Biomedical Engineering, 2000, 47(5): 589-593.
[15] ZHANG Jia-cai, ZHAO Xiao-jie, LIU Yi-jun, et al. Mining the independent source of ERP components with ICA decomposition. Lecture Notes Computer Science 3973 (ISNN 2006), Springer-Verlag Berlin Heidelberg. 2006: 592-599.
[16] James C J, Gibson O J. Temporally constrained ica: an application to artifact rejection in electromagnetic brain signal analysis. IEEE Trans. on Biomedical Engineering, 2003, 50(9): 1108-1116.
[17] TichavskP, Koldovsk Z, Oja E. Performance analysis of the FastICA algorithm and Cramér-Rao bounds for linear independent component analysis. IEEE Trans. on Signal Processing, 2006, 54(4): 1189-1203.
[18] Blankertz B, Dornhege G, Schfer C, et al. Boosting bit rates and error detection for the classification of fast-paced motor commands based on single-trial EEG analysis. IEEE Trans. on Neural System Rehabilitation Engineering, 2003, 11: 127-131.
[19] Cristianini N, Shawe-Taylor J. An introduction to support vector machines. Cambridge University Press, Cambridge, UK, 2000.
[20] Kaper M, Meinicke P, Grossekathoefer U, et al. BCI competition 2003-data set IIb: support vector machines for the P300 speller paradigm. IEEE Trans. on Biomedical Engineering, 2004, 51: 1073-1076.
[21] Tsui C S, Gan J Q, Roberts S J. A self-paced brain-computer interface for controlling a robot simulator: an online event labelling paradigm and an extended Kalman filter based algorithm for online training. Medical and Biological Engineering and Computing, 2009, 47(3): 257-265.
[22] Smola A J, Schlkopf B, Williamson R C, et al. New support vector algorithms. Neural Computation, 2000, 12(5): 1207-1245.
[full text view]