Time Domain Parameters for Online Feedback fNIRS-Based Brain-Computer Interface Systems

详细信息    查看全文

• 作者：Tuan Hoang (20)
  Dat Tran (20)
  Khoa Truong (21)
  Trung Le (20)
  Xu Huang (21)
  Dharmendra Sharma (20)
  Toi Vo (21)
  
• 关键词：BCI ; fNIRS ; high order moment ; motor imagery ; person identification ; Hjorth parameters
• 刊名：Lecture Notes in Computer Science
• 出版年：2012
• 出版时间：2012
• 年：2012
• 卷：7664
• 期：1
• 页码：202-209
• 全文大小：254KB
• 参考文献：1. Arthurs, O.J., Boniface, S.: What Aspect of the fMRI BOLD Signal Best Reflects the Underlying Electrophysiology in Human Somatosensory Cortex? J. Clin. Neurophysiol.?114, 1203-212 (2003) dx.doi.org/10.1016/S1388-2457(03)00080-4">CrossRef
  2. Biel, L., Pettersson, O., Philipson, L., Wide, P.: ECG Analysis: a New Approach in Human Identification. IEEE T. Instrum. Meas.?50, 808-12 (2001) dx.doi.org/10.1109/19.930458">CrossRef
  3. Gottemukkula, V., Derakhshani, R.: Classification-Guided Feature Selection for NIRS-based BCI. In: The 5th International IEEE EMBS Conference on Neural Engineering, Mexico (2011)
  4. Hjorth, B.: EEG Analysis Based on Time Domain Properties. Electroenceph. Clin. Neurophysiol.?29, 306-10 (1970) dx.doi.org/10.1016/0013-4694(70)90143-4">CrossRef
  5. Hjorth, B.: The Physical Significance of Time Domain Descriptors in EEG Analysis. Electroenceph. Clin. Neurophysiol.?34, 321-25 (1973) dx.doi.org/10.1016/0013-4694(73)90260-5">CrossRef
  6. Hoang, T., Tran, D., Truong, K., Nguyen, P., Huang, X., Sharma, D.: High Order Moment Features for NIRS-based Classification Problems. In: The 4th International Conference on Biomolecular Engineering, Viet Nam (2012)
  7. Krepki, R., Curio, G., Blankertz, B., Muller, K.R.: Berlin Brain-Computer Interface - The HCI comm. Channel for Discovery. Int. J. Human-Computer Studies?65, 460-77 (2007) dx.doi.org/10.1016/j.ijhcs.2006.11.010">CrossRef
  8. Logothetis, N.K., Pauls, J., Augath, M., Trinath, T., Oeltermann, A.: Neurophysiological Investigation of the Basis of the fMRI Signal. Nature?412, 150-57 (2001) dx.doi.org/10.1038/35084005">CrossRef
  9. Marcel, S., Millan, J.D.R.: Person Authentication Using Brainwaves (EEG) and Maximum A Posteriori Model Adaptation. IEEE T. Pattern Anal.?29, 743-52 (2007) dx.doi.org/10.1109/TPAMI.2007.1012">CrossRef
  10. Navascues, M.A., Sebastian, M.V.: Time Domain Indices and Discrete Power Spectrum in Electroecephalographic Processing. Int. J. of Comp. Mathematics?86, 1968-978 (2009) dx.doi.org/10.1080/00207160903023599">CrossRef
  11. Niide, W., Tsubone, T., Wada, Y.: Identification of moving limb using near infrared spectroscopic signals for brain activation. In: Proc. IJCNN 2009, USA (2009)
  12. Riera, A., Soria-Frisch, A., Caparrini, M., Grau, C., Ruffini, G.: Unobtrusive Biometric System Based on EEG Analysis. EURASIP J. Adv. in Sig. Processing, 18-5 (2008)
  13. Rowe, R.K., Miller, W.A., Ge, N., Robinson, R.M.: U.S. Patent No. 7203345. Washington, DC: U.S. (2007)
  14. Sitaram, R., Zhang, H., Guan, C., Thulasidas, M., Hoshi, Y., Ishikawa, A., Shimizu, K., Birbaumer, N.: Temporal classification of multichannel near-infrared spectroscopy signals of motor imagery for developing a BCI. J. NeuroImage?34, 1416-427 (2007) dx.doi.org/10.1016/j.neuroimage.2006.11.005">CrossRef
  15. Villringer, A., Obrig, H.: Near-infrared spectroscopy and imaging. In: Toga, A.W., Mazziotta, J.C. (eds.) Brain Mapping: The Methods. Academic Press, Inc., San Diego (2002)
  16. Wolpaw, J.R., Birbaumer, N., McFarland, D.J., Pfurtscheller, G., Vaughan, T.M.: BCIs for communication and control. J. Clinical Neurophysiology?113, 767-91 (2007) dx.doi.org/10.1016/S1388-2457(02)00057-3">CrossRef
  
• 作者单位：Tuan Hoang (20)
  Dat Tran (20)
  Khoa Truong (21)
  Trung Le (20)
  Xu Huang (21)
  Dharmendra Sharma (20)
  Toi Vo (21)
  
  20. Faculty of Information Sciences and Engineering, University of Canberra, Australia
  21. Department of Biomedical Engineering, International University, Vietnam
  
• ISSN：1611-3349

文摘

We investigate time domain parameters called high order moments in functional Near Infrared Spectroscopy (fNIRS) signal and propose to use them as new brain features in fNIRS-based Brain Computer Interface (BCI) research. These high order moments are well appropriate with fNIRS data without any special preprocessing or filtering step. Therefore, they could be used to guide users in feedback fNIRS-based BCI experiments. We performed experiments on motor imagery and person identification problems with the 2nd order moment, 4th order moment and a combination of these moments. Experimental results showed that these features provided high accuracy. For motor imagery problem, our system could achieve accuracy up to 99.5% for subject independent problem and varies between 86.5±5.4% and 97.0±2.1% for subject dependent problem. For person identification problem, our system could achieve accuracy nearly 100%. Comparing with other systems that used non-filtered raw signal as feature, these features are more stable than the raw signal because of noise reduction. We also found that the 2nd order moment alone could be an excellent and efficient feature for fNIRS-based BCI systems.