P300 Detection Algorithm Based on Fisher Distance

Full Text (PDF, 247KB), PP.9-17

Views: 0 Downloads: 0

Author(s)

WANG Pan 1,* SHEN Ji-Zhong 1 SHEN Jin-He 1

1. Institute of Electronic Circuit and Information System, Zhejiang University, Hangzhou 310027, China

* Corresponding author.

DOI: https://doi.org/10.5815/ijmecs.2010.02.02

Received: 16 Sep. 2010 / Revised: 12 Oct. 2010 / Accepted: 5 Nov. 2010 / Published: 8 Dec. 2010

Index Terms

BCI, wavelet transform, P300, Fisher distance, Feature extraction

Abstract

With the aim to improve the divisibility of the features extracted by wavelet transformation in P300 detection, we researched the P300 frequency domain of event related potentials and the influence of mother wavelet selection towards the divisibility of extracted features, and then a novel P300 feature extraction method based on wavelet transform and Fisher distance. This can select features dynamically for a particular subject and thereby overcome the drawbacks of no systematic feature selection method during traditional P300 feature extraction based on wavelet transform. In this paper, both the BCI Competition 2003 and the BCI Competition 2005 data sets of P300 were used for validation, the experiment results showed that the proposed method can increase the divisibility by 121.8% of the features extracted by wavelet transformation, and the classification results showed that the proposed method can increase the classification accuracy by 1.2% while reduce 73.5% of the classification time. At the same time, integration of multi-domain algorithm is proposed based on the research of EEG feature extraction algorithm, and can be utilized in EEG preprocessing and feature extraction, even classification.

Cite This Paper

Pan WANG, Ji-zhong SHEN, Jin-he SHI, "P300 Detection Algorithm Based on Fisher Distance", International Journal of Modern Education and Computer Science(IJMECS), vol.2, no.2, pp.9-17, 2010. DOI:10.5815/ijmecs.2010.02.02

Reference

[1]D.J. Krusienski, E.W. Sellers, T.M. Vaughan. Common Spatio-Temporal Patterns for the P300 Speller[A]. In: Proceedings of the 3rd international IEEE EMBS Conference on Neural Engineering[C]. Hawaii, USA. 2007. 421-424.
[2]Schalk G, Dennis J, Thilo H,et a1. BCl2000:A general-purpose brain-computer interface(BCI) system[J].IEEE Transactions on Biomedical Engineering,2004,5l(6):1034-1043.
[3]Alexander Lenhardt, Matthias Kaper, Helge J. Ritter. An Adaptive P300-Based Online Brain–Computer Interface[J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2008, 16(2): 121-130.
[4]Tomonari Yamaguchi, Mitsuhiko Fujio, Katsuhiro Inoue, et al. Wavelet Analysis of EEG Singnals During Motor Imagery [A]. In: Proceedings of the 2008 International Conference on Wavelet Analysis and Pattern Recognition [C]. Hong Kong: 2008. 454-459.
[5]Kana Omori, Tomonari Yamaguchi, Katsuhiro Inoue. Feature Extraction from EEG Signals in P300 Spelling System[A]. In: ICROS-SICE International Joint Conference 2009[C]. Fukuoka International Congress Center, Japan. 2009. 849-852.
[6]Mathew Salvaris, Francisco Sepulveda. Wavelet and Ensemble of FLDs for P300 Classification[A]. In: Proceedings of the 4th international IEEE EMBS Conference on Neural Engineering[C]. Antalya, Turkay. 2009. 339-342.
[7]YANG Bang Hua, YAN Guo Zheng, YAN Bo. Extracting EEG Feature in Brain-computer Interface Based on Discrete Wavelet Transform [J]. Chinese Journal of Biomedical Engineering, 2006, 25(5): 518-522
[8]WU Xiao Pei, YE Zhong Fu, GUO Xiao Jing, et al. Dynamic Independent Component Analysis and its Application to EEG of Motor Imagination[J]. Chinese Journal of Biomedical Engineering, 2007, 26(6): 818-824.
[9]Chan F, Lam F, POoh P, et al. Detection of brainstem auditory evoked potential by adaptive filtering[J]. Med Biol Eng Comput, 1995, 33(2): 69-75.
[10]Seyedehmina Ayoubian Markazi, Lampros.S.Stergioulas, Anusha Ramchurn, et al. Wavelet Filtering of the P300 Component in Event-Related Potentials[A]. In: Proceeding of the 28th IEEE EMBS Annual International Conference[C]. New York, USA. 2006. 1719-1722.
[11]YANG Li Cai, LI Jin Liang, YAO Yu Cui, et al. P300 Detection Algorithm Based on Wavelet Decomposition and Support Vector Machines[J]. Chinese Journal of Biomedical Engineering, 2007,26(6): 804-809.
[12]Hilit Serby, Elad Yom-Tov, Gideon F. Inbar. An Improved P300-Based Brain-Computer Interface[J]. IEEE Trans on Neural System and Rehabilitation Engineering, 2005,13(1): 89-98.
[13]WANG Da Kui, PENG Jin Ye. Wavelet Analysis and Application in Signal Processing [M]. Beijing: Publishing House of Electronics Industry, 2006.1.
[14]DONG Chang Hong. Principle and Application of Matlab wavelet analysis toolbox[M]. Being: National Defense Industry Press, 2004.1.
[15]D. Huang, C. Xiang, S.S. Ge. Recursive Fisher Linear Discriminant for BCI Applications [A]. In: ISSNIP 2007 3rd International Conference [C]. Melbourne, Australia: 2007. 383-388.
[16]Ozair Idris Khan, Sang-Hyuk Kim, Adil Khan, et al. Extraction of P300 Using Constrained Independent Component Analysis[A]. In: 31st Annual International Conference of the IEEE EMBS[C]. Minnesota, USA. 2009. 4031-4034.
[17]Abeer E. Selim, Manal Abdel Wahed, Yasser M. Kadah. Machine Learning Methodologies in P300 Speller Brain-Computer Interface Systems[A]. In: 26rd National Radio Science Conference[C]. Future Univ, Egypt. 2009. 1-8.
[18]A. Bashashati, M. Fatourechi, R. K Ward, et al. A Survey of signal processing algorithms in brain-computer interfaces based on electrical brain signals [J]. J. Neural Eng, 2007, 32-57.