Motor Imagery Signal Classification for a Four State Brain Machine Interface

Authors: Hema C. R., Paulraj M. P., S. Yaacob, A. H. Adom, R. Nagarajan

Abstract:

Motor imagery classification provides an important basis for designing Brain Machine Interfaces [BMI]. A BMI captures and decodes brain EEG signals and transforms human thought into actions. The ability of an individual to control his EEG through imaginary mental tasks enables him to control devices through the BMI. This paper presents a method to design a four state BMI using EEG signals recorded from the C3 and C4 locations. Principle features extracted through principle component analysis of the segmented EEG are analyzed using two novel classification algorithms using Elman recurrent neural network and functional link neural network. Performance of both classifiers is evaluated using a particle swarm optimization training algorithm; results are also compared with the conventional back propagation training algorithm. EEG motor imagery recorded from two subjects is used in the offline analysis. From overall classification performance it is observed that the BP algorithm has higher average classification of 93.5%, while the PSO algorithm has better training time and maximum classification. The proposed methods promises to provide a useful alternative general procedure for motor imagery classification

Keywords: Motor Imagery, Brain Machine Interfaces, Neural Networks, Particle Swarm Optimization, EEG signal processing.

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1334325

References:

[1] G. Pfurtscheller and C. Neuper, "Motor Imagery and Direct Brain- Computer Communication," IEEE Transactions Vol. 89, No.7, July 2001, pp 1123-1134.
[2] S. Cososchi, R. Stungaru, A Unureanu and M. Ungureanu, " EEG Features Extraction for Motor Imagery," Proc. 28th IEEE EMBS Annual Intl. Conf. , USA, 2006, pp 1142 - 1145.
[3] G. Pfurtscheller, C. Neuper, A. Schlogl and K Lugger, "Separability of EEG Signals recorded During right and Left Motor Imagery using Adaptive Autoregressive Parameters," IEEE Trans. Rehabilitation Engineering, Vol.6, No.3, Sep 1998 , pp 316 - 325.
[4] C.W. Anderson, E.A. Stolz and S.Shamsunder , "Discriminating Mental Tasks using EEG represented by AR Models", IEEE-EMBC and CMBEC , 1997 pp 875-876.
[5] Z.A Keirn and J I. Aunon, "A New Mode of Communication between Man and his Surroundings" IEEE Trans. Biomedical Engineering, 1990, Vol. 37.no. 12. pp 1209-1214.
[6] Hema C.R., S. Yaacob, A.H. Adom, R. Nagarajan, Paulraj M.P "Classification of EEG Mental Task Signals for A Brain Machine Interface-, 3rd Intl. Colloquium on Signal Processing and its Applications, Malaysia, 2007 , pp 129 -131.
[7] W. Xu, C Guan, C.E. Siong, S Ranganatha, M. Thulasidas, J. Wu, " High Accuracy Classification of EEG Signal" proceedings of 17th International Conference on Pattern Recognition , 2004.
[8] Wang, J.Deng, B.He, "Classification of Motor Imagery EEG Patterns and their Topographic Representation", Proc. Of 26th Annual Internal. Conf. of IEEE EMBS, 2004, pp 4359-4362.
[9] Hema C.R., S. Yaacob, A.H.Adom, Paulraj M.P, R. Nagarajan, "Fuzzy Based Classification Of EEG Mental Tasks For A Brain Machine Interface" IEEE, Third International Conference On Intelligent Information Hiding And Multimedia Signal Processing , Taiwan , 2007, pp 53 -56.
[10] D.G. Domenick, "International 10-20 Electrode Placement System for Sleep", 1998. http://members.aol.com/aduial/1020sys.html.
[11] C.W. Anderson, J.N. Knight, T.O-Connor, Michael J Kirby, Artem Sokolov, Geometric Subspace Methods and Time-Delay Embedding for EEG Artifact Removal and Classification. IEEE Transactions on Neural Systems and Rehabilitation Engineering Vol 14 No. 2, June 2006, pp142-146.
[12] V Bostanov, "BCI Competition 2003- Data Set Ib and IIb: Feature Extraction from event Related Brain Potentials with the Continuos Wavelet Transform and t-Value Scalogram", IEEE Trans. Biomedical Engineering, 2004, pp 1057- 1061.
[13] B.Wan, B.Dhakal, H. QI, Xin Zhu, "Multi-method Synthesizing to Detect and Classify Epileptic Waves in EEG", Proc. Fourth International Conference on Computer and Information Technology, 2004.
[14] A. P. Engelbrecht, Computational Intelligence an Introduction, John Wiley and Sons Ltd. 2002.
[15] P.K. Dash, A.C. Liew, H.P. Satpathy, A functional link neural Network for Short Term Electric Load Forecasting Journal of Intelligent and Fuzzy Systems Vol. 7, Issue 9 , 1999, pp 209-221.
[16] Paulraj M.P, Sazali Yaacob, Mohd. Kamel Wan Ibrahim, Karthigeyan, "Active Noise Cancellation of Pink Noise source in Vehicles using Functional Link Networks", Proc. Second Intl. Conf. on Artificial Intelligence in Engineering & Technology, 2004 Kota Kinabalu, Malaysia, Vol2 pp 8.4-810.
[17] James Kennedy and Russell Eberhart , Particle Swarm Optimization, Proc. IEEE International Conf. on Neural Networks, Perth , Vol. 4, pp 1942-1948,1995
[18] Yuhui Shi and Russell C. Eberhart, Parameter Selection in Particle Swarm Optimization, Evolutionary Programming, Springer Verlag, New York , Vol. 7 , pp 591 - 600, 1998.
[19] S.N.Sivanandam, M.Paulraj, Introduction to Artificial Neural Networks Vikas Publishing House, India. 2003.
[20] D.G. Domenick. (1998). International 10-20 Electrode Placement System for Sleep. (Online) Available:http://members.aol.com/aduial/1020sys.html