IJMTES – ANN BASED FAST AND SLOW HAND MOVEMENTS CLASSIFICATION OF EEG: A W-CSP ALGORITHM APPROACH

Journal Title : International Journal of Modern Trends in Engineering and Science

Author’s Name : Febi Elizabath Jacob | Aswathy Madhu

Volume 02 Issue 11  Year 2015

ISSN no: 2348-3121

Page no: 38-43

Abstract This  paper  introduces  an application of artificial neural  network  (ANN) for the classification  of EEG  signal in the  context  of hand  movement  parameters. Brain Computer Interface (BCI) is a communication system which enables the user to control special computer applications by using his or her thoughts.  To achieve this, noninvasive electroencephalography (EEG) based BCI is used. An experiment was conducted to collect EEG data from subjects while they executed hand movements at two different speeds, namely fast and slow movements.  Depending  on BCI,  particular preprocessing and feature  extraction process  are  applied  to the  EEG  sample  of certain  length, which is then possible to detect the task-specific EEG signals or patterns from the EEG samples with a certain level of accuracy. The discriminative movement related features from the data sets were obtained using the Wavelet-Common Spatial Pattern (W-CSP) algorithm.  From these features, fast and slow hand movements were classified using ANN. The classification performances are analyzed by considering the number of input features, hidden neurons, training algorithms, connection between network   outputs   and targets, and mean square error. The outcomes of the analysis show that the best design of Levenberg Marquardt based neural network classifier can perform well with an average classification success rate of 97.50%.

Keywords Brain Computer Interface (BCI); Common Spatial Pattern (CSP); Discrete Wavelet Transform (DWT); Electroencephalography (EEG); movement related parameter; Artificial Neural Network (ANN).

Reference

[1] Neethu Robinson, A.P.Vinod, ‘EEG-Based Classification of Fast and Slow Hand Movements Using Wavelet-CSP Algorithm’, IEEE Trans. on Biomedical Engineering, Vol.60,NO.8, August (2013).
[2] B. Blankertz, R. Tomioka, S. Lemm, M. Kawanabe, and K.-R. Muller, ‘Optimizing spatial filters for robust EEG single-trial analysis’, IEEE Trans. Signal Processing, Vol. 25, No. 1, pp. 41–56, Jan. (2008).
[3] Thulasidas, M., Guan C. and Wu, ‘Robust classification of EEG signal for brain-computer interface’, IEEE Transactions on Neural Systems and Rehabilitation Engineering 14:24-9, (2006).
[4] G. Dornhege, B. Blankertz, M. Krauledat, F. Losch, G. Curio, and K. R. Muller., ‘Combined optimization of spatial and temporal filters for improving brain computer interfacing’,. IEEE Trans. Biomed. Eng, (2006).
[5] S. Lemm, B. Blankertz, G. Curio, and K. R. Muller, ‘Spatio-spectral filters for improving the classification of single trial EEG’, Biomedical Engineering, IEEE Transactions on, 52(9):1541–1548, (2005).
[6] G. E. Fabiani, D. J. McFarland, ‘Conversion of EEG activity into cursor movement by a Brain-computer interface(BCI)’, IEEE Trans. Neural Syst. Rehabilitation Eng., Vol. 12,, Sep. (2004).
[7] B. Blankertz, K.R Muller,G.Curio, and N. Birbaumer, ‘ The BCI Competition 2003: progress and perspectives in detection and discrimination of EEG single trials, IEEE Trans. Biomed. Eng., Vol.51, No.6, pp. 1044-1050, (2004).
[8] Haiping Lu, Konstantinos N. Plataniotis, ‘Regularized Common Spatial Patterns with Generic Learning for EEG Signal Classification’, IEEE Trans. Neural Syst. Rehabil. Eng, Aug (2003).
[9] Herbert Ramoser, Johannes Müller-Gerking,’Optimal Spatial Filtering of Single Trial EEG During Imagined Hand Movement’, IEEE Trans On Rehabilitation Engineering, VOL. 8, NO. 4, December (2000).
[10] E. Haselsteiner and G. Pfurtscheller, ‘Using time dependent neural networks for EEG classification,’ IEEE Trans. Rehab. Eng., vol. 6, pp. 457–463, Dec. (2000).
[11] Geeta Kaushik, Dr.H.P.Sinha, ‘ Biomedical Signal Analysis through Wavelets: A Review’ International Journal Volume 2, Issue 9, Sep (2012).
[12] Omarhodzic, S.Avadkovic, A.Nuhanovic, ‘Energy Distribution of EEG signal: EEG signal Wavelet Neural Network Classifier’, International journal of Biological Science, (2010).
[13] G. Ghodrati Amiri and A. Asadi,’Comparison of Different Methods of Wavelet and Wavelet Packet Transform in Processing Ground Motion Records ‘, International Journal of Civil Engineering. Vol. 7, No. 4, December (2009).
[14] Mohamed I. Mahmoud, Moawad I. M. Dessouky, ‘Comparison between Haar and Daubechies Wavelet Transformions on FPGA Technology’, International Journal of Electronics and Communications Engineering Vol:1 No:2, (2007).
[15] Ali Bashashati and Gary E Birch1, Rabab K Ward, ‘A survey of signal processing algorithms in brain computer interfaces based on electrical brain signals’, Journal Of Neural Engineering (2007).
[16] Lotte, F., Congedo M. And Arnalsi B., ‘A review of classification algorithms for EEG-based brain-computer interfaces’, Journal of Neural Engineering 4: R1-R13, (2007).
[17] Kalasurya KH, Perera ‘Forecasting epileptic seizures using EEG signals, wavelet transform and artificial neural networks’, IEEE international conference (2011).
[18] Victor Hugo Costa Albuquerque, Auzuir Ripardo de Alexandria, ‘Evaluation of Multilayer Perceptron and SelfOrganizing Map Neural Network Topologies applied on Microstructure Segmentation from Metallographic Images’,IEEE international conference (2011).
[19] K. K. Ang, Z. Y. Chin, H. Zhang, C. Guan, ‘Filter bank common spatial pattern (FBCSP) in brain-computer interface’, Proc. of IEEE Joint Conference on Neural Networks, pp. 2390-2397, Hongkong, June (2008).
[20] Barreto, G.A., Frota R.A. and Medeiros F.N.S.: ‘On the classification of mental tasks: a performance comparison of neural and statistical approaches’, Proc. IEEE Workshop on Machine Learning for Signal Processing.
[21] Leonardo Noriega, ‘Multilayer Perceptron Tutorial’.

Full Paper: Click Here

 

Scroll Up