Recognition of Motor Imagery Based on Dynamic Features of EEG Signals

Subject Areas : Renewable energy

Negar  Dashti ¹ (Department of Electrical Engineering, Najafabad Branch,, Islamic Azad University,, Najafabad, Iran)
Mahdi  Khezri ² (Digital Processing and Machine Vision Research Center, Najafabad Branch, Islamic Azad University, Najafabad, Iran)

Received: 2020-05-19 Accepted : 2020-07-20 Published : 2020-10-22

Keywords: Classification, Wavelet Transform, SVM, Motor imagery, Nonlinear features,

Abstract :

The control of artificial limbs can be done by distinguishing the patterns of imagined movement using the EEG signals. The aim of this study was to identify hand and foot imagery movements based on EEG signals. The Iva dataset of BCI Competition III, which includes EEG signals from 5 healthy individuals in C3, C4 and CZ channels, was used to design the imagery movements detection system. Initially, the basic components of EEG signal noise were removed using the MSPCA method. In the next step, the EEG signals were decomposed in two different ways including frequency filtering using the Butterworth filter and the wavelet packet transform (WPT). In this study, the detrended Fluctuation Analysis, Fractal dimension, Correlation dimension, Lempel-ziv complexity and Entropy as nonlinear dynamics features, were calculated for the signals. In both decomposition methods, the desired features were calculated for the temporal version of the specified subbands. In order to determine the best performance of the system, different combinations of the channels and the features were evaluated. The wavelet-based decomposition method, in the case of using all three channels and five features, provided the highest recognition accuracy; So that using support vector machine (SVM) classification method, the accuracy of 93% was obtained in identifying the desired movements.

References:

[1] B. Blankertz, G. Dornhege, M. Krauledat, K. Müller, G. Curio, "The non-invasive Berlin Brain-computer interface: fast acquisition of effective performance in untrained subjects", NeuroImage, vol. 37, pp. 539-550, Aug. 2007 (doi: 10.1016/j.neuroimage.2007.01.051).

[2] E.W. Sellers, E. Donchin, "A P300-based brain-computer interface: initial tests by ALS patients", Clin Neurophysiol, vol. 117, pp. 538-548, Mar. 2006 (doi: 10.1016/j.clinph.2005.06.027).

[3] X. Gao, D. Xu, M. Cheng, S. Gao, "A BCI-based environmental controller for the Motion disabled", IEEE Trans on Neural Systems and Rehabilitation Engineering, vol. 11, no. 2, pp. 137–140, Jun. 2003 (doi: 10.1109/TNSRE.2003.814449).

[4] B. Graimann, B. Allison, G. Pfurtscheller, "Brain-computer interfaces: A gentle introduction", In: Graimann B., Pfurtscheller G., Allison B. (eds) Brain-Computer Interfaces. The Frontiers Collection. Springer, Berlin, Heidelberg, pp. 1-27, 2010 (doi: 10.1007/978-3-642-02091-9_1).

[5] J. Meng, G. Liu, G. Huang, X. Zhu, "Automated selecting subset of channels based on CSP in motor imagery brain-computer interface system", IEEE International Conference on Robotics and Biomimetics (ROBIO), Guilin, China, pp. 2290-2294, Dec. 2009 (doi: 10.1109/ROBIO.2009.5420462).

[6] M. Li, C. Lu, "The recognition of EEG with CSSD and SVM", Proceedings of the IEEE/WCICA, Beijing, China, pp. 4741-4746, Nov. 2012 (doi: 10.1109/WCICA.2012.6359377).

[7] N. Robinson, A.P. Vinod, K.K. Ang, K.P. Tee, C.T. Guan, "EEG-based classification of fast and slow hand movements using wavelet-CSP algorithm", IEEE Trans on Biomedical Engineering, vol. 60, no. 8, pp. 2123-2132, Aug. 2013 (doi: 10.1109/TBME.2013.2248153).

[8] Y. Siuly, P. Li, P. Wen, "Modified CC-LR algorithm with three diverse feature sets for motor imagery tasks classification in EEG based brain computer interface", Comput Methods Programs Biomed, vol. 113 no.13, pp. 767-780, Jan. 2014 (doi: 10.1016/j.cmpb.2013.12.020).

[9] M. Severens, M. Perusquia-Hernandez, B. Nienhuis, J. Farquhar and J. Duysens, "Using Actual and Imagined Walking Related Desynchronization Features in a BCI", IEEE Trans Neural Syst Rehabil Eng, vol. 23, no. 5, pp. 877-886, Sept. 2015 (doi: 10.1109/TNSRE.2014.2371391).

[10] M. Ma, L. Guo, K. Su and D. Liang, "Classification of motor imagery EEG signals based on wavelet transform and sample entropy", 2017 IEEE 2^nd Advanced Information Technology, Electronic and Automation Control Conference (IAEAC), Chongqing, China, pp. 905-910, Oct. 2017 (doi: 10.1109/IAEAC.2017.8054145).

[11] S. Enshaeifar, C. C. Took, C. Park and D. P. Mandic, "Quaternion Common Spatial Patterns", IEEE Trans Neural Syst Rehabil Eng, vol. 25, no. 8, pp. 1278-1286, Aug.  2017 (doi: 10.1109/TNSRE.2016.2625039).

[12] X. Ma, S. Qiu, W. Wei, S. Wang and H. He, "Deep Channel-Correlation Network for Motor Imagery Decoding from the Same Limb", IEEE Trans. Neural Syst Rehabil Eng, vol. 28, no. 1, pp. 297-306, Jan.    2020 (doi: 10.1109/TNSRE.2019.2953121).

[13] B. Blankertz, K.R. Müller, D.J.  Krusienski, G.  Schalk, J.R.  Wolpaw, A.  Schlögl, G. Pfurtscheller, R.M.  Jdel, M.  Schröder, N.  Birbaumer, "The BCI competition III: Validating alternative approaches to actual BCI problems", IEEE Tans Neural Syst Rehabil Eng, vol. 14, no. 2, pp. 153–159, Jun. 2006 (doi: 10.1109/TNSRE.2006.875642).

[14] J.Kevric, and Subasi, "Comparison of signal decomposition methods in classification of EEG signals for motor-imagery BCI system". Biomed Signal Process Control, vol. 31, pp.398-406, Jan. 2017 (doi: 10.1016/j.bspc.2016.09.007).

[15] J.A. Wilson, G.  Schalk, L.M. Walton, J.C. Williams, "Using an EEG-Based brain-computer interface for virtual cursor movement with BCI2000", J. Vis Exp.  vol.29, Jul. 2009 (doi: 10.3791/1319).

[16] B. Hosseinifard, M.H. Moradi and R. Rostami, "Classifying depression patients and normal subjects using machine learning techniques and nonlinear features from EEG signal", Comput methods programs biomed, vol.109, no.3, pp.339-345, Mar. 2013 (doi: 10.1016/j.cmpb.2012.10.008).

[17] B.R.  Bakshi, "Multiscale PCA with application to multivariate statistical process monitoring", AlChE. Vol. 44, no.7, pp. 1596–1610, Jul. 1998 (doi: 10.1002/aic.690440712).

 [18] C. Peng, J. Hausdorff, A. Goldberger, "Fractal Mechanisms in Neural Control: Human Heartbeat and Gait Dynamics in Health and Disease", In: Walleczek J, ed. Self-Organized Biological Dynamics and Nonlinear Control. Cambridge: Cambridge University Press, 2000.

[19] R.  Esteller, G.  Vachtsevanos, J.  Echauz, B.  Litt, "A comparison of waveform fractal dimension algorithms", IEEE Trans Circuits Syst, I, Fundam Theory Appl, vol. 48, no.2, pp. 177–183, Feb. 2001 (doi: 10.1109/81.904882).

[20] C.  Go’mez, A.  Mediavilla, R.  Hornero, D.  Aba’solo, A. Ferna’ndez, "Use of the Higuchi’s fractal dimension for the analysis of MEG recordings from Alzheimer’s disease patients", Med Eng Phys,       vol. 31, no.3, pp. 306–313, Apr. 2009 (doi: 10.1016/j.medengphy.2008.06.010).

[21] M.  Akay, "Nonlinear Biomedical Signal Processing:  Dynamic Analysis and Modeling", Wiley-IEEE Press, New York, Sep. 2000.

[22] X. S. Zhang, R. J. Roy, and E. W. Jensen, "EEG complexity as a measure of depth of anesthesia for patients", IEEE Trans Biomed Eng, vol. 48, no. 12, pp. 1424–1433, Dec. 2001 (doi: 10.1109/10.966601).

[23] R. Nagarajan, "Quantifying physiological data with Lempel-Ziv complexity-certain issues", IEEE Trans Biomed Eng, vol. 49, no. 11, pp. 1371–1373, Nov. 2002 (doi: 10.1109/TBME.2002.804582).

[24] X. S. Zhang, Y. S. Zhu, N. V. Thakor, and Z. Z. Wang, "Detecting ventricular tachycardia and fibrillation by complexity measure", IEEE Trans Biomed Eng, vol. 46, no. 5, pp. 548–555, May. 1999 (doi: 10.1109/10.759055).

[25] G. Palshikar, "Simple algorithms for peak detection in time-series", In Proc. 1st Int. Conf. Advanced Data Analysis, Business Analytics and Intelligence, pp. 1-13, Jun. 2009.