Two Class Motor Imagery Classification via Wave Atom Sub-Bants

Authors: Nebi Gedik

Abstract:

The goal of motor image brain computer interface research is to create a link between the central nervous system and a computer or device. The most important signal for brain-computer interface is the electroencephalogram. The aim of this research is to explore a set of effective features from EEG signals, separated into frequency bands, using wave atom sub-bands to discriminate right and left-hand motor imagery signals. Over the transform coefficients, feature vectors are constructed for each frequency range and each transform sub-band, and their classification performances are tested. The method is validated using EEG signals from the BCI competition III dataset IIIa and classifiers such as support vector machine and k-nearest neighbors.

Keywords: motor imagery, EEG, Wave atom transform sub-bands, SVM, k-NN

References:

[1] J. R Millan, et al. "Noninvasive brain-actuated control of a mobile robot by human EEG." IEEE Transactions on biomedical Engineering, vol. 51, no.6, pp.1026-1033, 2004.
[2] J. R. Wolpaw, et al. "Brain–computer interfaces for communication and control." Clinical neurophysiology, vol.113, no.6, pp. 767-791, 2002.
[3] A. Finke, A. Lenhardt, H. Ritter. "The MindGame: a P300-based brain–computer interface game." Neural Networks, vol.22, no.9, pp. 1329-1333, 2009.
[4] J. J. Daly, J. E. Huggins, “Brain-computer interface: current and emerging rehabilitation applications.” Arch Phys Med Rehabil, vol. 96, no. 3, pp. 1-7, 2015.
[5] M. Athif, H. Ren, “WaveCSP: a robust motor imagery classifier for consumer EEG devices.” Australas Phys Eng Sci Med., vol. 42, no. 1, pp. 159-168, 2019.
[6] M. Miao, A. Wang, F. Liu, “A spatial-frequency-temporal optimized feature sparse representationbased classification method for motor imagery EEG pattern recognition.” Med Biol Eng Comput, vol. 55, no. 9, pp. 1589-603, 2017.
[7] M. Z. Al-Faiz, A. A. Al-hamadani. “Implementation of EEG signal processing and decoding for twoclass motor imagery data.” Biomed Eng Appl Basis Commun, vol. 31, no. 4, p.1950028, 2019.
[8] J. Wang, G. Yu, L. Zhong, W. Chen, Y. Sun, “Classification of EEG signal using convolutional neural networks”, in 14th IEEE Conference on Industrial Electronics and Applications, pp. 1694-1698, 2019.
[9] M. Li, W. Zhu, H. Liu, and J. Yang, “Adaptive feature extraction of motor imagery EEG with optimal wavelet packets and SE-isomap,” Applied Sciences, vol. 7, no. 390, pp. 1-18, 2017.
[10] L. Cheng, D. Li, G. Yu, Z. Zhang, X. Li, and S. Yu, “A motor imagery EEG feature extraction method based on energy principal component analysis and deep belief networks,” IEEE Access, vol. 8, pp. 21453–21472, 2020.
[11] BCI competition III, http://www.bbci.de/competition/iii/ (last accessed 20.11.2021).
[12] BCI competition III dataset IIIa, http://www.bbci.de/competition/iii/desc_IIIa.pdf (last accessed 20.11.2021)
[13] L. Demanet, and L. Ying, “Wave atoms and sparsity of oscillatory patterns,” Applied and Computational Harmonic Analysis, vol. 23, no. 3, pp. 368-387, 2007.
[14] J. Jin, Y. Miao, I. Daly, C.D. Hu, A. Cichocki, “Correlation-based channel selection and regularized feature optimization for MI-based BCI,” Neural Networks, vol.118, pp.262-270, 2019.
[15] G. Pfurtscheller and F. L. Da Silva, "Event-related EEG/MEG synchronization and desynchronization: Basic principles", Clin. Neurophysiol., vol. 110, no. 11, pp. 1842-1857, 1999.