Volume 20, Issue 3 (12-2023)
JSDP 2023, 20(3): 61-72 |
Back to browse issues page
Download citation:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
Kamandra M, Rashedi E, sanatijavan A. Channel Selection in EEG Signals Using Mutual Information for Motor Imagery Classification. JSDP 2023; 20 (3) : 5
URL: http://jsdp.rcisp.ac.ir/article-1-1282-en.html
URL: http://jsdp.rcisp.ac.ir/article-1-1282-en.html
Graduate University of Advanced Technology
Abstract: (739 Views)
Brain-computer interface systems based on classification of the motor imageries (MI) using multi-channel EEG signal play a major role in the control of artificial limbs and machines by people with disabilities. One of the main problems in classifying these signals to recognize different MI tasks is the large number of channels. The large number of channels causes a lot of cost and hassle during the measurement process, increasing computational load of the preprocessing, feature extraction, and classification, difficulty of interpretation of results, and over-fitting of the classifier due to the limited number and noisy training samples. Since not all measured channels for classifying a particular MI task have useful information, it would be beneficial to select the optimal channels for classifying desired MI tasks. Channel selection methods are categorized into wrapper, filtered, hybrid, and embedded categories. In this paper, a filtering method is used due to less computational cost and the independence of the classifier. The used criterion is very important in filtering methods. Criteria based on first- and second-order data moments are less efficient for non-Gaussian classes. The proposed method uses mutual information between candidate channels and class label as a comprehensive criterion and sequential forward selection search strategy. One of the problems in using this criterion is the accurate estimation of mutual information in the high dimensional spaces. The kpn entropy estimator is used to accurately estimate the mutual information in high dimensional space with limited number of training samples. The power of 2 Hz non overlapping sub-bands in the 8-30 Hz band and in 250 milliseconds non overlapping intervals in half to two and a half seconds after the onset of MI are extracted as features for each channel. The extracted features are reduced to 10 for each channel by combining the unsupervised L1-PCA and supervised NWFE dimensionality reduction methods. The reported results show the ability of the proposed method to select effective channels for classifying left and right hand and feet MI tasks. The overall accuracy of the SVM classifier on test samples for two subjects labeled aa and al from the BCI III competition dataset is 94.87% and 96.51%, respectively, while the number of channels is reduced from 118 to 7 channels.
Article number: 5
Keywords: Brain Computer Interface, EEG Signals, Motor Imagery Classification, Channel Selection, Mutual Information, kpn Entropy Estimation.
Type of Study: Research |
Subject:
Paper
Received: 2021/11/1 | Accepted: 2023/07/8 | Published: 2024/01/14 | ePublished: 2024/01/14
Received: 2021/11/1 | Accepted: 2023/07/8 | Published: 2024/01/14 | ePublished: 2024/01/14
References
1. [1] Ortiz-Rosario A, Adeli H, Brain-computer interface technologies: from signal to action. Rev Neurosci, vol. 24, no. 5, pp. 537-552, 2013.
2. [2] A. Bashashati, M. Fatourechi, R. K. Ward, and G. E. Birch, A survey of signal processing algorithms in brain-computer interfaces based on electrical brain signals, J. Neural Eng., vol. 4, no. 2, pp. R32-R57, Jun.2007.
3. [3] Hudspeth, A.J., Jessell, T.M., Kandel, E.R., Schwartz, J.H. and Siegelbaum, S.A. eds., 2013. Principles of neural science, McGraw-Hill, Health Professions Division.
4. [4] Wolpaw JR, Birbaumer N, Heetderks WJ, McFarland DJ, Peckham PH, Schalk G, Donchin E, Quatrano LA, Robinson CJ,VaughanTM, Brain-computer interface technology: a review of the first international meeting, IEEE Trans Rehabilit Eng, vol. 8, no. 2, pp. 164-173, 2000.
5. [5] Alotaiby, T., El-Samie, F.E.A., Alshebeili, S.A. et al. A review of channel selection algorithms for EEG signal processing, EURASIP J. Adv. Signal Process. 2015.
6. [6] Yang, Yuan, Olexiy Kyrgyzov, Joe Wiart, and Isabelle Bloch. Subject-specific channel selection for classification of motor imagery electroencephalographic data, In 2013 IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 1277-1280. IEEE, 2013.
7. [7] Wei Qingguo, and Yanmei Wang. Binary multi-objective particle swarm optimization for channel selection in motor imagery based brain-computer interfaces, In 2011 4th International conference on biomedical engineering and informatics (BMEI), vol. 2, pp. 667-670. IEEE, 2011.
8. [8] A. Ghaemi, E. Rashedi, A. M. Pourrahimi, M. Kamandar, and F. Rahdari. Automatic channel selection in EEG signals for classification of left or right hand movement in Brain Computer Interfaces using improved binary gravitation search algorithm, Biomedical Signal Processing and Control 33, pp. 109-118, 2017.
9. [9] Shan, Haijun, Han Yuan, Shanan Zhu, and Bin He. EEG-based motor imagery classification accuracy improves with gradually increased channel number, In 2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, pp. 1695-1698. IEEE, 2012.
10. [10] He, Lin, Youpan Hu, Yuanqing Li, and Daoli Li. Channel selection by Rayleigh coefficient maximization based genetic algorithm for classifying single-trial motor imagery EEG, Neurocomputing, pp. 423-433,2013
11. [11] Muhammad Zeeshan Baig, Nauman Aslam, Hubert P. H. Shum. Filtering techniques for channel selection in motor imagery EEG applications: a survey, Arti Intel Rev, vol. 53, pp.1207-1232, 2020.
12. [12] LemmS, BlankertzB, CurioG, MullerK-R. Spatio-spectral filters for improving the classification of single trial EEG, IEEE Trans Biomed Eng, vol. 52, pp. 1541-1548, 2005.
13. [13] AngKK, ChinZY, ZhangH, GuanC. Filter bank common spatial pattern (FBCSP) in brain-computer interface, In: IEEE world congress on computational intel-ligence. IEEE international joint conference on neural networks. IEEE, pp. 2390-7, 2008.
14. [14] ZhangY, ZhouG, JinJ, WangX, CichockiA. Optimizing spatial patterns with sparse filter bands for motor-imagery based brain-computer interface, J Neu-rosci Methods, pp. 85-91, 2015.
15. [15] ZhangY, NamCS, ZhouG, JinJ, WangX, CichockiA. Temporally constrained sparse group spatial patterns for motor imagery BCI, IEEE Trans Cybern, 48, pp. 3322-32, 2018.
16. [16] FarquharJ, HillJ, LalTN, SchölkopfB. Regularised CSP for sensor selection in BCI, In: Proceedings of the 3rd international brain-computer interface work-shop and training course; 2006.
17. [17] WuW, ChenZ, GaoX, LiY, BrownEN, GaoS. Probabilistic common spatial patterns for multichannel EEG analysis, IEEE Trans Pattern Anal Mach Intell, 37, pp. 639-53, 2015.
18. [18] Gómez-Herrero G. Automatic artifact removal (AAR) toolbox v1. 3 (Release 09.12. 2007) for MATLAB, Tampere University of Technology, 2007. [cited 2017 Aug 1]. Available from: http://germangh.github.io/ pubs/aardoc07.pdf.
19. [19] Bor-Chen Kuo and D. A. Landgrebe, Nonparametric weighted feature extraction for classification, in IEEE Transactions on Geoscience and Remote Sensing, vol. 42, no. 5, pp. 1096-1105, May 2004, doi: 10.1109/TGRS.2004.825578. [DOI:10.1109/TGRS.2004.825578]
20. [20] Li, Mingai, Jianyong Ma, and Songmin Jia. Optimal combination of channels selection based on common spatial pattern algorithm, In 2011 IEEE International Conference on Mechatronics and Automation, pp. 295-300. IEEE, 2011.
21. [21] J. Meng, G. Liu, G. Huang and X. Zhu, Automated selecting subset of channels based on CSP in motor imagery brain-computer interface system, 2009 IEEE International Conference on Robotics and Biomimetics (ROBIO), Guilin, 2009, pp. 2290-2294, doi: 10.1109/ROBIO.2009.5420462. [DOI:10.1109/ROBIO.2009.5420462]
Send email to the article author
| Rights and permissions | |
 |
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. |
