Multi optimized SVM classifiers for motor imagery left and right hand movement identification
- 39 Downloads
EEG signal can be a good alternative for disabled persons who cannot perform actions or perform them improperly. Brain computer interface (BCI) is an attractive technology which permits control and interaction with a computer or a machine using EEG signals. Brain task identification based on EEG signals is very difficult task and is still challenging researchers. In this paper, the motor imagery of left and right hand actions are identified using new features which are fed to a set of optimized SVM classifiers. Multi classifiers based classification showed having high faculty to improve the classification accuracy when using different kind or diversified features. Features selection was performed by genetic algorithm optimization. In single optimized SVM classifier, a mean classification accuracy of 89.8% was reached. To further improve the rate of classification, three SVMs classifiers have been suggested and optimized in order to find suitable features for each classifier. The three SVMs classifiers were optimized and achieved a performance mean of 94.11%. The achieved performance is a significant improvement comparing to the existing methods which does not exceed 81% while using the same database. Here, combining multi classifiers with selecting suitable features by optimization can be a good alternative for BCI applications.
KeywordsElectroencephalography EEG signals Motor imagery BCI (MI) Features extraction BCI system SVM classifier Optimization
The authors would like to acknowledge the Institute for Knowledge Discovery (Laboratory of Brain-Computer Interfaces), Graz University of Technology, for providing the dataset online (https://www.bbci.de/competition/iii).
Compliance with ethical standards
Conflict of interest
No conflicts of interest are declared by the authors.
This article does not contain any studies with human participants performed by any of the authors.
- 1.Teplan M (2002) Fundamental of EEG measurement. Meas Sci Rev 2(2):1Google Scholar
- 4.The Ten Twenty Electrode System: International Federation of Societies for Electroencephalography and Clinical Neurophysiology. Am J EEG Technol 1961; 1:13–19Google Scholar
- 5.Brodu N, Lotte F, Lécuyer A (2011) Comparative study of band-power extraction techniques for motor imagery classification. In: IEEE symposium on computational intelligence, cognitive algorithms, mind, and brain (CCMB), pp 1–6Google Scholar
- 9.Chaudhari R, Galiyawala HJ (2017) A review on motor imagery signal classification for BCI. Signal Process Int J (SPIJ) 11(2):16–34Google Scholar
- 11.Malouin F, Richards CL (2013) Clinical applications of motor imagery in rehabilitation Multisensory imagery. Springer, New York, pp 397–419Google Scholar
- 18.Pattnaik PK, Sarraf J (2016) Brain computer interface issues on hand movement. J King Saud Univ Comput Inform Sci 30(1):18–24Google Scholar
- 19.Coyle D, Prasad G, McGinnity TM (2005) A time-frequency approach to feature extraction for a brain-computer interface with a comparative analysis of performance measures. EURASIP J Appl Signal Process 19:3141–3151Google Scholar
- 25.Lee H, Choi S (2003) PCA+HMM+SVM for EEG pattern classification. In: Proceedings of the IEEE seventh international symposium on signal processing and its applications, pp 541–544Google Scholar
- 27.Wang Y, Jung T-P (2012) Improving brain-computer interfaces using independent component analysis. In: Allison B, Dunne S, Leeb R, Del R, Millán J, Nijholt A (eds) Towards practical brain–computer interfaces, vol 67. Springer, Berlin, p 83Google Scholar
- 30.Amarasinghe K, Sivils P, Manic M (2016) EEG feature selection for thought driven robots using evolutionary algorithms. In: 9th IEEE international conference on human system interactions (HSI), pp 355–361Google Scholar
- 33.Cai Y, Zhang L, Wenjuan J, Changsheng L (2015) A hybrid SVM/HMM classification method for motor imagery based BCI. J Comput Inform Syst 11(4):1259–1267Google Scholar
- 35.Rakotomamonjy A, Guigue V, Mallet G, Alvarado V (2005) Ensemble of svms for improving brain computer interface p300 speller performances. In: International conference on artificial neural networks, pp 45–50Google Scholar
- 40.Akay M (ed) (1997) Time frequency and wavelets in biomedical signal processing, series in biomedical engineering. IEEE Press, PiscatawayGoogle Scholar
- 45.Blankertz B, Müller KR, Curio G, Vaughan TM, Schalk G, Wolpaw JR, Schlögl A, Neuper C, Pfurtscheller G, Hinterberger T, Schröder M, Birbaumer N (2004) The BCI competition 2003: progress and perspectives in detection and discrimination of EEG single trials. IEEE Trans Biomed Eng 51(6):1044–1051CrossRefPubMedGoogle Scholar
- 49.Vapnik VN (1995) The nature of statistical learning theory. ISBN 0-387-94559-8, Springer-VerlagGoogle Scholar
- 51.Breiman L (1996) Bagging predictors. Mach Learn 24(2):123–140Google Scholar