Abstract
Non-stationarity of electroencephalogram (EEG) signals greatly affect classifier performance in brain-computer interface (BCI). To overcome this problem we propose an adaptive classifier model known as extended multi-class pooled mean linear discriminant analysis (EMPMLDA). Here, we update the average class pair co-variance matrix along with pooled mean values. Evaluation of classifiers are done on visual evoked cortical potential data-sets. We demonstrate that EMPMLDA can significantly outperform other static classifiers such as MLDA and adaptive classifiers (MPMLDA). Furthermore an optimal update coefficient can be achieved using different datasets.
Acknowledgments
The authors are thankful to the Director of the G. H. Raisoni College of Engineering, Nagpur University for her valuable support.
Ethical Approval: The conducted research is not related to either human or animal use.
Author contributions: All the authors have accepted responsibility for the entire content of this submitted manuscript and approved submission.
Research funding: None declared.
Employment or leadership: None declared.
Honorarium: None declared.
Competing interests: The funding organization(s) played no role in the study design; in the collection, analysis, and interpretation of data; in the writing of the report; or in the decision to submit the report for publication.
Conflict of interest: The authors declare that they have no conflict of interest.
Funding: The authors did not receive any funding to carry out this research work.
References
[1] Nicolas-Alonso LF, Gomez-Gil J. Brain computer interface. a review. Sensors 2012;12:1211–79.10.3390/s120201211Search in Google Scholar PubMed PubMed Central
[2] Lotte F, Lecuyer A, Arnaldi B. FuRIA: an inverse solution based feature extraction algorithm using fuzzy set theory for brain-computer interfaces. IEEE Trans Signal Proc 2009;57:3253–63.10.1109/TSP.2009.2020752Search in Google Scholar
[3] Clerc M, Bougrain L, Lotte F. Brain-computer interfaces 1: foundations and methods. USA: ISTE-Wiley, 2016.10.1002/9781119144977Search in Google Scholar
[4] Lotte F, Congedo M. EEG feature extraction. Wiley Online Library. 2016;127–43.10.1002/9781119144977.ch7Search in Google Scholar
[5] Lotte F, Bougrain L, Cichocki A, Clerc M, Congedo M, Rakotomamonjy A. A review of classification algorithms for EEG-based brain-computer interfaces: a 10-year update. J Neural Eng. 2018;55(1741-2552/18/031005):1–29.10.1088/1741-2552/aab2f2Search in Google Scholar PubMed
[6] Lotte F. Towards usable electroencephalography-based brain-computer interfaces. Habilitation thesis habilitation la diriger des recherches (HDR). University of Bordeaux, 2016.Search in Google Scholar
[7] Lotte F. A tutorial on EEG signal processing techniques for mental state recognition in brain-computer interfaces. In: Miranda ER, Castet J, editors. Guide to brain-computer music interfacing. London: Springer, 2014.Search in Google Scholar
[8] Luis F, Corralejo R, Gomez-Pilar J, Álvarez D, Hornero R. Adaptive semi-supervised classification to reduce intersession non-stationarity in multi class motor imagery-based brain computer interfaces. Neurocomputing 2015;159:186–96.10.1016/j.neucom.2015.02.005Search in Google Scholar
[9] Llera A, Gómez V, Kappen HJ. Adaptive classification on brain-computer interfaces using reinforcement signals. J Neural Comput Archive 2012;24:2900–23.10.1162/NECO_a_00348Search in Google Scholar PubMed
[10] Vidaurre C, Kawanabe M, Von Bunau P, Blankertz B, Muller K. Toward unsupervised adaptation of LDA for brain computer interfaces. IEEE Trans Biomed Eng 2011;58:587–97.10.1109/TBME.2010.2093133Search in Google Scholar PubMed
[11] Xu P, Yang P, Lei X, Yao D. An enhanced probabilistic LDA for multi-class brain computer interface. PLoS One. 2012;1–11.10.1371/journal.pone.0014634Search in Google Scholar PubMed PubMed Central
[12] Faller J, Scherer R, Costa U, Opisso E, Medina J, Muller-Putz GR. A co-adaptive brain-computer interface for end users with severe motor impairment. PLoS One 2014;9:e101168.10.1371/journal.pone.0101168Search in Google Scholar PubMed PubMed Central
[13] Llera A, Gomez V, Kappen HJ. Adaptive multi-class classification for brain computer interfaces. Neural Comput 2014;26:1108–27.10.1162/NECO_a_00592Search in Google Scholar PubMed
[14] Hitziger S, Clerc M, Saillet S, Benar C, Papadopoulo T. Adaptive waveform learning: a framework for modeling variability in neurophysiological signals. IEEE Trans Signal Proc 2017;65:4324–38.10.1109/TSP.2017.2698415Search in Google Scholar
[15] Bishop C. Pattern recognition and machine learning. New York: Springer-Verlag, 2007, 978-0-387-31073-2.Search in Google Scholar
[16] Haykin S. Adaptive filter theory. Englewood Cliffs, NJ: Prentice-Hall, 1996.Search in Google Scholar
[17] Andreev A, Barachant A, Lotte F, Congedo M. Recreational applications in OpenViBE: brain invaders and use-the-force. In: Clerc M, Bougrain L, Lotte F, editors. Brain-computer interfaces 2: technology and application. France: Wiley-iSTE, 2016:241–58.10.1002/9781119332428.ch14Search in Google Scholar
[18] Kotz S, Read C, Balakrishnan N, Vidakovic B, Johnson NL. Encyclopedia of statistical sciences. New York: Wiley, 2004, 9780471150442.10.1002/0471667196Search in Google Scholar
© 2019 Walter de Gruyter GmbH, Berlin/Boston
