COMPARATIVE EVALUATION OF MODERN ALGORITHMS FOR SSVEP-based BCIs
DOI:
https://doi.org/10.24867/25RB02ParoskiKeywords:
EEG signals, data processing, kNN, NN, DTAbstract
This paper provides an overview of the various algorithms applied to the recorded EEG signals of 11 subjects observed both together and individually, where the results were compared within 3 different types of filtering, feature extraction, and classification. The elliptic filter, periodogram, and k-NN algorithm proved to be the best, achieving accuracy of 58.47% and 90.4%, respectively for classifying into 5 classes.
References
[1] A. M. Norcia, L. G. Appelbaum, J. M. Ales, B. R. Cottereau, B. Rossion, “The steady-state visual evoked potential in vision research: a review”, Journal of Vision, (2015.)
[2] T. Sand, M. B. Kvaley, T. Wader, H. Hovdal, ”Evoked potential tests in clinical diagnosis”, Tidsskriftet – den Norske legeforening, (2013.)
[3] S. Tobimatsu, “Transient and steady state VEPs – reappraisal”, International Congress Series
[4] V. P. Oikonomou, G. Liaros, K. Georgiadis, E. Chatzilari, K. Adam, S. Nikopoulos, I. Kompatsiaris, “Comparative evaluation of state-of-the-art algorithms for SSVEP-based BCIs”, Technical Report, 2016.
[2] T. Sand, M. B. Kvaley, T. Wader, H. Hovdal, ”Evoked potential tests in clinical diagnosis”, Tidsskriftet – den Norske legeforening, (2013.)
[3] S. Tobimatsu, “Transient and steady state VEPs – reappraisal”, International Congress Series
[4] V. P. Oikonomou, G. Liaros, K. Georgiadis, E. Chatzilari, K. Adam, S. Nikopoulos, I. Kompatsiaris, “Comparative evaluation of state-of-the-art algorithms for SSVEP-based BCIs”, Technical Report, 2016.
Downloads
Published
2024-01-05
Issue
Section
Biomedical Engineering
