Accepted Articles                   Back to the articles list | Back to browse issues page

XML Print

1- Biomedical Engineering Department, Engineering Faculty, University of Isfahan, Isfahan, Iran

Introduction: Brain-Computer Interface (BCI) systems build a communication pathway between users and systems. BCI systems based on SSVEP are widely used in recent decades. Different feature extraction methods have been introduced in the literature to estimate SSVEP responses for BCI applications.
Methods: In this study, the new algorithms including CCA, LASSO, L1MCCA, MsetCCA, CFA, and MLR are compared using proper statistical methods to determine which of these algorithms have better performance when using minimum number of electrodes.
Results: It was demonstrated that MLR, MsetCCA, and CFA algorithms provided the highest performances and significantly outperformed CCA, LASSO and L1MCCA algorithms when using 8 EEG channels. However, when only one or two EEG channel were used, CFA method provided the highest f-scores. This algorithm also outperformed MLR and MsetCCA when applied on different electrode montages, and also provided the fastest computation time on the test set.
Conclusion: Although MLR method has already demonstrated to have higher performance in comparison with other frequency recognition algorithms, this study showed that in a practical SSVEP-based BCI system with one or two EEG channels and short time windows, CFA method outperforms other algorithms. Therefore, it is proposed that CFA algorithm is a promising choice for the expansion of practical SSVEP BCI systems.

Type of Study: Original | Subject: Computational Neuroscience
Received: 2017/06/18 | Accepted: 2018/06/3 | Published: 2018/06/3

Add your comments about this article : Your username or Email:

Send email to the article author

© 2019 All Rights Reserved | Basic and Clinical Neuroscience

Designed & Developed by : Yektaweb