Comparing Steady-State Visually Evoked Potentials Frequency Estimation Methods in Brain-Computer Interface With the Minimum Number of EEG Channels
Introduction: Brain-Computer Interface (BCI) systems provide a communication pathway between users and systems. BCI systems based on Steady-State Visually Evoked Potentials (SSVEP) are widely used in recent decades. Different feature extraction methods have been introduced in the literature to estim...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Iran University of Medical Sciences
2019-05-01
|
| Series: | Basic and Clinical Neuroscience |
| Subjects: | |
| Online Access: | http://bcn.iums.ac.ir/article-1-968-en.html |
| _version_ | 1827333399190175744 |
|---|---|
| author | Mehrnoosh Neghabi Hamid Reza Marateb Amin Mahnam |
| author_facet | Mehrnoosh Neghabi Hamid Reza Marateb Amin Mahnam |
| author_sort | Mehrnoosh Neghabi |
| collection | DOAJ |
| description | Introduction: Brain-Computer Interface (BCI) systems provide a communication pathway between users and systems. BCI systems based on Steady-State Visually Evoked Potentials (SSVEP) are widely used in recent decades. Different feature extraction methods have been introduced in the literature to estimate SSVEP responses to BCI applications.
Methods: In this study, the new algorithms, including Canonical Correlation Analysis (CCA), Least Absolute Shrinkage and Selection Operator (LASSO), L1-regularized Multi-way CCA (L1-MCCA), Multi-set CCA (MsetCCA), Common Feature Analysis (CFA), and Multiple Logistic Regression (MLR) are compared using proper statistical methods to determine which one has better performance with the least number of EEG electrodes.
Results: It was found that MLR, MsetCCA, and CFA algorithms provided the highest performances and significantly outperformed CCA, LASSO, and L1-MCCA algorithms when using 8 EEG channels. However, when using only 1 or 2 EEG channels d, CFA method provided the highest F-scores. This algorithm not only outperformed MLR and MsetCCA when applied on different electrode montages but 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 1 or 2 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-based BCI systems. |
| first_indexed | 2024-03-07T17:24:45Z |
| format | Article |
| id | doaj.art-094973eede5a4fb8b0cd90f432ea9844 |
| institution | Directory Open Access Journal |
| issn | 2008-126X 2228-7442 |
| language | English |
| last_indexed | 2024-03-07T17:24:45Z |
| publishDate | 2019-05-01 |
| publisher | Iran University of Medical Sciences |
| record_format | Article |
| series | Basic and Clinical Neuroscience |
| spelling | doaj.art-094973eede5a4fb8b0cd90f432ea98442024-03-02T19:16:39ZengIran University of Medical SciencesBasic and Clinical Neuroscience2008-126X2228-74422019-05-01103245256Comparing Steady-State Visually Evoked Potentials Frequency Estimation Methods in Brain-Computer Interface With the Minimum Number of EEG ChannelsMehrnoosh Neghabi0Hamid Reza Marateb1Amin Mahnam2 Department of Biomedical Engineering, Faculty of Engineering, University of Isfahan, Isfahan, Iran. Department of Biomedical Engineering, Faculty of Engineering, University of Isfahan, Isfahan, Iran. Department of Biomedical Engineering, Faculty of Engineering, University of Isfahan, Isfahan, Iran. Introduction: Brain-Computer Interface (BCI) systems provide a communication pathway between users and systems. BCI systems based on Steady-State Visually Evoked Potentials (SSVEP) are widely used in recent decades. Different feature extraction methods have been introduced in the literature to estimate SSVEP responses to BCI applications. Methods: In this study, the new algorithms, including Canonical Correlation Analysis (CCA), Least Absolute Shrinkage and Selection Operator (LASSO), L1-regularized Multi-way CCA (L1-MCCA), Multi-set CCA (MsetCCA), Common Feature Analysis (CFA), and Multiple Logistic Regression (MLR) are compared using proper statistical methods to determine which one has better performance with the least number of EEG electrodes. Results: It was found that MLR, MsetCCA, and CFA algorithms provided the highest performances and significantly outperformed CCA, LASSO, and L1-MCCA algorithms when using 8 EEG channels. However, when using only 1 or 2 EEG channels d, CFA method provided the highest F-scores. This algorithm not only outperformed MLR and MsetCCA when applied on different electrode montages but 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 1 or 2 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-based BCI systems.http://bcn.iums.ac.ir/article-1-968-en.htmlBrain-Computer Interface (BCI)Electroencephalogram (EEG)Feature extractionSteady-State Visually Evoked Potential (SSVEP) |
| spellingShingle | Mehrnoosh Neghabi Hamid Reza Marateb Amin Mahnam Comparing Steady-State Visually Evoked Potentials Frequency Estimation Methods in Brain-Computer Interface With the Minimum Number of EEG Channels Basic and Clinical Neuroscience Brain-Computer Interface (BCI) Electroencephalogram (EEG) Feature extraction Steady-State Visually Evoked Potential (SSVEP) |
| title | Comparing Steady-State Visually Evoked Potentials Frequency Estimation Methods in Brain-Computer Interface With the Minimum Number of EEG Channels |
| title_full | Comparing Steady-State Visually Evoked Potentials Frequency Estimation Methods in Brain-Computer Interface With the Minimum Number of EEG Channels |
| title_fullStr | Comparing Steady-State Visually Evoked Potentials Frequency Estimation Methods in Brain-Computer Interface With the Minimum Number of EEG Channels |
| title_full_unstemmed | Comparing Steady-State Visually Evoked Potentials Frequency Estimation Methods in Brain-Computer Interface With the Minimum Number of EEG Channels |
| title_short | Comparing Steady-State Visually Evoked Potentials Frequency Estimation Methods in Brain-Computer Interface With the Minimum Number of EEG Channels |
| title_sort | comparing steady state visually evoked potentials frequency estimation methods in brain computer interface with the minimum number of eeg channels |
| topic | Brain-Computer Interface (BCI) Electroencephalogram (EEG) Feature extraction Steady-State Visually Evoked Potential (SSVEP) |
| url | http://bcn.iums.ac.ir/article-1-968-en.html |
| work_keys_str_mv | AT mehrnooshneghabi comparingsteadystatevisuallyevokedpotentialsfrequencyestimationmethodsinbraincomputerinterfacewiththeminimumnumberofeegchannels AT hamidrezamarateb comparingsteadystatevisuallyevokedpotentialsfrequencyestimationmethodsinbraincomputerinterfacewiththeminimumnumberofeegchannels AT aminmahnam comparingsteadystatevisuallyevokedpotentialsfrequencyestimationmethodsinbraincomputerinterfacewiththeminimumnumberofeegchannels |