Maximum Signal Fraction Analysis for Enhancing Signal-to-Noise Ratio of EEG Signals in SSVEP-Based BCIs
Various improved canonical correlation analysis (CCA) methods were developed for enhancing the performance of steady-state visual evoked potential (SSVEP)-based brain-computer interfaces (BCIs). Among them, the method combining CCA spatial filters from sine-cosine references and individual templates...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2019-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/8746186/ |
| _version_ | 1819179428199006208 |
|---|---|
| author | Qingguo Wei Shan Zhu Yijun Wang Xiaorong Gao Hai Guo Xuan Wu |
| author_facet | Qingguo Wei Shan Zhu Yijun Wang Xiaorong Gao Hai Guo Xuan Wu |
| author_sort | Qingguo Wei |
| collection | DOAJ |
| description | Various improved canonical correlation analysis (CCA) methods were developed for enhancing the performance of steady-state visual evoked potential (SSVEP)-based brain-computer interfaces (BCIs). Among them, the method combining CCA spatial filters from sine-cosine references and individual templates yielded the highest performance. However, the CCA aims to optimize the correlation between two sets of variables rather than the signal-to-noise ratio (SNR) of the SSVEP signals, upon which the performance of an SSVEP-based BCI depends mainly. In this paper, a novel algorithm, namely, maximum signal fraction analysis (MSFA), is proposed for creating spatial filters based on individual training data. The spatial filter for a specific stimulus target is estimated by directly maximizing the averaged SNR of the observed signals across multiple trials. An individual template is calculated for each target by averaging training signals of multiple trials. Target recognition is based on template matching between filtered template signals and a single-trial testing signal. Classification performance of the MSFA-based method was evaluated on a benchmark dataset and compared with that of the CCA-based methods. The results suggest that the proposed MSFA method significantly outperforms the CCA-based methods in terms of classification accuracy, and thus, it has great potential to be applied in the real-life SSVEP-based BCI systems. |
| first_indexed | 2024-12-22T21:58:17Z |
| format | Article |
| id | doaj.art-02daed14ab2d4cae96ef394f22a4ea54 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-22T21:58:17Z |
| publishDate | 2019-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-02daed14ab2d4cae96ef394f22a4ea542022-12-21T18:11:12ZengIEEEIEEE Access2169-35362019-01-017854528546110.1109/ACCESS.2019.29250788746186Maximum Signal Fraction Analysis for Enhancing Signal-to-Noise Ratio of EEG Signals in SSVEP-Based BCIsQingguo Wei0https://orcid.org/0000-0002-2265-9821Shan Zhu1Yijun Wang2https://orcid.org/0000-0002-8161-2150Xiaorong Gao3Hai Guo4Xuan Wu5Department of Electronic Information Engineering, School of Information Engineering, Nanchang University, Nanchang, ChinaDepartment of Electronic Information Engineering, School of Information Engineering, Nanchang University, Nanchang, ChinaState Key Laboratory on Integrated Optoelectronics, Institute Semiconductors, Chinese Academy of Science, Beijing, ChinaDepartment of Biomedical Engineering, School of Medicine, Tsinghua University, Beijing, ChinaDepartment of Electronic Information Engineering, School of Information Engineering, Nanchang University, Nanchang, ChinaDepartment of Electronic Information Engineering, School of Information Engineering, Nanchang University, Nanchang, ChinaVarious improved canonical correlation analysis (CCA) methods were developed for enhancing the performance of steady-state visual evoked potential (SSVEP)-based brain-computer interfaces (BCIs). Among them, the method combining CCA spatial filters from sine-cosine references and individual templates yielded the highest performance. However, the CCA aims to optimize the correlation between two sets of variables rather than the signal-to-noise ratio (SNR) of the SSVEP signals, upon which the performance of an SSVEP-based BCI depends mainly. In this paper, a novel algorithm, namely, maximum signal fraction analysis (MSFA), is proposed for creating spatial filters based on individual training data. The spatial filter for a specific stimulus target is estimated by directly maximizing the averaged SNR of the observed signals across multiple trials. An individual template is calculated for each target by averaging training signals of multiple trials. Target recognition is based on template matching between filtered template signals and a single-trial testing signal. Classification performance of the MSFA-based method was evaluated on a benchmark dataset and compared with that of the CCA-based methods. The results suggest that the proposed MSFA method significantly outperforms the CCA-based methods in terms of classification accuracy, and thus, it has great potential to be applied in the real-life SSVEP-based BCI systems.https://ieeexplore.ieee.org/document/8746186/Brain-computer interfacesteady-state visual evoked potentialmaximum signal fraction analysiscanonical correlation analysissignal-to-noise ratio |
| spellingShingle | Qingguo Wei Shan Zhu Yijun Wang Xiaorong Gao Hai Guo Xuan Wu Maximum Signal Fraction Analysis for Enhancing Signal-to-Noise Ratio of EEG Signals in SSVEP-Based BCIs IEEE Access Brain-computer interface steady-state visual evoked potential maximum signal fraction analysis canonical correlation analysis signal-to-noise ratio |
| title | Maximum Signal Fraction Analysis for Enhancing Signal-to-Noise Ratio of EEG Signals in SSVEP-Based BCIs |
| title_full | Maximum Signal Fraction Analysis for Enhancing Signal-to-Noise Ratio of EEG Signals in SSVEP-Based BCIs |
| title_fullStr | Maximum Signal Fraction Analysis for Enhancing Signal-to-Noise Ratio of EEG Signals in SSVEP-Based BCIs |
| title_full_unstemmed | Maximum Signal Fraction Analysis for Enhancing Signal-to-Noise Ratio of EEG Signals in SSVEP-Based BCIs |
| title_short | Maximum Signal Fraction Analysis for Enhancing Signal-to-Noise Ratio of EEG Signals in SSVEP-Based BCIs |
| title_sort | maximum signal fraction analysis for enhancing signal to noise ratio of eeg signals in ssvep based bcis |
| topic | Brain-computer interface steady-state visual evoked potential maximum signal fraction analysis canonical correlation analysis signal-to-noise ratio |
| url | https://ieeexplore.ieee.org/document/8746186/ |
| work_keys_str_mv | AT qingguowei maximumsignalfractionanalysisforenhancingsignaltonoiseratioofeegsignalsinssvepbasedbcis AT shanzhu maximumsignalfractionanalysisforenhancingsignaltonoiseratioofeegsignalsinssvepbasedbcis AT yijunwang maximumsignalfractionanalysisforenhancingsignaltonoiseratioofeegsignalsinssvepbasedbcis AT xiaoronggao maximumsignalfractionanalysisforenhancingsignaltonoiseratioofeegsignalsinssvepbasedbcis AT haiguo maximumsignalfractionanalysisforenhancingsignaltonoiseratioofeegsignalsinssvepbasedbcis AT xuanwu maximumsignalfractionanalysisforenhancingsignaltonoiseratioofeegsignalsinssvepbasedbcis |