Enhancing the performance of SSVEP-based BCIs by combining task-related component analysis and deep neural network
Abstract Steady-State Visually Evoked Potential (SSVEP) signals can be decoded by either a traditional machine learning algorithm or a deep learning network. Combining the two methods is expected to enhance the performance of an SSVEP-based brain-computer interface (BCI) by exploiting their advantag...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-01-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-024-84534-6 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841559776624902144 |
|---|---|
| author | Qingguo Wei Chang Li Yijun Wang Xiaorong Gao |
| author_facet | Qingguo Wei Chang Li Yijun Wang Xiaorong Gao |
| author_sort | Qingguo Wei |
| collection | DOAJ |
| description | Abstract Steady-State Visually Evoked Potential (SSVEP) signals can be decoded by either a traditional machine learning algorithm or a deep learning network. Combining the two methods is expected to enhance the performance of an SSVEP-based brain-computer interface (BCI) by exploiting their advantages. However, an efficient strategy for integrating the two methods has not yet been established. To address this issue, we propose a classification framework named eTRCA + sbCNN that combines an ensemble task-related component analysis (eTRCA) algorithm and a sub-band convolutional neural network (sbCNN) for recognizing the frequency of SSVEP signals. The two models are first trained separately, then their classification score vectors are added together, and finally the frequency corresponding to the maximal summed score is decided as the frequency of SSVEP signals. The proposed framework can effectively exploit the complementarity between the two kinds of feature signals and significantly improve the classification performance of SSVEP-based BCIs. The performance of the proposed method is validated on two SSVEP BCI datasets and compared with that of eTRCA, sbCNN and other state-of-the-art models. Experimental results indicate that the proposed method significantly outperform the compared algorithms, and thus helps to promote the practical application of SSVEP- BCI systems. |
| format | Article |
| id | doaj-art-ec530c761bd549a091881199c2229b9f |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-ec530c761bd549a091881199c2229b9f2025-01-05T12:13:24ZengNature PortfolioScientific Reports2045-23222025-01-0115111610.1038/s41598-024-84534-6Enhancing the performance of SSVEP-based BCIs by combining task-related component analysis and deep neural networkQingguo Wei0Chang Li1Yijun Wang2Xiaorong Gao3Jiangxi Provincial Key Laboratory of Intelligent Systems and Human-Machine Interaction, Department of Electronic Engineering, School of Information Engineering, Nanchang UniversityJiangxi Provincial Key Laboratory of Intelligent Systems and Human-Machine Interaction, Department of Electronic Engineering, School of Information Engineering, Nanchang UniversityState Key Laboratory on Integrated Optoelectronics, Institute Semiconductors, Chinese Academy of ScienceDepartment of Biomedical Engineering, School of Biomedical Engineering, Tsinghua UniversityAbstract Steady-State Visually Evoked Potential (SSVEP) signals can be decoded by either a traditional machine learning algorithm or a deep learning network. Combining the two methods is expected to enhance the performance of an SSVEP-based brain-computer interface (BCI) by exploiting their advantages. However, an efficient strategy for integrating the two methods has not yet been established. To address this issue, we propose a classification framework named eTRCA + sbCNN that combines an ensemble task-related component analysis (eTRCA) algorithm and a sub-band convolutional neural network (sbCNN) for recognizing the frequency of SSVEP signals. The two models are first trained separately, then their classification score vectors are added together, and finally the frequency corresponding to the maximal summed score is decided as the frequency of SSVEP signals. The proposed framework can effectively exploit the complementarity between the two kinds of feature signals and significantly improve the classification performance of SSVEP-based BCIs. The performance of the proposed method is validated on two SSVEP BCI datasets and compared with that of eTRCA, sbCNN and other state-of-the-art models. Experimental results indicate that the proposed method significantly outperform the compared algorithms, and thus helps to promote the practical application of SSVEP- BCI systems.https://doi.org/10.1038/s41598-024-84534-6Brain-computer interfaceSteady-state visual evoked potentialEnsemble task-related component analysisSub-band convolutional neural networkModel combination |
| spellingShingle | Qingguo Wei Chang Li Yijun Wang Xiaorong Gao Enhancing the performance of SSVEP-based BCIs by combining task-related component analysis and deep neural network Scientific Reports Brain-computer interface Steady-state visual evoked potential Ensemble task-related component analysis Sub-band convolutional neural network Model combination |
| title | Enhancing the performance of SSVEP-based BCIs by combining task-related component analysis and deep neural network |
| title_full | Enhancing the performance of SSVEP-based BCIs by combining task-related component analysis and deep neural network |
| title_fullStr | Enhancing the performance of SSVEP-based BCIs by combining task-related component analysis and deep neural network |
| title_full_unstemmed | Enhancing the performance of SSVEP-based BCIs by combining task-related component analysis and deep neural network |
| title_short | Enhancing the performance of SSVEP-based BCIs by combining task-related component analysis and deep neural network |
| title_sort | enhancing the performance of ssvep based bcis by combining task related component analysis and deep neural network |
| topic | Brain-computer interface Steady-state visual evoked potential Ensemble task-related component analysis Sub-band convolutional neural network Model combination |
| url | https://doi.org/10.1038/s41598-024-84534-6 |
| work_keys_str_mv | AT qingguowei enhancingtheperformanceofssvepbasedbcisbycombiningtaskrelatedcomponentanalysisanddeepneuralnetwork AT changli enhancingtheperformanceofssvepbasedbcisbycombiningtaskrelatedcomponentanalysisanddeepneuralnetwork AT yijunwang enhancingtheperformanceofssvepbasedbcisbycombiningtaskrelatedcomponentanalysisanddeepneuralnetwork AT xiaoronggao enhancingtheperformanceofssvepbasedbcisbycombiningtaskrelatedcomponentanalysisanddeepneuralnetwork |