Cross-Subject Transfer Learning for Boosting Recognition Performance in SSVEP-Based BCIs
Steady-state visual evoked potential (SSVEP)-based brain-computer interfaces (BCIs) have been substantially studied in recent years due to their fast communication rate and high signal-to-noise ratio. The transfer learning is typically utilized to improve the performance of SSVEP-based BCIs with aux...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2023-01-01
|
Series: | IEEE Transactions on Neural Systems and Rehabilitation Engineering |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/10057002/ |
_version_ | 1797805074591776768 |
---|---|
author | Yue Zhang Sheng Quan Xie Chaoyang Shi Jun Li Zhi-Qiang Zhang |
author_facet | Yue Zhang Sheng Quan Xie Chaoyang Shi Jun Li Zhi-Qiang Zhang |
author_sort | Yue Zhang |
collection | DOAJ |
description | Steady-state visual evoked potential (SSVEP)-based brain-computer interfaces (BCIs) have been substantially studied in recent years due to their fast communication rate and high signal-to-noise ratio. The transfer learning is typically utilized to improve the performance of SSVEP-based BCIs with auxiliary data from the source domain. This study proposed an inter-subject transfer learning method for enhancing SSVEP recognition performance through transferred templates and transferred spatial filters. In our method, the spatial filter was trained via multiple covariance maximization to extract SSVEP-related information. The relationships between the training trial, the individual template, and the artificially constructed reference are involved in the training process. The spatial filters are applied to the above templates to form two new transferred templates, and the transferred spatial filters are obtained accordingly via the least-square regression. The contribution scores of different source subjects can be calculated based on the distance between the source subject and the target subject. Finally, a four-dimensional feature vector is constructed for SSVEP detection. To demonstrate the effectiveness of the proposed method, a publicly available dataset and a self-collected dataset were employed for performance evaluation. The extensive experimental results validated the feasibility of the proposed method for improving SSVEP detection. |
first_indexed | 2024-03-13T05:45:33Z |
format | Article |
id | doaj.art-30590c563eec4fc38a64b8b0e2ef0580 |
institution | Directory Open Access Journal |
issn | 1558-0210 |
language | English |
last_indexed | 2024-03-13T05:45:33Z |
publishDate | 2023-01-01 |
publisher | IEEE |
record_format | Article |
series | IEEE Transactions on Neural Systems and Rehabilitation Engineering |
spelling | doaj.art-30590c563eec4fc38a64b8b0e2ef05802023-06-13T20:09:55ZengIEEEIEEE Transactions on Neural Systems and Rehabilitation Engineering1558-02102023-01-01311574158310.1109/TNSRE.2023.325095310057002Cross-Subject Transfer Learning for Boosting Recognition Performance in SSVEP-Based BCIsYue Zhang0https://orcid.org/0000-0002-4988-0219Sheng Quan Xie1https://orcid.org/0000-0003-2641-2620Chaoyang Shi2https://orcid.org/0000-0002-9065-9057Jun Li3Zhi-Qiang Zhang4https://orcid.org/0000-0003-0204-3867School of Electrical and Electronic Engineering, Institute of Robotics, Autonomous System and Sensing, University of Leeds, Leeds, U.KSchool of Electrical and Electronic Engineering, Institute of Robotics, Autonomous System and Sensing, University of Leeds, Leeds, U.KSchool of Mechanical Engineering, Tianjin University, Tianjin, ChinaCollege of Intelligent Systems Science and Engineering, Hubei Minzu University, Enshi, Hubei, ChinaSchool of Electrical and Electronic Engineering, Institute of Robotics, Autonomous System and Sensing, University of Leeds, Leeds, U.KSteady-state visual evoked potential (SSVEP)-based brain-computer interfaces (BCIs) have been substantially studied in recent years due to their fast communication rate and high signal-to-noise ratio. The transfer learning is typically utilized to improve the performance of SSVEP-based BCIs with auxiliary data from the source domain. This study proposed an inter-subject transfer learning method for enhancing SSVEP recognition performance through transferred templates and transferred spatial filters. In our method, the spatial filter was trained via multiple covariance maximization to extract SSVEP-related information. The relationships between the training trial, the individual template, and the artificially constructed reference are involved in the training process. The spatial filters are applied to the above templates to form two new transferred templates, and the transferred spatial filters are obtained accordingly via the least-square regression. The contribution scores of different source subjects can be calculated based on the distance between the source subject and the target subject. Finally, a four-dimensional feature vector is constructed for SSVEP detection. To demonstrate the effectiveness of the proposed method, a publicly available dataset and a self-collected dataset were employed for performance evaluation. The extensive experimental results validated the feasibility of the proposed method for improving SSVEP detection.https://ieeexplore.ieee.org/document/10057002/Brain–computer interface (BCI)electroencephalography (EEG)steady-state visual evoked potential (SSVEP)transfer learningcross-subject |
spellingShingle | Yue Zhang Sheng Quan Xie Chaoyang Shi Jun Li Zhi-Qiang Zhang Cross-Subject Transfer Learning for Boosting Recognition Performance in SSVEP-Based BCIs IEEE Transactions on Neural Systems and Rehabilitation Engineering Brain–computer interface (BCI) electroencephalography (EEG) steady-state visual evoked potential (SSVEP) transfer learning cross-subject |
title | Cross-Subject Transfer Learning for Boosting Recognition Performance in SSVEP-Based BCIs |
title_full | Cross-Subject Transfer Learning for Boosting Recognition Performance in SSVEP-Based BCIs |
title_fullStr | Cross-Subject Transfer Learning for Boosting Recognition Performance in SSVEP-Based BCIs |
title_full_unstemmed | Cross-Subject Transfer Learning for Boosting Recognition Performance in SSVEP-Based BCIs |
title_short | Cross-Subject Transfer Learning for Boosting Recognition Performance in SSVEP-Based BCIs |
title_sort | cross subject transfer learning for boosting recognition performance in ssvep based bcis |
topic | Brain–computer interface (BCI) electroencephalography (EEG) steady-state visual evoked potential (SSVEP) transfer learning cross-subject |
url | https://ieeexplore.ieee.org/document/10057002/ |
work_keys_str_mv | AT yuezhang crosssubjecttransferlearningforboostingrecognitionperformanceinssvepbasedbcis AT shengquanxie crosssubjecttransferlearningforboostingrecognitionperformanceinssvepbasedbcis AT chaoyangshi crosssubjecttransferlearningforboostingrecognitionperformanceinssvepbasedbcis AT junli crosssubjecttransferlearningforboostingrecognitionperformanceinssvepbasedbcis AT zhiqiangzhang crosssubjecttransferlearningforboostingrecognitionperformanceinssvepbasedbcis |