Double Stage Transfer Learning for Brain–Computer Interfaces
In the application of brain-computer interfaces (BCIs), electroencephalogram (EEG) signals are difficult to collect in large quantities due to the non-stationary nature and long calibration time required. Transfer learning (TL), which transfers knowledge learned from existing subjects to new subject...
Saved in:
| 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/10034671/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850154636329091072 |
|---|---|
| author | Yunyuan Gao Mengting Li Yun Peng Feng Fang Yingchun Zhang |
| author_facet | Yunyuan Gao Mengting Li Yun Peng Feng Fang Yingchun Zhang |
| author_sort | Yunyuan Gao |
| collection | DOAJ |
| description | In the application of brain-computer interfaces (BCIs), electroencephalogram (EEG) signals are difficult to collect in large quantities due to the non-stationary nature and long calibration time required. Transfer learning (TL), which transfers knowledge learned from existing subjects to new subjects, can be applied to solve this problem. Some existing EEG-based TL algorithms cannot achieve good results because they only extract partial features. To achieve effective transfer, a double-stage transfer learning (DSTL) algorithm which applied transfer learning to both preprocessing stage and feature extraction stage of typical BCIs was proposed. First, Euclidean alignment (EA) was used to align EEG trials from different subjects. Second, aligned EEG trials in the source domain were reweighted by the distance between the covariance matrix of each trial in the source domain and the mean covariance matrix of the target domain. Lastly, after extracting spatial features with common spatial patterns (CSP), transfer component analysis (TCA) was adopted to reduce the differences between different domains further. Experiments on two public datasets in two transfer paradigms (multi-source to single-target (MTS) and single-source to single-target (STS)) verified the effectiveness of the proposed method. The proposed DSTL achieved better classification accuracy on two datasets: 84.64% and 77.16% in MTS, 73.38% and 68.58% in STS, which shows that DSTL performs better than other state-of-the-art methods. The proposed DSTL can reduce the difference between the source domain and the target domain, providing a new method for EEG data classification without training dataset. |
| format | Article |
| id | doaj-art-157572e6e7db4396a2d4d7666b3df5fd |
| institution | OA Journals |
| issn | 1534-4320 1558-0210 |
| language | English |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Transactions on Neural Systems and Rehabilitation Engineering |
| spelling | doaj-art-157572e6e7db4396a2d4d7666b3df5fd2025-08-20T02:25:16ZengIEEEIEEE Transactions on Neural Systems and Rehabilitation Engineering1534-43201558-02102023-01-01311128113610.1109/TNSRE.2023.324130110034671Double Stage Transfer Learning for Brain–Computer InterfacesYunyuan Gao0https://orcid.org/0000-0003-2128-2185Mengting Li1Yun Peng2https://orcid.org/0000-0002-6891-180XFeng Fang3Yingchun Zhang4https://orcid.org/0000-0002-1927-4103College of Automation, Hangzhou Dianzi University, Hangzhou, Zhejiang, ChinaCollege of Automation, Hangzhou Dianzi University, Hangzhou, Zhejiang, ChinaDepartment of Biomedical Engineering, University of Houston, Houston, TX, USADepartment of Biomedical Engineering, University of Houston, Houston, TX, USADepartment of Biomedical Engineering, University of Houston, Houston, TX, USAIn the application of brain-computer interfaces (BCIs), electroencephalogram (EEG) signals are difficult to collect in large quantities due to the non-stationary nature and long calibration time required. Transfer learning (TL), which transfers knowledge learned from existing subjects to new subjects, can be applied to solve this problem. Some existing EEG-based TL algorithms cannot achieve good results because they only extract partial features. To achieve effective transfer, a double-stage transfer learning (DSTL) algorithm which applied transfer learning to both preprocessing stage and feature extraction stage of typical BCIs was proposed. First, Euclidean alignment (EA) was used to align EEG trials from different subjects. Second, aligned EEG trials in the source domain were reweighted by the distance between the covariance matrix of each trial in the source domain and the mean covariance matrix of the target domain. Lastly, after extracting spatial features with common spatial patterns (CSP), transfer component analysis (TCA) was adopted to reduce the differences between different domains further. Experiments on two public datasets in two transfer paradigms (multi-source to single-target (MTS) and single-source to single-target (STS)) verified the effectiveness of the proposed method. The proposed DSTL achieved better classification accuracy on two datasets: 84.64% and 77.16% in MTS, 73.38% and 68.58% in STS, which shows that DSTL performs better than other state-of-the-art methods. The proposed DSTL can reduce the difference between the source domain and the target domain, providing a new method for EEG data classification without training dataset.https://ieeexplore.ieee.org/document/10034671/EEGbrain-computer interfacedouble stage transfer learningmultiple source domains |
| spellingShingle | Yunyuan Gao Mengting Li Yun Peng Feng Fang Yingchun Zhang Double Stage Transfer Learning for Brain–Computer Interfaces IEEE Transactions on Neural Systems and Rehabilitation Engineering EEG brain-computer interface double stage transfer learning multiple source domains |
| title | Double Stage Transfer Learning for Brain–Computer Interfaces |
| title_full | Double Stage Transfer Learning for Brain–Computer Interfaces |
| title_fullStr | Double Stage Transfer Learning for Brain–Computer Interfaces |
| title_full_unstemmed | Double Stage Transfer Learning for Brain–Computer Interfaces |
| title_short | Double Stage Transfer Learning for Brain–Computer Interfaces |
| title_sort | double stage transfer learning for brain x2013 computer interfaces |
| topic | EEG brain-computer interface double stage transfer learning multiple source domains |
| url | https://ieeexplore.ieee.org/document/10034671/ |
| work_keys_str_mv | AT yunyuangao doublestagetransferlearningforbrainx2013computerinterfaces AT mengtingli doublestagetransferlearningforbrainx2013computerinterfaces AT yunpeng doublestagetransferlearningforbrainx2013computerinterfaces AT fengfang doublestagetransferlearningforbrainx2013computerinterfaces AT yingchunzhang doublestagetransferlearningforbrainx2013computerinterfaces |