A Tensor-Based Frequency Features Combination Method for Brain–Computer Interfaces
With the development of the brain-computer interface (BCI) community, motor imagery-based BCI system using electroencephalogram (EEG) has attracted increasing attention because of its portability and low cost. Concerning the multi-channel EEG, the frequency component is one of the most critical feat...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | IEEE Transactions on Neural Systems and Rehabilitation Engineering |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9600883/ |
| _version_ | 1797805170032115712 |
|---|---|
| author | Yu Pei Zhiguo Luo Hongyu Zhao Dengke Xu Weiguo Li Ye Yan Huijiong Yan Liang Xie Minpeng Xu Erwei Yin |
| author_facet | Yu Pei Zhiguo Luo Hongyu Zhao Dengke Xu Weiguo Li Ye Yan Huijiong Yan Liang Xie Minpeng Xu Erwei Yin |
| author_sort | Yu Pei |
| collection | DOAJ |
| description | With the development of the brain-computer interface (BCI) community, motor imagery-based BCI system using electroencephalogram (EEG) has attracted increasing attention because of its portability and low cost. Concerning the multi-channel EEG, the frequency component is one of the most critical features. However, insufficient extraction hinders the development and application of MI-BCIs. To deeply mine the frequency information, we proposed a method called tensor-based frequency feature combination (TFFC). It combined tensor-to-vector projection (TVP), fast fourier transform (FFT), common spatial pattern (CSP) and feature fusion to construct a new feature set. With two datasets, we used different classifiers to compare TFFC with the state-of-the-art feature extraction methods. The experimental results showed that our proposed TFFC could robustly improve the classification accuracy of about 5% (<inline-formula> <tex-math notation="LaTeX">${p} < 0.01$ </tex-math></inline-formula>). Moreover, visualization analysis implied that the TFFC was a generalization of CSP and Filter Bank CSP (FBCSP). Also, a complementarity between weighted narrowband features (wNBFs) and broadband features (BBFs) was observed from the averaged fusion ratio. This article certificates the importance of frequency information in the MI-BCI system and provides a new direction for designing a feature set of MI-EEG. |
| first_indexed | 2024-03-13T05:47:05Z |
| format | Article |
| id | doaj.art-9ba4cd9b78f840d0a9bd54a2d4ef4978 |
| institution | Directory Open Access Journal |
| issn | 1558-0210 |
| language | English |
| last_indexed | 2024-03-13T05:47:05Z |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Transactions on Neural Systems and Rehabilitation Engineering |
| spelling | doaj.art-9ba4cd9b78f840d0a9bd54a2d4ef49782023-06-13T20:08:11ZengIEEEIEEE Transactions on Neural Systems and Rehabilitation Engineering1558-02102022-01-013046547510.1109/TNSRE.2021.31253869600883A Tensor-Based Frequency Features Combination Method for Brain–Computer InterfacesYu Pei0https://orcid.org/0000-0003-0185-2283Zhiguo Luo1https://orcid.org/0000-0003-4647-5629Hongyu Zhao2Dengke Xu3Weiguo Li4Ye Yan5Huijiong Yan6Liang Xie7Minpeng Xu8Erwei Yin9https://orcid.org/0000-0002-2147-9888School of Software, Beihang University, Beijing, ChinaTianjin Artificial Intelligence Innovation Center (TAIIC), Tianjin, ChinaKey Laboratory of Smart Manufacturing in Energy Chemical Process, Ministry of Education, East China University of Science and Technology, Shanghai, ChinaChina Academy of Railway Sciences, Institute of Communication Signals, Beijing, ChinaSchool of Software, Beihang University, Beijing, ChinaTianjin Artificial Intelligence Innovation Center (TAIIC), Tianjin, ChinaTianjin Artificial Intelligence Innovation Center (TAIIC), Tianjin, ChinaTianjin Artificial Intelligence Innovation Center (TAIIC), Tianjin, ChinaDepartment of Biomedical Engineering, College of Precision Instruments and Optoelectronics Engineering, Laboratory of Neural Engineering & Rehabilitation, Tianjin University, Tianjin, ChinaTianjin Artificial Intelligence Innovation Center (TAIIC), Tianjin, ChinaWith the development of the brain-computer interface (BCI) community, motor imagery-based BCI system using electroencephalogram (EEG) has attracted increasing attention because of its portability and low cost. Concerning the multi-channel EEG, the frequency component is one of the most critical features. However, insufficient extraction hinders the development and application of MI-BCIs. To deeply mine the frequency information, we proposed a method called tensor-based frequency feature combination (TFFC). It combined tensor-to-vector projection (TVP), fast fourier transform (FFT), common spatial pattern (CSP) and feature fusion to construct a new feature set. With two datasets, we used different classifiers to compare TFFC with the state-of-the-art feature extraction methods. The experimental results showed that our proposed TFFC could robustly improve the classification accuracy of about 5% (<inline-formula> <tex-math notation="LaTeX">${p} < 0.01$ </tex-math></inline-formula>). Moreover, visualization analysis implied that the TFFC was a generalization of CSP and Filter Bank CSP (FBCSP). Also, a complementarity between weighted narrowband features (wNBFs) and broadband features (BBFs) was observed from the averaged fusion ratio. This article certificates the importance of frequency information in the MI-BCI system and provides a new direction for designing a feature set of MI-EEG.https://ieeexplore.ieee.org/document/9600883/Brain–computer interfaceelectroencephalogrammotor imagerycommon spatial patterntensor-to-vector projectionfast fourier transformation |
| spellingShingle | Yu Pei Zhiguo Luo Hongyu Zhao Dengke Xu Weiguo Li Ye Yan Huijiong Yan Liang Xie Minpeng Xu Erwei Yin A Tensor-Based Frequency Features Combination Method for Brain–Computer Interfaces IEEE Transactions on Neural Systems and Rehabilitation Engineering Brain–computer interface electroencephalogram motor imagery common spatial pattern tensor-to-vector projection fast fourier transformation |
| title | A Tensor-Based Frequency Features Combination Method for Brain–Computer Interfaces |
| title_full | A Tensor-Based Frequency Features Combination Method for Brain–Computer Interfaces |
| title_fullStr | A Tensor-Based Frequency Features Combination Method for Brain–Computer Interfaces |
| title_full_unstemmed | A Tensor-Based Frequency Features Combination Method for Brain–Computer Interfaces |
| title_short | A Tensor-Based Frequency Features Combination Method for Brain–Computer Interfaces |
| title_sort | tensor based frequency features combination method for brain x2013 computer interfaces |
| topic | Brain–computer interface electroencephalogram motor imagery common spatial pattern tensor-to-vector projection fast fourier transformation |
| url | https://ieeexplore.ieee.org/document/9600883/ |
| work_keys_str_mv | AT yupei atensorbasedfrequencyfeaturescombinationmethodforbrainx2013computerinterfaces AT zhiguoluo atensorbasedfrequencyfeaturescombinationmethodforbrainx2013computerinterfaces AT hongyuzhao atensorbasedfrequencyfeaturescombinationmethodforbrainx2013computerinterfaces AT dengkexu atensorbasedfrequencyfeaturescombinationmethodforbrainx2013computerinterfaces AT weiguoli atensorbasedfrequencyfeaturescombinationmethodforbrainx2013computerinterfaces AT yeyan atensorbasedfrequencyfeaturescombinationmethodforbrainx2013computerinterfaces AT huijiongyan atensorbasedfrequencyfeaturescombinationmethodforbrainx2013computerinterfaces AT liangxie atensorbasedfrequencyfeaturescombinationmethodforbrainx2013computerinterfaces AT minpengxu atensorbasedfrequencyfeaturescombinationmethodforbrainx2013computerinterfaces AT erweiyin atensorbasedfrequencyfeaturescombinationmethodforbrainx2013computerinterfaces AT yupei tensorbasedfrequencyfeaturescombinationmethodforbrainx2013computerinterfaces AT zhiguoluo tensorbasedfrequencyfeaturescombinationmethodforbrainx2013computerinterfaces AT hongyuzhao tensorbasedfrequencyfeaturescombinationmethodforbrainx2013computerinterfaces AT dengkexu tensorbasedfrequencyfeaturescombinationmethodforbrainx2013computerinterfaces AT weiguoli tensorbasedfrequencyfeaturescombinationmethodforbrainx2013computerinterfaces AT yeyan tensorbasedfrequencyfeaturescombinationmethodforbrainx2013computerinterfaces AT huijiongyan tensorbasedfrequencyfeaturescombinationmethodforbrainx2013computerinterfaces AT liangxie tensorbasedfrequencyfeaturescombinationmethodforbrainx2013computerinterfaces AT minpengxu tensorbasedfrequencyfeaturescombinationmethodforbrainx2013computerinterfaces AT erweiyin tensorbasedfrequencyfeaturescombinationmethodforbrainx2013computerinterfaces |