A new framework for automatic detection of motor and mental imagery EEG signals for robust BCI systems
Nonstationary signal decomposition (SD) is a primary procedure to extract monotonic components or modes from electroencephalogram (EEG) signals for the development of robust brain-computer interface (BCI) systems. This study proposes a novel automated computerized framework for proficient identifica...
| Main Authors: | , , , , |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2022
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/159504 |
| _version_ | 1824455696122380288 |
|---|---|
| author | Yu, Xiaojun Muhammad Zulkifal Aziz Muhammad Tariq Sadiq Fan, Zeming Xiao, Gaoxi |
| author2 | School of Electrical and Electronic Engineering |
| author_facet | School of Electrical and Electronic Engineering Yu, Xiaojun Muhammad Zulkifal Aziz Muhammad Tariq Sadiq Fan, Zeming Xiao, Gaoxi |
| author_sort | Yu, Xiaojun |
| collection | NTU |
| description | Nonstationary signal decomposition (SD) is a primary procedure to extract monotonic components or modes from electroencephalogram (EEG) signals for the development of robust brain-computer interface (BCI) systems. This study proposes a novel automated computerized framework for proficient identification of motor and mental imagery (MeI) EEG tasks by employing empirical Fourier decomposition (EFD) and improved EFD (IEFD) methods. Specifically, the multiscale principal component analysis (MSPCA) is rendered to denoise EEG data first, and then, EFD is utilized to decompose nonstationary EEG into subsequent modes, while the IEFD criterion is proposed for a single conspicuous mode selection. Finally, the time-and frequency-domain features are extracted and classified with a feedforward neural network (FFNN) classifier. Extensive experiments are conducted on four multichannel motor and MeI data sets from BCI competitions II and III using a tenfold cross-validation strategy. Results compared with the other existing methods demonstrated that the highest classification accuracies of 99.82% (data set IV-A), 93.33% (data set IV-b), 91.96% (data set III), and 88.08% (data set V) in subject-specific scenarios, while 82.70% (data set IV-A) in the subject-independent framework are achieved for IEFD with FFNN classifiers collectively. The overall exploratory results authenticate that the proposed IEFD-based automated computerized framework not only outperforms the conventional SD methods but is also robust and computationally efficient for the development of subject-dependent and subject-independent BCI systems. |
| first_indexed | 2025-02-19T03:42:18Z |
| format | Journal Article |
| id | ntu-10356/159504 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2025-02-19T03:42:18Z |
| publishDate | 2022 |
| record_format | dspace |
| spelling | ntu-10356/1595042022-06-24T05:45:27Z A new framework for automatic detection of motor and mental imagery EEG signals for robust BCI systems Yu, Xiaojun Muhammad Zulkifal Aziz Muhammad Tariq Sadiq Fan, Zeming Xiao, Gaoxi School of Electrical and Electronic Engineering Engineering::Electrical and electronic engineering Biomedical Signal Processing Brain–Computer Interface Nonstationary signal decomposition (SD) is a primary procedure to extract monotonic components or modes from electroencephalogram (EEG) signals for the development of robust brain-computer interface (BCI) systems. This study proposes a novel automated computerized framework for proficient identification of motor and mental imagery (MeI) EEG tasks by employing empirical Fourier decomposition (EFD) and improved EFD (IEFD) methods. Specifically, the multiscale principal component analysis (MSPCA) is rendered to denoise EEG data first, and then, EFD is utilized to decompose nonstationary EEG into subsequent modes, while the IEFD criterion is proposed for a single conspicuous mode selection. Finally, the time-and frequency-domain features are extracted and classified with a feedforward neural network (FFNN) classifier. Extensive experiments are conducted on four multichannel motor and MeI data sets from BCI competitions II and III using a tenfold cross-validation strategy. Results compared with the other existing methods demonstrated that the highest classification accuracies of 99.82% (data set IV-A), 93.33% (data set IV-b), 91.96% (data set III), and 88.08% (data set V) in subject-specific scenarios, while 82.70% (data set IV-A) in the subject-independent framework are achieved for IEFD with FFNN classifiers collectively. The overall exploratory results authenticate that the proposed IEFD-based automated computerized framework not only outperforms the conventional SD methods but is also robust and computationally efficient for the development of subject-dependent and subject-independent BCI systems. This work was supported in part by the National Key Research and Development Program of Shaanxi (2021SF-342), Fundamental Research Funds for the Central Universities (G2018KY0308), China Postdoctoral Science Foundation under Grant (2018M641013), Postdoctoral Science Foundation of Shaanxi Province (2018BSHYDZZ05). 2022-06-24T05:45:27Z 2022-06-24T05:45:27Z 2021 Journal Article Yu, X., Muhammad Zulkifal Aziz, Muhammad Tariq Sadiq, Fan, Z. & Xiao, G. (2021). A new framework for automatic detection of motor and mental imagery EEG signals for robust BCI systems. IEEE Transactions On Instrumentation and Measurement, 70, 1006612-. https://dx.doi.org/10.1109/TIM.2021.3069026 0018-9456 https://hdl.handle.net/10356/159504 10.1109/TIM.2021.3069026 2-s2.0-85103280355 70 1006612 en IEEE Transactions on Instrumentation and Measurement © 2021 IEEE. All rights reserved. |
| spellingShingle | Engineering::Electrical and electronic engineering Biomedical Signal Processing Brain–Computer Interface Yu, Xiaojun Muhammad Zulkifal Aziz Muhammad Tariq Sadiq Fan, Zeming Xiao, Gaoxi A new framework for automatic detection of motor and mental imagery EEG signals for robust BCI systems |
| title | A new framework for automatic detection of motor and mental imagery EEG signals for robust BCI systems |
| title_full | A new framework for automatic detection of motor and mental imagery EEG signals for robust BCI systems |
| title_fullStr | A new framework for automatic detection of motor and mental imagery EEG signals for robust BCI systems |
| title_full_unstemmed | A new framework for automatic detection of motor and mental imagery EEG signals for robust BCI systems |
| title_short | A new framework for automatic detection of motor and mental imagery EEG signals for robust BCI systems |
| title_sort | new framework for automatic detection of motor and mental imagery eeg signals for robust bci systems |
| topic | Engineering::Electrical and electronic engineering Biomedical Signal Processing Brain–Computer Interface |
| url | https://hdl.handle.net/10356/159504 |
| work_keys_str_mv | AT yuxiaojun anewframeworkforautomaticdetectionofmotorandmentalimageryeegsignalsforrobustbcisystems AT muhammadzulkifalaziz anewframeworkforautomaticdetectionofmotorandmentalimageryeegsignalsforrobustbcisystems AT muhammadtariqsadiq anewframeworkforautomaticdetectionofmotorandmentalimageryeegsignalsforrobustbcisystems AT fanzeming anewframeworkforautomaticdetectionofmotorandmentalimageryeegsignalsforrobustbcisystems AT xiaogaoxi anewframeworkforautomaticdetectionofmotorandmentalimageryeegsignalsforrobustbcisystems AT yuxiaojun newframeworkforautomaticdetectionofmotorandmentalimageryeegsignalsforrobustbcisystems AT muhammadzulkifalaziz newframeworkforautomaticdetectionofmotorandmentalimageryeegsignalsforrobustbcisystems AT muhammadtariqsadiq newframeworkforautomaticdetectionofmotorandmentalimageryeegsignalsforrobustbcisystems AT fanzeming newframeworkforautomaticdetectionofmotorandmentalimageryeegsignalsforrobustbcisystems AT xiaogaoxi newframeworkforautomaticdetectionofmotorandmentalimageryeegsignalsforrobustbcisystems |