Incorporating EEG and fNIRS Patterns to Evaluate Cortical Excitability and MI-BCI Performance During Motor Training
As electroencephalography (EEG) is nonlinear and nonstationary in nature, an imperative challenge for brain-computer interfaces (BCIs) is to construct a robust classifier that can survive for a long time and monitor the brain state stably. To this end, this research aims to improve BCI performance b...
| 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/10141658/ |
| _version_ | 1827904547683565568 |
|---|---|
| author | Zhongpeng Wang Lu Yang Yijie Zhou Long Chen Bin Gu Shuang Liu Minpeng Xu Feng He Dong Ming |
| author_facet | Zhongpeng Wang Lu Yang Yijie Zhou Long Chen Bin Gu Shuang Liu Minpeng Xu Feng He Dong Ming |
| author_sort | Zhongpeng Wang |
| collection | DOAJ |
| description | As electroencephalography (EEG) is nonlinear and nonstationary in nature, an imperative challenge for brain-computer interfaces (BCIs) is to construct a robust classifier that can survive for a long time and monitor the brain state stably. To this end, this research aims to improve BCI performance by incorporation of electroencephalographic and cerebral hemodynamic patterns. A motor imagery (MI)-BCI based visual-haptic neurofeedback training (NFT) experiment was designed with sixteen participants. EEG and functional near infrared spectroscopy (fNIRS) signals were simultaneously recorded before and after this transient NFT. Cortical activation was significantly improved after repeated and continuous NFT through time-frequency and topological analysis. A classifier calibration strategy, weighted EEG-fNIRS patterns (WENP), was proposed, in which elementary classifiers were constructed by using both the EEG and fNIRS information and then integrated into a strong classifier with their independent accuracy-based weight assessment. The results revealed that the classifier constructed on integrating EEG and fNIRS patterns was significantly superior to that only with independent information (<inline-formula> <tex-math notation="LaTeX">$\sim $ </tex-math></inline-formula>10% and <inline-formula> <tex-math notation="LaTeX">$\sim $ </tex-math></inline-formula>18% improvement respectively), reaching <inline-formula> <tex-math notation="LaTeX">$\sim $ </tex-math></inline-formula>89% in mean classification accuracy. The WENP is a classifier calibration strategy that can effectively improve the performance of the MI-BCI and could also be used to other BCI paradigms. These findings validate that our proposed methods are feasible and promising for optimizing conventional motor training methods and clinical rehabilitation. |
| first_indexed | 2024-03-13T00:28:55Z |
| format | Article |
| id | doaj.art-41554cd6780241c79bea14720e510d8b |
| institution | Directory Open Access Journal |
| issn | 1558-0210 |
| language | English |
| last_indexed | 2024-03-13T00:28:55Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Transactions on Neural Systems and Rehabilitation Engineering |
| spelling | doaj.art-41554cd6780241c79bea14720e510d8b2023-07-10T23:00:06ZengIEEEIEEE Transactions on Neural Systems and Rehabilitation Engineering1558-02102023-01-01312872288210.1109/TNSRE.2023.328185510141658Incorporating EEG and fNIRS Patterns to Evaluate Cortical Excitability and MI-BCI Performance During Motor TrainingZhongpeng Wang0Lu Yang1https://orcid.org/0000-0001-6459-976XYijie Zhou2https://orcid.org/0000-0003-1413-8425Long Chen3https://orcid.org/0000-0002-9091-8020Bin Gu4Shuang Liu5Minpeng Xu6https://orcid.org/0000-0001-6746-4828Feng He7https://orcid.org/0000-0001-8359-2635Dong Ming8https://orcid.org/0000-0002-8192-2538Academy of Medical Engineering and Translational Medicine, the College of Precision Instruments and Optoelectronics Engineering, the Tianjin Center for Brain Science, and the Tianjin International Joint Research Center for Neural Engineering, Tianjin University, Tianjin, ChinaAcademy of Medical Engineering and Translational Medicine, Tianjin University, Tianjin, ChinaAcademy of Medical Engineering and Translational Medicine, Tianjin University, Tianjin, ChinaAcademy of Medical Engineering and Translational Medicine, Tianjin University, Tianjin, ChinaAcademy of Medical Engineering and Translational Medicine, the College of Precision Instruments and Optoelectronics Engineering, the Tianjin Center for Brain Science, and the Tianjin International Joint Research Center for Neural Engineering, Tianjin University, Tianjin, ChinaAcademy of Medical Engineering and Translational Medicine, Tianjin University, Tianjin, ChinaAcademy of Medical Engineering and Translational Medicine, the College of Precision Instruments and Optoelectronics Engineering, the Tianjin Center for Brain Science, and the Tianjin International Joint Research Center for Neural Engineering, Tianjin University, Tianjin, ChinaAcademy of Medical Engineering and Translational Medicine, the College of Precision Instruments and Optoelectronics Engineering, the Tianjin Center for Brain Science, and the Tianjin International Joint Research Center for Neural Engineering, Tianjin University, Tianjin, ChinaAcademy of Medical Engineering and Translational Medicine, the College of Precision Instruments and Optoelectronics Engineering, the Tianjin Center for Brain Science, and the Tianjin International Joint Research Center for Neural Engineering, Tianjin University, Tianjin, ChinaAs electroencephalography (EEG) is nonlinear and nonstationary in nature, an imperative challenge for brain-computer interfaces (BCIs) is to construct a robust classifier that can survive for a long time and monitor the brain state stably. To this end, this research aims to improve BCI performance by incorporation of electroencephalographic and cerebral hemodynamic patterns. A motor imagery (MI)-BCI based visual-haptic neurofeedback training (NFT) experiment was designed with sixteen participants. EEG and functional near infrared spectroscopy (fNIRS) signals were simultaneously recorded before and after this transient NFT. Cortical activation was significantly improved after repeated and continuous NFT through time-frequency and topological analysis. A classifier calibration strategy, weighted EEG-fNIRS patterns (WENP), was proposed, in which elementary classifiers were constructed by using both the EEG and fNIRS information and then integrated into a strong classifier with their independent accuracy-based weight assessment. The results revealed that the classifier constructed on integrating EEG and fNIRS patterns was significantly superior to that only with independent information (<inline-formula> <tex-math notation="LaTeX">$\sim $ </tex-math></inline-formula>10% and <inline-formula> <tex-math notation="LaTeX">$\sim $ </tex-math></inline-formula>18% improvement respectively), reaching <inline-formula> <tex-math notation="LaTeX">$\sim $ </tex-math></inline-formula>89% in mean classification accuracy. The WENP is a classifier calibration strategy that can effectively improve the performance of the MI-BCI and could also be used to other BCI paradigms. These findings validate that our proposed methods are feasible and promising for optimizing conventional motor training methods and clinical rehabilitation.https://ieeexplore.ieee.org/document/10141658/Brain--computer interfaceneurofeedback traininghybrid brain signalweighted EEG-fNIRS patternsmotor imagery |
| spellingShingle | Zhongpeng Wang Lu Yang Yijie Zhou Long Chen Bin Gu Shuang Liu Minpeng Xu Feng He Dong Ming Incorporating EEG and fNIRS Patterns to Evaluate Cortical Excitability and MI-BCI Performance During Motor Training IEEE Transactions on Neural Systems and Rehabilitation Engineering Brain--computer interface neurofeedback training hybrid brain signal weighted EEG-fNIRS patterns motor imagery |
| title | Incorporating EEG and fNIRS Patterns to Evaluate Cortical Excitability and MI-BCI Performance During Motor Training |
| title_full | Incorporating EEG and fNIRS Patterns to Evaluate Cortical Excitability and MI-BCI Performance During Motor Training |
| title_fullStr | Incorporating EEG and fNIRS Patterns to Evaluate Cortical Excitability and MI-BCI Performance During Motor Training |
| title_full_unstemmed | Incorporating EEG and fNIRS Patterns to Evaluate Cortical Excitability and MI-BCI Performance During Motor Training |
| title_short | Incorporating EEG and fNIRS Patterns to Evaluate Cortical Excitability and MI-BCI Performance During Motor Training |
| title_sort | incorporating eeg and fnirs patterns to evaluate cortical excitability and mi bci performance during motor training |
| topic | Brain--computer interface neurofeedback training hybrid brain signal weighted EEG-fNIRS patterns motor imagery |
| url | https://ieeexplore.ieee.org/document/10141658/ |
| work_keys_str_mv | AT zhongpengwang incorporatingeegandfnirspatternstoevaluatecorticalexcitabilityandmibciperformanceduringmotortraining AT luyang incorporatingeegandfnirspatternstoevaluatecorticalexcitabilityandmibciperformanceduringmotortraining AT yijiezhou incorporatingeegandfnirspatternstoevaluatecorticalexcitabilityandmibciperformanceduringmotortraining AT longchen incorporatingeegandfnirspatternstoevaluatecorticalexcitabilityandmibciperformanceduringmotortraining AT bingu incorporatingeegandfnirspatternstoevaluatecorticalexcitabilityandmibciperformanceduringmotortraining AT shuangliu incorporatingeegandfnirspatternstoevaluatecorticalexcitabilityandmibciperformanceduringmotortraining AT minpengxu incorporatingeegandfnirspatternstoevaluatecorticalexcitabilityandmibciperformanceduringmotortraining AT fenghe incorporatingeegandfnirspatternstoevaluatecorticalexcitabilityandmibciperformanceduringmotortraining AT dongming incorporatingeegandfnirspatternstoevaluatecorticalexcitabilityandmibciperformanceduringmotortraining |