System Derived Spatial-Temporal CNN for High-Density fNIRS BCI
An intuitive and generalisable approach to spatial-temporal feature extraction for high-density (HD) functional Near-Infrared Spectroscopy (fNIRS) brain-computer interface (BCI) is proposed, demonstrated here using Frequency-Domain (FD) fNIRS for motor-task classification. Enabled by the HD probe de...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Open Journal of Engineering in Medicine and Biology |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10073629/ |
| _version_ | 1797346305186463744 |
|---|---|
| author | Robin Dale Thomas D. O'sullivan Scott Howard Felipe Orihuela-Espina Hamid Dehghani |
| author_facet | Robin Dale Thomas D. O'sullivan Scott Howard Felipe Orihuela-Espina Hamid Dehghani |
| author_sort | Robin Dale |
| collection | DOAJ |
| description | An intuitive and generalisable approach to spatial-temporal feature extraction for high-density (HD) functional Near-Infrared Spectroscopy (fNIRS) brain-computer interface (BCI) is proposed, demonstrated here using Frequency-Domain (FD) fNIRS for motor-task classification. Enabled by the HD probe design, layered topographical maps of Oxy/deOxy Haemoglobin changes are used to train a 3D convolutional neural network (CNN), enabling simultaneous extraction of spatial and temporal features. The proposed spatial-temporal CNN is shown to effectively exploit the spatial relationships in HD fNIRS measurements to improve the classification of the functional haemodynamic response, achieving an average F1 score of 0.69 across seven subjects in a mixed subjects training scheme, and improving subject-independent classification as compared to a standard temporal CNN. |
| first_indexed | 2024-03-08T11:30:08Z |
| format | Article |
| id | doaj.art-7e6c3e2401b54fe7bb62579bcb590081 |
| institution | Directory Open Access Journal |
| issn | 2644-1276 |
| language | English |
| last_indexed | 2024-03-08T11:30:08Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Open Journal of Engineering in Medicine and Biology |
| spelling | doaj.art-7e6c3e2401b54fe7bb62579bcb5900812024-01-26T00:02:06ZengIEEEIEEE Open Journal of Engineering in Medicine and Biology2644-12762023-01-014859510.1109/OJEMB.2023.324849210073629System Derived Spatial-Temporal CNN for High-Density fNIRS BCIRobin Dale0https://orcid.org/0000-0001-8013-7768Thomas D. O'sullivan1https://orcid.org/0000-0001-8662-5121Scott Howard2https://orcid.org/0000-0003-3246-6799Felipe Orihuela-Espina3https://orcid.org/0000-0001-8963-7283Hamid Dehghani4https://orcid.org/0000-0003-4117-0412University of Birmingham, Birmingham, U.K.University of Notre Dame, Notre Dame, IN, USAUniversity of Notre Dame, Notre Dame, IN, USAUniversity of Birmingham, Birmingham, U.K.University of Birmingham, Birmingham, U.K.An intuitive and generalisable approach to spatial-temporal feature extraction for high-density (HD) functional Near-Infrared Spectroscopy (fNIRS) brain-computer interface (BCI) is proposed, demonstrated here using Frequency-Domain (FD) fNIRS for motor-task classification. Enabled by the HD probe design, layered topographical maps of Oxy/deOxy Haemoglobin changes are used to train a 3D convolutional neural network (CNN), enabling simultaneous extraction of spatial and temporal features. The proposed spatial-temporal CNN is shown to effectively exploit the spatial relationships in HD fNIRS measurements to improve the classification of the functional haemodynamic response, achieving an average F1 score of 0.69 across seven subjects in a mixed subjects training scheme, and improving subject-independent classification as compared to a standard temporal CNN.https://ieeexplore.ieee.org/document/10073629/fNIRSbrain-computer interfaceneural networkmachine learningCNN |
| spellingShingle | Robin Dale Thomas D. O'sullivan Scott Howard Felipe Orihuela-Espina Hamid Dehghani System Derived Spatial-Temporal CNN for High-Density fNIRS BCI IEEE Open Journal of Engineering in Medicine and Biology fNIRS brain-computer interface neural network machine learning CNN |
| title | System Derived Spatial-Temporal CNN for High-Density fNIRS BCI |
| title_full | System Derived Spatial-Temporal CNN for High-Density fNIRS BCI |
| title_fullStr | System Derived Spatial-Temporal CNN for High-Density fNIRS BCI |
| title_full_unstemmed | System Derived Spatial-Temporal CNN for High-Density fNIRS BCI |
| title_short | System Derived Spatial-Temporal CNN for High-Density fNIRS BCI |
| title_sort | system derived spatial temporal cnn for high density fnirs bci |
| topic | fNIRS brain-computer interface neural network machine learning CNN |
| url | https://ieeexplore.ieee.org/document/10073629/ |
| work_keys_str_mv | AT robindale systemderivedspatialtemporalcnnforhighdensityfnirsbci AT thomasdosullivan systemderivedspatialtemporalcnnforhighdensityfnirsbci AT scotthoward systemderivedspatialtemporalcnnforhighdensityfnirsbci AT felipeorihuelaespina systemderivedspatialtemporalcnnforhighdensityfnirsbci AT hamiddehghani systemderivedspatialtemporalcnnforhighdensityfnirsbci |