Less Is More: Brain Functional Connectivity Empowered Generalizable Intention Classification With Task-Relevant Channel Selection
Electroencephalography (EEG) signals are gaining popularity in Brain-Computer Interface (BCI)-based rehabilitation and neural engineering applications thanks to their portability and availability. Inevitably, the sensory electrodes on the entire scalp would collect signals irrelevant to the particul...
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/10059195/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849735170017460224 |
|---|---|
| author | Haowei Lou Zesheng Ye Lina Yao Yu Zhang |
| author_facet | Haowei Lou Zesheng Ye Lina Yao Yu Zhang |
| author_sort | Haowei Lou |
| collection | DOAJ |
| description | Electroencephalography (EEG) signals are gaining popularity in Brain-Computer Interface (BCI)-based rehabilitation and neural engineering applications thanks to their portability and availability. Inevitably, the sensory electrodes on the entire scalp would collect signals irrelevant to the particular BCI task, increasing the risks of overfitting in machine learning-based predictions. While this issue is being addressed by scaling up the EEG datasets and handcrafting the complex predictive models, this also leads to increased computation costs. Moreover, the model trained for one set of subjects cannot easily be adapted to other sets due to inter-subject variability, which creates even higher over-fitting risks. Meanwhile, despite previous studies using either convolutional neural networks (CNNs) or graph neural networks (GNNs) to determine spatial correlations between brain regions, they fail to capture brain functional connectivity beyond physical proximity. To this end, we propose 1) removing task-irrelevant noises instead of merely complicating models; 2) extracting subject-invariant discriminative EEG encodings, by taking functional connectivity into account. Specifically, we construct a task-adaptive graph representation of the brain network based on topological functional connectivity rather than distance-based connections. Further, non-contributory EEG channels are excluded by selecting only functional regions relevant to the corresponding intention. We empirically show that the proposed approach outperforms the state-of-the-art, with around 1% and 11% improvements over CNN-based and GNN-based models, on performing motor imagery predictions. Also, the task-adaptive channel selection demonstrates similar predictive performance with only 20% of raw EEG data, suggesting a possible shift in direction for future works other than simply scaling up the model. |
| format | Article |
| id | doaj-art-9e709beb0ef240ffa62db97b9d365b2a |
| institution | DOAJ |
| 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-9e709beb0ef240ffa62db97b9d365b2a2025-08-20T03:07:37ZengIEEEIEEE Transactions on Neural Systems and Rehabilitation Engineering1534-43201558-02102023-01-01311888189910.1109/TNSRE.2023.325261010059195Less Is More: Brain Functional Connectivity Empowered Generalizable Intention Classification With Task-Relevant Channel SelectionHaowei Lou0https://orcid.org/0009-0009-1359-872XZesheng Ye1Lina Yao2https://orcid.org/0000-0002-4149-839XYu Zhang3School of Computer Science and Engineering, University of New South Wales, Sydney, NSW, AustraliaSchool of Computer Science and Engineering, University of New South Wales, Sydney, NSW, AustraliaCSIRO’s Data61 and the School of Computer Science and Engineering, University of New South Wales, Sydney, NSW, AustraliaDepartment of Bioengineering and the Department of Electrical and Computer Engineering, Lehigh University, Bethlehem, PA, USAElectroencephalography (EEG) signals are gaining popularity in Brain-Computer Interface (BCI)-based rehabilitation and neural engineering applications thanks to their portability and availability. Inevitably, the sensory electrodes on the entire scalp would collect signals irrelevant to the particular BCI task, increasing the risks of overfitting in machine learning-based predictions. While this issue is being addressed by scaling up the EEG datasets and handcrafting the complex predictive models, this also leads to increased computation costs. Moreover, the model trained for one set of subjects cannot easily be adapted to other sets due to inter-subject variability, which creates even higher over-fitting risks. Meanwhile, despite previous studies using either convolutional neural networks (CNNs) or graph neural networks (GNNs) to determine spatial correlations between brain regions, they fail to capture brain functional connectivity beyond physical proximity. To this end, we propose 1) removing task-irrelevant noises instead of merely complicating models; 2) extracting subject-invariant discriminative EEG encodings, by taking functional connectivity into account. Specifically, we construct a task-adaptive graph representation of the brain network based on topological functional connectivity rather than distance-based connections. Further, non-contributory EEG channels are excluded by selecting only functional regions relevant to the corresponding intention. We empirically show that the proposed approach outperforms the state-of-the-art, with around 1% and 11% improvements over CNN-based and GNN-based models, on performing motor imagery predictions. Also, the task-adaptive channel selection demonstrates similar predictive performance with only 20% of raw EEG data, suggesting a possible shift in direction for future works other than simply scaling up the model.https://ieeexplore.ieee.org/document/10059195/Motor imagery recognitiongraph neural networkchannel selection |
| spellingShingle | Haowei Lou Zesheng Ye Lina Yao Yu Zhang Less Is More: Brain Functional Connectivity Empowered Generalizable Intention Classification With Task-Relevant Channel Selection IEEE Transactions on Neural Systems and Rehabilitation Engineering Motor imagery recognition graph neural network channel selection |
| title | Less Is More: Brain Functional Connectivity Empowered Generalizable Intention Classification With Task-Relevant Channel Selection |
| title_full | Less Is More: Brain Functional Connectivity Empowered Generalizable Intention Classification With Task-Relevant Channel Selection |
| title_fullStr | Less Is More: Brain Functional Connectivity Empowered Generalizable Intention Classification With Task-Relevant Channel Selection |
| title_full_unstemmed | Less Is More: Brain Functional Connectivity Empowered Generalizable Intention Classification With Task-Relevant Channel Selection |
| title_short | Less Is More: Brain Functional Connectivity Empowered Generalizable Intention Classification With Task-Relevant Channel Selection |
| title_sort | less is more brain functional connectivity empowered generalizable intention classification with task relevant channel selection |
| topic | Motor imagery recognition graph neural network channel selection |
| url | https://ieeexplore.ieee.org/document/10059195/ |
| work_keys_str_mv | AT haoweilou lessismorebrainfunctionalconnectivityempoweredgeneralizableintentionclassificationwithtaskrelevantchannelselection AT zeshengye lessismorebrainfunctionalconnectivityempoweredgeneralizableintentionclassificationwithtaskrelevantchannelselection AT linayao lessismorebrainfunctionalconnectivityempoweredgeneralizableintentionclassificationwithtaskrelevantchannelselection AT yuzhang lessismorebrainfunctionalconnectivityempoweredgeneralizableintentionclassificationwithtaskrelevantchannelselection |