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...

Full description

Saved in:
Bibliographic Details
Main Authors: Haowei Lou, Zesheng Ye, Lina Yao, Yu Zhang
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