Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/164529
Full metadata record
DC FieldValueLanguage
dc.contributor.authorJu, Ceen_US
dc.contributor.authorGuan, Cuntaien_US
dc.date.accessioned2023-01-31T02:08:09Z-
dc.date.available2023-01-31T02:08:09Z-
dc.date.issued2022-
dc.identifier.citationJu, C. & Guan, C. (2022). Tensor-CSPNet: a novel geometric deep learning framework for motor imagery classification. IEEE Transactions On Neural Networks and Learning Systems, 1-15. https://dx.doi.org/10.1109/TNNLS.2022.3172108en_US
dc.identifier.issn2162-237Xen_US
dc.identifier.urihttps://hdl.handle.net/10356/164529-
dc.description.abstractDeep learning (DL) has been widely investigated in a vast majority of applications in electroencephalography (EEG)-based brain-computer interfaces (BCIs), especially for motor imagery (MI) classification in the past five years. The mainstream DL methodology for the MI-EEG classification exploits the temporospatial patterns of EEG signals using convolutional neural networks (CNNs), which have been particularly successful in visual images. However, since the statistical characteristics of visual images depart radically from EEG signals, a natural question arises whether an alternative network architecture exists apart from CNNs. To address this question, we propose a novel geometric DL (GDL) framework called Tensor-CSPNet, which characterizes spatial covariance matrices derived from EEG signals on symmetric positive definite (SPD) manifolds and fully captures the temporospatiofrequency patterns using existing deep neural networks on SPD manifolds, integrating with experiences from many successful MI-EEG classifiers to optimize the framework. In the experiments, Tensor-CSPNet attains or slightly outperforms the current state-of-the-art performance on the cross-validation and holdout scenarios in two commonly used MI-EEG datasets. Moreover, the visualization and interpretability analyses also exhibit the validity of Tensor-CSPNet for the MI-EEG classification. To conclude, in this study, we provide a feasible answer to the question by generalizing the DL methodologies on SPD manifolds, which indicates the start of a specific GDL methodology for the MI-EEG classification.en_US
dc.language.isoenen_US
dc.relationA20G8b0102en_US
dc.relation.ispartofIEEE Transactions on Neural Networks and Learning Systemsen_US
dc.rights© 2022 The Authors. This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/.en_US
dc.subjectEngineering::Computer science and engineeringen_US
dc.titleTensor-CSPNet: a novel geometric deep learning framework for motor imagery classificationen_US
dc.typeJournal Articleen
dc.contributor.schoolSchool of Computer Science and Engineeringen_US
dc.contributor.researchS-Laben_US
dc.identifier.doi10.1109/TNNLS.2022.3172108-
dc.description.versionPublished versionen_US
dc.identifier.pmid35749326-
dc.identifier.scopus2-s2.0-85133748336-
dc.identifier.spage1en_US
dc.identifier.epage15en_US
dc.subject.keywordsGeometric Deep Learningen_US
dc.subject.keywordsMotor Imagery Classificationen_US
dc.description.acknowledgementThis work was supported in part by the RIE2020 Industry Alignment Fund–Industry Collaboration Projects (IAF-ICP) Funding Initiative and in part by the RIE2020 AME Programmatic Fund, Singapore, under Grant A20G8b0102.en_US
item.fulltextWith Fulltext-
item.grantfulltextopen-
Appears in Collections:SCSE Journal Articles

SCOPUSTM   
Citations 20

10
Updated on Jul 15, 2024

Web of ScienceTM
Citations 50

4
Updated on Oct 24, 2023

Page view(s)

168
Updated on Jul 16, 2024

Download(s) 50

174
Updated on Jul 16, 2024

Google ScholarTM

Check

Altmetric


Plumx

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.