Relation Learning Using Temporal Episodes for Motor Imagery Brain-Computer Interfaces

Basit Öğe Kaydı
dc.authoridZhou, Nan/0000-0002-0434-6231
dc.authoridChoi, Kup-Sze/0000-0003-0836-7088
dc.authoridHUANG, Xiuyu/0000-0003-1600-9109
dc.authorwosidli, jixiang/JXN-7599-2024
dc.authorwosidli, qing/JEF-9044-2023
dc.authorwosidJia, Li/JVN-3095-2024
dc.authorwosidxiao, ming/KHT-1774-2024
dc.authorwosidZhou, Hong/JKJ-1067-2023
dc.authorwosidli, jing/JEF-8436-2023
dc.authorwosidpeng, jin/JRW-4493-2023
dc.contributor.authorHuang, Xiuyu
dc.contributor.authorLiang, Shuang
dc.contributor.authorZhang, Yuanpeng
dc.contributor.authorZhou, Nan
dc.contributor.authorPedrycz, Witold
dc.contributor.authorChoi, Kup-Sze
dc.date.accessioned2024-05-19T14:45:52Z
dc.date.available2024-05-19T14:45:52Z
dc.date.issued2023
dc.departmentİstinye Üniversitesien_US
dc.description.abstractFor practical motor imagery (MI) brain-computer interface (BCI) applications, generating a reliable model for a target subject with few MI trials is important since the data collection process is labour-intensive and expensive. In this paper, we address this issue by proposing a few-shot learning method called temporal episode relation learning (TERL). TERL models MI with only limited trials from the target subject by the ability to compare MI trials through episode-based training. It can be directly applied to a new user without being re-trained, which is vital to improve user experience and realize real-world MIBCI applications. We develop a new and effective approach where, unlike the original episode learning, the temporal pattern between trials in each episode is encoded during the learning to boost the classification performance. We also perform an online evaluation simulation, in addition to the offline analysis that the previous studies only conduct, to better understand the performance of different approaches in real-world scenario. Extensive experiments are completed on four publicly available MIBCI datasets to evaluate the proposed TERL. Results show that TERL outperforms baseline and recent state-of-the-art methods, demonstrating competitive performance for subject-specific MIBCI where few trials are available from a target subject and a considerable number of trials from other source subjects.en_US
dc.description.sponsorshipNational Natural Science Foundation of China [82072019]; Natural Science Foundation of Jiangsu Province [BK20201441]; Hong Kong Research Grants Council [PolyU152006/19E]en_US
dc.description.sponsorshipThis work was supported in part by the National Natural Science Foundation of China under Grant 82072019, in part by the Natural Science Foundation of Jiangsu Province under Grant BK20201441, and in part by the Hong Kong Research Grants Council under Grant PolyU152006/19E.(Corresponding authors: Yuanpeng Zhang; Kup-Sze Choi.).en_US
dc.identifier.doi10.1109/TNSRE.2022.3228216
dc.identifier.endpage543en_US
dc.identifier.issn1534-4320
dc.identifier.issn1558-0210
dc.identifier.pmid37015468en_US
dc.identifier.startpage530en_US
dc.identifier.urihttps://doi.org10.1109/TNSRE.2022.3228216
dc.identifier.urihttps://hdl.handle.net/20.500.12713/5373
dc.identifier.volume31en_US
dc.identifier.wosWOS:000965756100001en_US
dc.identifier.wosqualityN/Aen_US
dc.indekslendigikaynakWeb of Scienceen_US
dc.language.isoenen_US
dc.publisherIeee-Inst Electrical Electronics Engineers Incen_US
dc.relation.ispartofIeee Transactions on Neural Systems and Rehabilitation Engineeringen_US
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/openAccessen_US
dc.snmz20240519_kaen_US
dc.subjectMotor Imageryen_US
dc.subjectBrain-Computer Interfaceen_US
dc.subjectTemporal Encodingen_US
dc.subjectEpisode Trainingen_US
dc.titleRelation Learning Using Temporal Episodes for Motor Imagery Brain-Computer Interfacesen_US
dc.typeArticleen_US

Dosyalar

Koleksiyon

WoS İndeksli Yayınlar Koleksiyonu
PubMed İndeksli Yayınlar Koleksiyonu