Full metadata record

DC Field Value Language
dc.contributor.authorSung, Dong-Jin-
dc.contributor.authorKim, Keun-Tae-
dc.contributor.authorJeong, Ji Hyeok-
dc.contributor.authorKim, Lae hyun-
dc.contributor.authorLee, Song Joo-
dc.contributor.authorKim, Hyungmin-
dc.contributor.authorKim, Seung-Jong-
dc.date.accessioned2024-09-19T00:00:22Z-
dc.date.available2024-09-19T00:00:22Z-
dc.date.created2024-09-14-
dc.date.issued2024-09-
dc.identifier.urihttps://pubs.kist.re.kr/handle/201004/150605-
dc.description.abstractMotor imagery (MI)-based brain-computer interfaces (BCIs) using electroencephalography (EEG) have found practical applications in external device control. However, the non-stationary nature of EEG signals remains to obstruct BCI performance across multiple sessions, even for the same user. In this study, we aim to address the impact of non-stationarity, also known as inter-session variability, on multi-session MI classification performance by introducing a novel approach, the relevant session-transfer (RST) method. Leveraging the cosine similarity as a benchmark, the RST method transfers relevant EEG data from the previous session to the current one. The effectiveness of the proposed RST method was investigated through performance comparisons with the self-calibrating method, which uses only the data from the current session, and the whole-session transfer method, which utilizes data from all prior sessions. We validated the effectiveness of these methods using two datasets: a large MI public dataset (Shu Dataset) and our own dataset of gait-related MI, which includes both healthy participants and individuals with spinal cord injuries. Our experimental results revealed that the proposed RST method leads to a 2.29 % improvement (p < 0.001) in the Shu Dataset and up to a 6.37 % improvement in our dataset when compared to the self-calibrating method. Moreover, our method surpassed the performance of the recent highest-performing method that utilized the Shu Dataset, providing further support for the efficacy of the RST method in improving multi-session MI classification performance. Consequently, our findings confirm that the proposed RST method can improve classification performance across multiple sessions in practical MI-BCIs.-
dc.languageEnglish-
dc.publisherCell Press-
dc.titleImproving inter-session performance via relevant session-transfer for multi-session motor imagery classification-
dc.typeArticle-
dc.identifier.doi10.1016/j.heliyon.2024.e37343-
dc.description.journalClass1-
dc.identifier.bibliographicCitationHeliyon, v.10, no.17-
dc.citation.titleHeliyon-
dc.citation.volume10-
dc.citation.number17-
dc.description.isOpenAccessY-
dc.description.journalRegisteredClassscie-
dc.description.journalRegisteredClassscopus-
dc.identifier.wosid001310473800001-
dc.relation.journalWebOfScienceCategoryMultidisciplinary Sciences-
dc.relation.journalResearchAreaScience & Technology - Other Topics-
dc.type.docTypeArticle-
dc.subject.keywordPlusEEG-
dc.subject.keywordPlusBCI-
dc.subject.keywordPlusDOMAIN ADAPTATION NETWORK-
dc.subject.keywordAuthorSession-transfer approach-
dc.subject.keywordAuthorCosine similarity-
dc.subject.keywordAuthorConvolutional neural network-
dc.subject.keywordAuthorBrain-computer interface-
dc.subject.keywordAuthorGait-related motor imagery-
Appears in Collections:
KIST Article > 2024
Files in This Item:
There are no files associated with this item.
Export
RIS (EndNote)
XLS (Excel)
XML

qrcode

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

BROWSE