Show simple item record

AuthorLi, Ruilin
AuthorGao, Ruobin
AuthorYuan, Liqiang
AuthorSuganthan, P.N.
AuthorWang, Lipo
AuthorSourina, Olga
Available date2023-05-16T09:07:33Z
Publication Date2023
Publication NameEngineering Applications of Artificial Intelligence
ResourceScopus
ISSN9521976
URIhttp://dx.doi.org/10.1016/j.engappai.2023.106237
URIhttp://hdl.handle.net/10576/42794
AbstractThis work investigated the use of an ensemble deep random vector functional link (edRVFL) network for electroencephalogram (EEG)-based driver fatigue recognition. Against the low feature learning capability of the edRVFL network from raw EEG signals, two strategies were exploited in this work. Specifically, the first one was to exploit the advantages of the feature extractor module in CNNs, i.e., use CNN features as the input of the edRVFL network. The second one was to improve the feature learning capability of the edRVFL network. An enhanced edRFVL network named FGloWD-edRVFL was proposed, in which four enhancements were implemented, including random forest-based Feature selection, Global output layer, Weighting and entropy-based Dynamic ensemble. The proposed FGloWD-edRVFL network was evaluated on the challenging cross-subject driver fatigue recognition tasks. The results indicated that the proposed model could boost the recognition performance, significantly outperforming all strong baselines. The step-wise analysis further demonstrated the effectiveness of the proposed enhancements in the edRVFL network. 2023 The Author(s)
SponsorOpen Access funding provided by the Qatar National Library.
Languageen
PublisherElsevier
SubjectCross-subject driver fatigue recognition
Dynamic ensemble
Electroencephalogram (EEG)
Ensemble deep random vector functional link (edRVFL)
Feature selection
TitleAn enhanced ensemble deep random vector functional link network for driver fatigue recognition
TypeArticle
Volume Number123
dc.accessType Open Access


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record