Driver fatigue estimation using multimodal deep learning with eeg and eog signals

Basit Öğe Kaydı
dc.authorid0000-0003-0261-4404
dc.contributor.authorDemir, Șevval
dc.contributor.authorYapar, Rümeysa
dc.contributor.authorAldaş, Ahsen Nur
dc.contributor.authorGözüaçık, Necip
dc.date.accessioned2026-08-21T08:55:20Z
dc.date.available2026-08-21T08:55:20Z
dc.date.issued2026
dc.departmentFakülteler, Mühendislik ve Doğa Bilimleri Fakültesi, Yazılım Mühendisliği Bölümü
dc.departmentFakülteler, Mühendislik ve Doğa Bilimleri Fakültesi, Bilgisayar Mühendisliği Bölümü
dc.description.abstractDriver fatigue is a critical condition that increases accident risk by causing loss of concentration and perceptual limitations. Therefore, researchers have focused on developing systems aimed at the early detection of driver fatigue. In this study, driver fatigue detection was targeted using Differential Entropy–Linear Dynamic System (DE-LDS) based Electroencephalography (EEG) features and Electrooculography (EOG) features provided by the SEED-VIG dataset. The feature pool employed in the study was enriched through feature engineering methods such as band ratios, temporal delta components, hemispheric asymmetry, and moving standard deviation. Moreover, by eliminating the need for raw signal processing, the focus was directed toward the temporal variation patterns of meaningful features. Experimental results demonstrated that predictions based solely on EEG data remained limited, whereas the inclusion of EOG data significantly improved performance.These findings reveal that EEG and EOG signals provide complementary information in the prediction of driver fatigue. The proposed multimodal approach exhibited greater robustness against inter-subject variability compared to unimodal systems and offered a more generalizable monitoring framework.
dc.identifier.citationDemir, Ș., Yapar, R., Aldaş, A. N., & Gözüaçık, N. (2026). Driver fatigue estimation using multimodal deep learning with eeg and eog signals. 34th Signal Processing and Communications Applications Conference (SIU), IEEE. https://doi.org/10.1109/SIU71813.2026.11636868
dc.identifier.doi10.1109/SIU71813.2026.11636868
dc.identifier.issn2165-0608
dc.identifier.urihttps://doi.org/10.1109/SIU71813.2026.11636868
dc.identifier.urihttps://hdl.handle.net/20.500.13055/1586
dc.indekslendigikaynakWeb of Science
dc.institutionauthorDemir, Șevval
dc.institutionauthorYapar, Rümeysa
dc.institutionauthorAldaş, Ahsen Nur
dc.institutionauthorGözüaçık, Necip
dc.institutionauthorid0000-0003-0261-4404
dc.language.isoen
dc.publisherIEEE
dc.relation.ispartof34th Signal Processing and Communications Applications Conference (SIU)
dc.relation.publicationcategoryKonferans Öğesi - Uluslararası - Kurum Öğretim Elemanı
dc.rightsinfo:eu-repo/semantics/openAccess
dc.subjectEeg
dc.subjectEog
dc.subjectDeep Learning
dc.subjectMachine Learning
dc.subjectDriver Fatigue
dc.subjectMultimodal Prediction
dc.subjectDerin Öğrenme
dc.subjectMakine Öğrenmesi
dc.subjectSürücü Yorgunluğu
dc.subjectÇok Modlu Tahmin
dc.titleDriver fatigue estimation using multimodal deep learning with eeg and eog signals
dc.title.alternativeEEG ve EOG sinyalleriyle çok modlu derin öğrenme ile sürücü yorgunluğu tahmini
dc.typeConference Object
dspace.entity.typePublication

Dosyalar

Orijinal paket
Listeleniyor 1 - 1 / 1
Küçük Resim
İsim:
Tam Metin / Full Text.pdf
Boyut:
1.09 MB
Biçim:
Adobe Portable Document Format
İndir
Lisans paketi
Listeleniyor 1 - 1 / 1
Kapalı Erişim
İsim:
license.txt
Boyut:
1.17 KB
Biçim:
Item-specific license agreed upon to submission
Açıklama:
İndir

Koleksiyon

Yazılım Mühendisliği Bölümü
Bilgisayar Mühendisliği Bölümü Koleksiyonu