A deep feature driven expert system to estimate the postmortem interval from corneal opacity development

Basit Öğe Kaydı
dc.authorid0000-0003-0690-1873
dc.authorid0000-0001-9720-9852
dc.contributor.authorCantürk, İsmail
dc.contributor.authorÖzyılmaz, Lale
dc.date.accessioned2024-10-18T06:10:47Z
dc.date.available2024-10-18T06:10:47Z
dc.date.issued2024
dc.departmentFakülteler, Mühendislik ve Doğa Bilimleri Fakültesi, Mekatronik Mühendisliği Bölümü
dc.description.abstractPostmortem interval (PMI) estimation remains an unresolved challenge in forensic science, necessitating practical, reliable andmore accurate tools. This study aimed to develop a quantitative PMI estimation tool that effectively meets these needs. Focusingon the postmortem opacity development of the eye as a key marker for determining time since death, we propose an artificialintelligence-based clinical PMI prediction system utilising computer vision, deep learning and machine learning methods. TheAlexNet algorithm was utilised to extract deep features from the postmortem eye images. Extracted features were then processedby machine learning algorithms. For feature selection, Lasso and Relief techniques were employed, while SVM and KNN wereapplied for classifications. The results were validated using the leave- one-subject-out method. The system was tested across dif-ferent postmortem ranges, providing multi-label predictions. The performance was evaluated using various metrics. The deepfeatures exhibited effective performance in grading postmortem opacity development, achieving state-of-the-art results. Theaccuracy scores were 0.96 and 0.97 for 3-h intervals (i.e., 5-class) and 5-h intervals (i.e., 3-class) experiments, respectively. Theexperimental results indicate that the proposed system represents a promising tool for PMI estimation.
dc.description.sponsorshipYildiz Technical University -- FBA-2021-4429
dc.identifier.citationCantürk, İ., & Özyılmaz, L. (2024). A deep feature driven expert system to estimate the postmortem ınterval from corneal opacity development. Expert Systems. https://doi.org/10.1111/exsy.13757
dc.identifier.doi10.1111/exsy.13757
dc.identifier.issn1468-0394
dc.identifier.issn0266-4720
dc.identifier.scopus2-s2.0-85206153436
dc.identifier.scopusqualityQ1
dc.identifier.urihttps://doi.org/10.1111/exsy.13757
dc.identifier.urihttps://hdl.handle.net/20.500.13055/827
dc.identifier.wosWOS:001330267500001
dc.identifier.wosqualityQ2
dc.indekslendigikaynakWeb of Science
dc.indekslendigikaynakScopus
dc.indekslendigikaynakPubMed
dc.institutionauthorÖzyılmaz, Lale
dc.institutionauthorid0000-0001-9720-9852
dc.language.isoen
dc.publisherWiley
dc.relation.ispartofExpert Systems
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı
dc.rightsinfo:eu-repo/semantics/closedAccess
dc.subjectCorneal Opacity
dc.subjectDeep Features
dc.subjectForensic Science
dc.subjectPostmortem Interval Estimation
dc.subjectTime of Death
dc.titleA deep feature driven expert system to estimate the postmortem interval from corneal opacity development
dc.typeArticle
dspace.entity.typePublication

Dosyalar

Orijinal paket
Listeleniyor 1 - 1 / 1
Kapalı Erişim
İsim:
Tam Metin / Full Text
Boyut:
4.45 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

Mekatronik Mühendisliği Bölümü Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu
WoS İndeksli Yayınlar Koleksiyonu