Identifying causes of aviation safety events using wW2V-tCNN with data augmentation

Basit Öğe Kaydı
dc.authorscopusidWitold Pedrycz / 58861905800
dc.authorwosidWitold Pedrycz / HJZ-2779-2023
dc.contributor.authorXiong, Sheng Hua
dc.contributor.authorWei, Xi Hang
dc.contributor.authorChen, Zhen Song
dc.contributor.authorZhang, Hao
dc.contributor.authorPedrycz, Witold
dc.contributor.authorSkibniewski, Mirosław J.
dc.date.accessioned2025-04-18T10:32:24Z
dc.date.available2025-04-18T10:32:24Z
dc.date.issued2025
dc.departmentİstinye Üniversitesi, Mühendislik ve Doğa Bilimleri Fakültesi, Bilgisayar Mühendisliği Bölümü
dc.description.abstractIdentifying the causes of these safety events is crucial for safety agencies to create recommendations and for airlines to enhance procedures and mitigate hazards. This paper proposes a model to identify the causes of civil aviation safety events using a weighted Word2Vec-based Text-CNN (wW2V-tCNN) algorithm and data augmentation techniques. A corpus is built by matching narrative texts from investigation reports with cause labels from the Aviation Safety Network database. This corpus is transformed into Text-CNN inputs using a weighted sentence vector method based on word embeddings, considering word frequency and part-of-speech weighting. Additionally, a novel document balancing method is introduced for data augmentation. The proposed identification model achieves Macro-F1 and Macro-accuracy scores of 0.9803 and 0.9699, outperforming traditional methods and showing significant improvement over models like Doc2vec and SBERT. This model provides an accurate tool for safety agencies and airlines to analyze and effectively mitigate civil aviation safety events. © 2025 Informa UK Limited, trading as Taylor & Francis Group.
dc.identifier.citationXiong, S. H., Wei, X. H., Chen, Z. S., Zhang, H., Pedrycz, W., & Skibniewski, M. J. (2025). Identifying causes of aviation safety events using wW2V-tCNN with data augmentation. International Journal of General Systems, 1-30.
dc.identifier.doi10.1080/03081079.2025.2456960
dc.identifier.issn03081079
dc.identifier.scopus2-s2.0-85216466996
dc.identifier.scopusqualityQ2
dc.identifier.urihttp://dx.doi.org/10.1080/03081079.2025.2456960
dc.identifier.urihttps://hdl.handle.net/20.500.12713/7111
dc.identifier.wosWOS:001409573700001
dc.indekslendigikaynakScopus
dc.indekslendigikaynakWeb of Science
dc.institutionauthorPedrycz, Witold
dc.institutionauthoridWitold Pedrycz / 0000-0002-9335-9930
dc.language.isoen
dc.publisherTaylor and Francis Ltd.
dc.relation.ispartofInternational Journal of General Systems
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı
dc.rightsinfo:eu-repo/semantics/closedAccess
dc.subjectAviation Safety
dc.subjectData Augmentatio
dc.subjectText-CNN
dc.subjectWord Weight
dc.subjectWord2Vec
dc.titleIdentifying causes of aviation safety events using wW2V-tCNN with data augmentation
dc.typeArticle

Dosyalar

Orijinal paket
Listeleniyor 1 - 1 / 1
Küçük Resim
İsim:
Identifying causes of aviation safety events using wW2V-tCNN with data augmentation (1).pdf
Boyut:
3.57 MB
Biçim:
Adobe Portable Document Format
İndir
Lisans paketi
Listeleniyor 1 - 1 / 1
Küçük Resim Yok
İsim:
license.txt
Boyut:
1.17 KB
Biçim:
Item-specific license agreed upon to submission
Açıklama:
İndir

Koleksiyon

Bilgisayar Mühendisliği Bölümü Makale Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu