EUVIMEDEUVIMED entdecken
Zurückgezogene PublikationOpen Access · CC BY 4.0

Machine learning-based anomaly detection and prediction in commercial aircraft using autonomous surveillance data

Tian Xia iD, Lanju Zhou, Khalil Ahmad

PLOS ONE · 06.02.2025 · 20 (2) · e0317914

DOI: 10.1371/journal.pone.0317914 ↗

Kurz gefasst

Zurückgezogene Publikation in der Zeitschrift PLOS ONE, online erschienen am 06.02.2025. Verfasst von Tian Xia und 2 weiteren Autor:innen. Beteiligte Einrichtung: School of Intelligent Manufacturing, Tianjin Electronic Information College, Tianjin, China. Hauptthemen laut MEDLINE: Machine Learning, Aircraft, Accidents, Aviation. Die Arbeit wurde bisher 14-mal zitiert (Crossref) und nennt 52 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Natural Science Research Project for higher education institutions in Tianjin Municipality, Tianjin Electronic Information College 2024 “TY Plan” to serve “The new quality productive forces” project.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Regarding the transportation of people, commodities, and other items, aeroplanes are an essential need for society. Despite the generally low danger associated with various modes of transportation, some accidents may occur. The creation of a machine learning model employing data from autonomous-reliant surveillance transmissions is essential for the detection and prediction of commercial aircraft accidents. This research included the development of abnormal categorisation models, assessment of data recognition quality, and detection of anomalies. The research methodology consisted of the following steps: formulation of the problem, selection of data and labelling, construction of the model for prediction, installation, and testing. The data tagging technique was based on the requirements set by the Global Aviation Organisation for business jet-engine aircraft, which expert business pilots then validated. The 93% precision demonstrated an excellent match for the most effective prediction model, linear dipole testing. Furthermore, the "good fit" of the model was verified by its achieved area-under-the-curve ratios of 0.97 for abnormal identification and 0.96 for daily detection.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Machine LearningAircraftAccidents, AviationHumans

Autor:innen und Institutionen

  • School of Intelligent Manufacturing, Tianjin Electronic Information College, Tianjin, China.
  • School of Instrumentation and Optoelectronic Engineering, Beihang University, Beijing, China.

ORCID-Profile: Tian Xia

Förderung

  • Natural Science Research Project for higher education institutions in Tianjin Municipality
  • Tianjin Electronic Information College 2024 “TY Plan” to serve “The new quality productive forces” project

Zitieren

APA

Xia, T., Zhou, L., & Ahmad, K. (2025). Machine learning-based anomaly detection and prediction in commercial aircraft using autonomous surveillance data. PLOS ONE, 20(2), e0317914. https://doi.org/10.1371/journal.pone.0317914

Vancouver

Xia T, Zhou L, Ahmad K. Machine learning-based anomaly detection and prediction in commercial aircraft using autonomous surveillance data. PLOS ONE. 2025;20(2):e0317914. doi:10.1371/journal.pone.0317914

BibTeX
@article{Xia2025,
  author = {Xia, Tian and Zhou, Lanju and Ahmad, Khalil},
  title = {Machine learning-based anomaly detection and prediction in commercial aircraft using autonomous surveillance data},
  journal = {PLOS ONE},
  year = {2025},
  volume = {20},
  number = {2},
  pages = {e0317914},
  doi = {10.1371/journal.pone.0317914}
}
Kostenlos starten →