Comparative evaluation of VAE-based monitoring statistics for real-time anomaly detection in AIS data
YongKyung Oh,
Kwonin Yoon,
Jaemin Park and
Sungil Kim
Maritime Policy & Management, 2025, vol. 52, issue 4, 609-626
Abstract:
Real-time tracking and anomaly detection in vessel navigation using AIS (Automatic Identification System) data is a critical issue in maritime logistics. However, the substantial volume, inherent noise, and irregular temporal intervals of AIS data pose challenges in applying traditional Statistical Process Monitoring (SPM) methods. To overcome these challenges, recent research has proposed the use of deep probabilistic latent variable models, specifically variational autoencoders (VAE). However, the monitoring statistics based on VAE employed in previous studies may vary. In this study, we conduct a comprehensive comparison and evaluation of various monitoring statistics based on VAE within the context of statistical process monitoring. Furthermore, we propose a new real-time monitoring method by integrating VAE-based monitoring statistics with the CUSUM chart for monitoring AIS data. By utilizing both simulated and real-world AIS data, our proposed method demonstrates superior detection performance and robustness compared to traditional methods.
Date: 2025
References: Add references at CitEc
Citations:
Downloads: (external link)
http://hdl.handle.net/10.1080/03088839.2024.2388177 (text/html)
Access to full text is restricted to subscribers.
Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.
Export reference: BibTeX
RIS (EndNote, ProCite, RefMan)
HTML/Text
Persistent link: https://EconPapers.repec.org/RePEc:taf:marpmg:v:52:y:2025:i:4:p:609-626
Ordering information: This journal article can be ordered from
http://www.tandfonline.com/pricing/journal/TMPM20
DOI: 10.1080/03088839.2024.2388177
Access Statistics for this article
Maritime Policy & Management is currently edited by Dr Kevin Li and Heather Leggate McLaughlin
More articles in Maritime Policy & Management from Taylor & Francis Journals
Bibliographic data for series maintained by Chris Longhurst ().