There are no files associated with this item.
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.citation.endPage | 13 | - |
dc.citation.startPage | 1 | - |
dc.citation.title | IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING | - |
dc.contributor.author | Oh, YongKyung | - |
dc.contributor.author | Kim, Sungil | - |
dc.date.accessioned | 2024-01-09T10:35:10Z | - |
dc.date.available | 2024-01-09T10:35:10Z | - |
dc.date.created | 2024-01-08 | - |
dc.date.issued | 2023-11 | - |
dc.description.abstract | Maritime logistics play an important role in the global economy. However, the uncertain and dynamic maritime environment presents challenges that hamper the achievement of proper situational awareness in route transportation. In the case of ocean transportation, detecting the anomalous behavior of vessels in such an unpredictable environment promotes the rapid achievement of successful situational awareness. To detect abnormal behavior of vessels, we propose a novel statistical anomaly detector in a grid-based structure. To overcome the drawback of the grid-based approach when the monitored area is large, we divide the monitored area into multiple grids by selecting intermediate cells. For each grid, the proposed method extracts a normal representation, called a baseline, from historical AIS data combined with bill-of-lading data. Bayesian bootstrap techniques are adopted to quantify any uncertainty in the baseline and to compute the probability that each route will be abnormal. Based on the computed probability, the proposed method enables real-time spatial and temporal maritime traffic monitoring. The effectiveness of the proposed method is evaluated using simulated data and real data from maritime logistics. |
- |
dc.identifier.bibliographicCitation | IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING, pp.1 - 13 | - |
dc.identifier.doi | 10.1109/TASE.2023.3329041 | - |
dc.identifier.issn | 1545-5955 | - |
dc.identifier.scopusid | 2-s2.0-85177028023 | - |
dc.identifier.uri | https://scholarworks.unist.ac.kr/handle/201301/67882 | - |
dc.identifier.wosid | 001103662700001 | - |
dc.language | 영어 | - |
dc.publisher | Institute of Electrical and Electronics Engineers | - |
dc.title | Grid-Based Bayesian Bootstrap Approach for Real-Time Detection of Abnormal Vessel Behaviors From AIS Data in Maritime Logistics | - |
dc.type | Article | - |
dc.description.isOpenAccess | FALSE | - |
dc.relation.journalWebOfScienceCategory | Automation & Control Systems | - |
dc.relation.journalResearchArea | Automation & Control Systems | - |
dc.type.docType | Article | - |
dc.description.journalRegisteredClass | scie | - |
dc.description.journalRegisteredClass | scopus | - |
dc.subject.keywordAuthor | Uncertainty | - |
dc.subject.keywordAuthor | Anomaly detection | - |
dc.subject.keywordAuthor | Artificial intelligence | - |
dc.subject.keywordAuthor | baseline traffic extraction | - |
dc.subject.keywordAuthor | Bayes methods | - |
dc.subject.keywordAuthor | Behavioral sciences | - |
dc.subject.keywordAuthor | machine learning | - |
dc.subject.keywordAuthor | maritime traffic representation | - |
dc.subject.keywordAuthor | Statistical anomaly detection | - |
dc.subject.keywordAuthor | Trajectory | - |
dc.subject.keywordAuthor | Transportation | - |
dc.subject.keywordPlus | KNOWLEDGE DISCOVERY | - |
dc.subject.keywordPlus | ANOMALY DETECTION | - |
dc.subject.keywordPlus | IDENTIFICATION | - |
dc.subject.keywordPlus | PATTERNS | - |
dc.subject.keywordPlus | PATH | - |
Items in Repository are protected by copyright, with all rights reserved, unless otherwise indicated.
Tel : 052-217-1404 / Email : scholarworks@unist.ac.kr
Copyright (c) 2023 by UNIST LIBRARY. All rights reserved.
ScholarWorks@UNIST was established as an OAK Project for the National Library of Korea.