Change search
Link to record
Permanent link

Direct link
BETA
Osekowska, Ewa
Publications (6 of 6) Show all publications
Osekowska, E., Johnson, H. & Carlsson, B. (2017). Maritime vessel traffic modeling in the context of concept drift. In: Transportation Research Procedia: . Paper presented at World Conference on Transport Research - WCTR 2016, Shanghai (pp. 1457-1476). Elsevier, 25
Open this publication in new window or tab >>Maritime vessel traffic modeling in the context of concept drift
2017 (English)In: Transportation Research Procedia, Elsevier, 2017, Vol. 25, p. 1457-1476Conference paper, Published paper (Refereed)
Abstract [en]

Maritime traffic modeling serves the purpose of extracting human-readable information and discovering knowledge in the otherwise illegible mass of traffic data. The goal of this study is to examine the presence and character of fluctuations in maritime traffic patterns. The main objective is to identify such fluctuations and capture them in terms of a concept drift, i.e., unforeseen shifts in statistical properties of the modeled target occurring over time. The empirical study is based on a collection of AIS vessel tracking data, spanning over a year. The scope of the study limits the AIS data area to the Baltic region (9-31°E, 53-66°N), which experiences some of the most dense maritime traffic in the world. The investigations employ a novel maritime traffic modeling method based on the potential fields concept, adapted for this study to facilitate the examination of concept drift. The concept drift is made apparent in course of the statistical and visual analysis of the experimental results. This study shows a number of particular cases, in which the maritime traffic is affected by concept drifts of varying extent and character. The visual representations of the traffic models make shifts in the traffic patterns apparent and comprehensible to human eye. Based on the experimental outcomes, the robustness of the modeling method against concept drift in traffic is discussed and improvements are proposed. The outcomes provide insights into regularly reoccurring drifts and irregularities within the traffic data itself that may serve to further optimize the modeling method, and - in turn - the performance of detection based on it. © 2017 The Authors. Published by Elsevier B. V.

Place, publisher, year, edition, pages
Elsevier, 2017
Series
Transportation Research Procedia
Keywords
anomaly detection, concept drift, maritime traffic, traffic modeling
National Category
Information Systems
Identifiers
urn:nbn:se:bth-14677 (URN)10.1016/j.trpro.2017.05.173 (DOI)
Conference
World Conference on Transport Research - WCTR 2016, Shanghai
Available from: 2017-06-22 Created: 2017-06-22 Last updated: 2018-01-13Bibliographically approved
Osekowska, E. & Carlsson, B. (2015). Learning Maritime Traffic Rules Using Potential Fields. In: COMPUTATIONAL LOGISTICS (ICCL 2015): . Paper presented at 6th International Conference on Computational Logistics (ICCL), SEP 23-25, 2015, Delft, NETHERLANDS (pp. 298-312).
Open this publication in new window or tab >>Learning Maritime Traffic Rules Using Potential Fields
2015 (English)In: COMPUTATIONAL LOGISTICS (ICCL 2015), 2015, p. 298-312Conference paper, Published paper (Refereed)
Abstract [en]

The Automatic Identification System (AIS) is used to identify and locate active maritime vessels. Datasets of AIS messages recorded over time make it possible to model ship movements and analyze traffic events. Here, the maritime traffic is modeled using a potential fields method, enabling the extraction of traffic patterns and anomaly detection. A software tool named STRAND, implementing the modeling method, displays real-world ship behavior patterns, and is shown to generate traffic rules spontaneously. STRAND aids maritime situational awareness by displaying patterns of common behaviors and highlighting suspicious events, i.e., abstracting informative content from the raw AIS data and presenting it to the user. In this it can support decisions regarding, e.g., itinerary planning, routing, rescue operations, or even legislative traffic regulation. This study in particular focuses on identification and analysis of traffic rules discovered based on the computed traffic models. The case study demonstrates and compares results from three different areas, and corresponding traffic rules identified in course of the result analysis. The ability to capture distinctive, repetitive traffic behaviors in a quantitative, automatized manner may enhance detection and provide additional information about sailing practices.

Series
Lecture Notes in Computer Science, ISSN 0302-9743 ; 9335
Keywords
Anomaly detection, Visualization, Potential fields, Automatic identification system, Traffic modeling
National Category
Computer and Information Sciences
Identifiers
urn:nbn:se:bth-11351 (URN)10.1007/978-3-319-24264-4_21 (DOI)000365946400021 ()978-3-319-24264-4; 978-3-319-24263-7 (ISBN)
Conference
6th International Conference on Computational Logistics (ICCL), SEP 23-25, 2015, Delft, NETHERLANDS
Available from: 2016-01-04 Created: 2016-01-04 Last updated: 2018-01-10Bibliographically approved
Osekowska, E., Axelsson, S. & Carlsson, B. (2015). Potential fields in modeling transport over water. Operations Research/Computer Science Interfaces Series, 58, 259-280
Open this publication in new window or tab >>Potential fields in modeling transport over water
2015 (English)In: Operations Research/Computer Science Interfaces Series, ISSN 1387-666X, Vol. 58, p. 259-280Article in journal (Refereed) Published
Abstract [en]

Without an explicit road-like regulation, following the proper sailing routes and practices is still a challenge mostly addressed using seamen’s know-how and experience. This chapter focuses on the problem of modeling ship movements over water with the aim to extract and represent this kind of knowledge. The purpose of the developed modeling method, inspired by the theory of potential fields, is to capture the process of navigation and piloting through the observation of ship behaviors in transport over water on narrow waterways. When successfully modeled, that knowledge can be subsequently used for various purposes. Here, the models of typical ship movements and behaviors are used to provide a visual insight into the actual normal traffic properties (maritime situational awareness) and to warn about potentially dangerous traffic behaviors (anomaly detection). A traffic modeling and anomaly detection prototype system STRAND implements the potential field based method for a collected set of AIS data. A quantitative case study is taken out to evaluate the applicability and performance of the implemented modeling method. The case study focuses on quantifying the detections for varying geographical resolution of the detection process. The potential fields extract and visualize the actual behavior patterns, such as right-hand sailing rule and speed limits, without any prior assumptions or information introduced in advance. The display of patterns of correct (normal) behavior aids the choice of an optimal path, in contrast to the anomaly detection which notifies about possible traffic incidents. A tool visualizing the potential fields may aid traffic surveillance and incident response, help recognize traffic regulation and legislative issues, and facilitate the process of waterways development and maintenance. © Springer International Publishing Switzerland 2015.

National Category
Computer Sciences
Identifiers
urn:nbn:se:bth-10656 (URN)10.1007/978-3-319-16133-4_14 (DOI)2-s2.0-84930617045 (Scopus ID)
Available from: 2015-09-17 Created: 2015-09-15 Last updated: 2018-01-11Bibliographically approved
Osekowska, E. (2014). Design and Implementation of a Maritime Traffic Modeling and Anomaly Detection Method. (Licentiate dissertation). Karlskrona: Blekinge Institute of Technology
Open this publication in new window or tab >>Design and Implementation of a Maritime Traffic Modeling and Anomaly Detection Method
2014 (English)Licentiate thesis, comprehensive summary (Other academic)
Abstract [en]

Nowadays ships are usually equipped with a system of marine instruments, one of which is an Automatic Identification System (AIS) transponder. The availability of the global AIS ship tracking data opened the possibilities to develop maritime security far beyond the simple collision prevention. The research work summarized in this thesis explores this opportunity, with the aim of developing an intuitive and comprehensible method for traffic modeling and anomaly detection in the maritime domain. The novelty of the method lays in employing the technique of artificial potential fields. The general idea is for the potentials to represent typical patterns of vessels' behaviors. A conflict between potentials, which have been observed in the past, and the potential of a vessel currently in motion, indicates an anomaly. The developed potential field based method has been examined using a web-based anomaly detection system STRAND (for Seafaring TRansport ANomaly Detection). Its applicability has been demonstrated in several publications, examining its scalability, modeling capabilities and detection performance. The experimental investigations led to identifying optimal detection resolution for different traffic areas (open sea, harbor and river), and extracting traffic rules, e.g., with regard to speed limits and course, i.e., right-hand sailing rule. The map-based display of modeled traffic patterns and detection cases has been analyzed as well, using several demonstrative cases. The massive AIS database created for this study, together with a dataset of real traffic incidents, provides an abundance of challenges for future studies.

Place, publisher, year, edition, pages
Karlskrona: Blekinge Institute of Technology, 2014. p. 113 p.
Series
Blekinge Institute of Technology Licentiate Dissertation Series, ISSN 1650-2140 ; 9
National Category
Computer Sciences
Identifiers
urn:nbn:se:bth-00600 (URN)oai:bth.se:forskinfoA2E86BCA1FF1BEE4C1257D79005719E8 (Local ID)978-91-7295-291-1 (ISBN)oai:bth.se:forskinfoA2E86BCA1FF1BEE4C1257D79005719E8 (Archive number)oai:bth.se:forskinfoA2E86BCA1FF1BEE4C1257D79005719E8 (OAI)
Available from: 2014-12-15 Created: 2014-10-22 Last updated: 2018-01-11Bibliographically approved
Osekowska, E., Johnson, H. & Carlsson, B. (2014). Grid size optimization for potential field based maritime anomaly detection. In: Benitez, FG Rossi, R (Ed.), 17TH MEETING OF THE EURO WORKING GROUP ON TRANSPORTATION, EWGT2014: . Paper presented at 17th Meeting of the EURO-Working-Group on Transportation (EWGT), JUL 02-04, 2014, Sevilla, SPAIN (pp. 720-729). ELSEVIER SCIENCE BV
Open this publication in new window or tab >>Grid size optimization for potential field based maritime anomaly detection
2014 (English)In: 17TH MEETING OF THE EURO WORKING GROUP ON TRANSPORTATION, EWGT2014 / [ed] Benitez, FG Rossi, R, ELSEVIER SCIENCE BV , 2014, p. 720-729Conference paper, Published paper (Refereed)
Abstract [en]

This study focuses on improving the potential field based maritime data modeling method, developed to extract traffic patterns and detect anomalies, in a clear, understandable and informative way. The method's novelty lies in employing the concept of a potential field for AIS vessel tracking data abstraction and maritime traffic representation. Unlike the traditional maritime surveillance equipment, such as radar or GPS, the AIS system comprehensively represents the identity and properties of a vessel, as well as its behavior, thus preserving the effects of navigational decisions, based on the skills of experienced seamen. In the developed data modeling process, every vessel generates potential charges, which value represent the vessel's behavior, and drops the charges at locations it passes. Each AIS report is used to assign a potential charge at the reported vessel positions. The method derives three construction elements, which define, firstly, how charges are accumulated, secondly, how a charge decays over time, and thirdly, in what way the potential is distributed around the source charge. The collection of potential fields represents a model of normal behavior, and vessels not conforming to it are marked as anomalous. In the anomaly detection prototype system STRAND, the sensitivity of anomaly detection can be modified by setting a geographical coordinate grid precision to more dense or coarse. The objective of this study is to identify the optimal grid size for two different conditions an open sea and a port area case. A noticeable shift can be observed between the results for the open sea and the port area. The plotted detection rates converge towards an optimal ratio for smaller grid sizes in the port area (60-200 meters), than in the open sea case (300-1000 meters). The effective outcome of the potential filed based anomaly detection is filtering out all vessels behaving normally and presenting a set of anomalies, for a subsequent incident analysis using STRAND as an information visualization tool.

Place, publisher, year, edition, pages
ELSEVIER SCIENCE BV, 2014
Series
Transportation Research Procedia, ISSN 2352-1465 ; 3
Keywords
anomaly detection, maritime traffic, potential field, AIS
National Category
Communication Systems Computer Systems
Identifiers
urn:nbn:se:bth-14579 (URN)10.1016/j.trpro.2014.10.051 (DOI)000377412600077 ()
Conference
17th Meeting of the EURO-Working-Group on Transportation (EWGT), JUL 02-04, 2014, Sevilla, SPAIN
Available from: 2017-06-19 Created: 2017-06-19 Last updated: 2017-06-19Bibliographically approved
Osekowska, E., Axelsson, S. & Carlsson, B. (2013). Potential fields in maritime anomaly detection. In: : . Paper presented at Proceedings of the 3rd International Conference on Models and Technologies for Intelligent Transport Systems. Dresden: TUD Press
Open this publication in new window or tab >>Potential fields in maritime anomaly detection
2013 (English)Conference paper, Published paper (Refereed)
Abstract [en]

This paper presents a novel approach for pattern extraction and anomaly detection in mari- time vessel traffic, based on the theory of potential fields. Potential fields are used to rep- resent and model normal, i.e. correct, behaviour in maritime transportation, observed in historical vessel tracks. The recorded paths of each maritime vessel generate potentials based on metrics such as geographical location, course, velocity, and type of vessel, resulting in a potential-based model of maritime traffic patterns. A prototype system STRAND, developed for this study, computes and displays distinctive traffic patterns as potential fields on a geographic representation of the sea. The system builds a model of normal behaviour, by collating and smoothing historical vessel tracks. The resulting visual presentation exposes distinct patterns of normal behaviour inherent in the recorded maritime traffic data. Based on the created model of normality, the system can then perform anomaly detection on current real-world maritime traffic data. Anomalies are detected as conflicts between vessel’s potential in live data, and the local history-based potential field. The resulting detection performance is tested on AIS maritime tracking data from the Baltic region, and varies depending on the type of potential. The potential field based approach contributes to maritime situational awareness and enables automatic detection. The results show that anomalous behaviours in maritime traffic can be detected using this method, with varying performance, necessitating further study.

Place, publisher, year, edition, pages
Dresden: TUD Press, 2013
Keywords
Anomaly Detection, Maritime Traffic, Potential Fields
National Category
Computer Sciences
Identifiers
urn:nbn:se:bth-6417 (URN)oai:bth.se:forskinfo1A9F575FF8EB6F16C1257D96003EF055 (Local ID)978-3-944331-34-8 (ISBN)oai:bth.se:forskinfo1A9F575FF8EB6F16C1257D96003EF055 (Archive number)oai:bth.se:forskinfo1A9F575FF8EB6F16C1257D96003EF055 (OAI)
Conference
Proceedings of the 3rd International Conference on Models and Technologies for Intelligent Transport Systems
Available from: 2015-02-17 Created: 2014-11-20 Last updated: 2018-01-11Bibliographically approved
Organisations

Search in DiVA

Show all publications