The DOI matches its Crossref record; 12 of the 12 references it cites were found in a registry or an index.
Maritime Anomaly Detection Based on Mean-Reverting Stochastic Processes Applied to a Real-World Scenario
Open accessAbstract
A novel anomaly detection procedure is presented, based on the Ornstein-Uhlenbeck (OU) mean-reverting stochastic process. The considered anomaly is a vessel that deviates from a planned route, changing its nominal velocity. In order to hide this behavior, the vessel switches off its Automatic Identification System (AIS) device for a certain time, and then tries to revert to the previous nominal velocity. The decision that has to be taken is either declaring that a deviation happened or not, relying only upon two consecutive AIS contacts. A proper statistical hypothesis testing procedure that builds on the changes in the OU process long-term velocity parameter of the vessel is the core of the proposed approach and enables for the solution of the anomaly detection problem.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The anomaly detector in [31], [32] runs a generalized likelihood ratio test to make decisions on the existence of anomalous deviations within a given time window relying upon available measurements such as AIS, radar, or SAR.
“Using the OU model to represent the vessel dynamics and contextual information to define the nominal behaviour at sea, the anomaly detector in [31], [32] runs a hypothesis testing procedure - the generalized likelihood ratio test - to make decisions on the existence of anomalous deviations within a given time window relying upon the available measurements (e.g. AIS, radar, SAR).”
From Space-Based Global Maritime Surveillance. Part II: Artificial Intelligence and Data Fusion Techniques (2021) · cites this paper as [32]
Section C describes a generalized likelihood ratio test for detecting deviations, and Section II formulates the decision over the interval during which AIS is disabled. But the Introduction says this paper's decision relies only on two consecutive AIS contacts; it assigns the extension to other sensor contacts to a different work. This source therefore does not support the radar and SAR examples. (LLM, conf=0.89)
Experimental — accuracy not yet measuredThis method can integrate measurements from multiple sources and handle different levels of data unavailability.
“This method, successfully applied to a real-world rendezvous detection scenario in [32], can integrate measurements from multiple sources and handle different levels of data unavailability.”
From Space-Based Global Maritime Surveillance. Part II: Artificial Intelligence and Data Fusion Techniques (2021) · cites this paper as [32]
The First and Second region sections (page numbers unavailable) show the detector working with simulated gaps in real-world AIS tracks, supporting its use when some data are unavailable. The paper does not show it integrating measurements from multiple sources or establish performance across different levels of data unavailability. (LLM, conf=0.84)
Experimental — accuracy not yet measuredAn innovative statistical framework combines available context data with a parametric model of the vessel's kinematic behaviour.
“More recently, an innovative statistical framework [31], [32] that combines the available context data with a parametric model of the vessel's kinematic behaviour has received special attention.”
From Space-Based Global Maritime Surveillance. Part II: Artificial Intelligence and Data Fusion Techniques (2021) · cites this paper as [32]
The Problem Formulation describes a statistical hypothesis test using a parametric Ornstein–Uhlenbeck model of vessel velocity, supporting the kinematic-model part of the claim. But the Introduction says the decision relies only on two AIS contacts, and the Problem Formulation specifies no other information during the gap; our copy does not establish that the framework combines the model with available context data. Page numbers are unavailable in our copy. (LLM, conf=0.83)
Experimental — accuracy not yet measuredThis line of research has focused on the development of anomaly detection strategies that provide the ability to reveal vessel deviations from standard navigational routes as well as dark deviations in the presence of possibly intentional surveillance gaps.
“This line of research has focused on the development of anomaly detection strategies that provide the ability to reveal vessel deviations from standard navigational routes as well as dark deviations in the presence of possibly intentional surveillance gaps (due to AIS disablements or limited sensor coverage).”
From Space-Based Global Maritime Surveillance. Part II: Artificial Intelligence and Data Fusion Techniques (2021) · cites this paper as [32]
This method has been successfully applied to a real-world rendezvous detection scenario.
“This method, successfully applied to a real-world rendezvous detection scenario in [32], can integrate measurements from multiple sources and handle different levels of data unavailability.”
From Space-Based Global Maritime Surveillance. Part II: Artificial Intelligence and Data Fusion Techniques (2021) · cites this paper as [32]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Survey of maneuvering targettracking . part I: dynamic models
Li, X. R., & Jilkov, V. P. (2003) · IEEE Transactions on Aerospace and Electronic Systems · doi:10.1109/taes.2003.1261132 · Cited by 2,410
Fundamentals of Statistical Signal Processing, Volume II: Detection Theory
Kay, S. (1998) · Cited by 716
Maritime anomaly detection and threat assessment
(2010) · doi:10.1109/icif.2010.5711998 · Cited by 131
Modeling vessel kinematics using a stochastic mean-reverting process for long-term prediction
Millefiori, L. M., Braca, P., Bryan, K., & Willett, P. (2016) · IEEE Transactions on Aerospace and Electronic Systems · doi:10.1109/taes.2016.150596 · Cited by 119
Self-citationMultiple Ornstein–Uhlenbeck Processes for Maritime Traffic Graph Representation
Coscia, P., Braca, P., Millefiori, L. M., Palmieri, F. A. N., & Willett, P. (2018) · IEEE Transactions on Aerospace and Electronic Systems · doi:10.1109/taes.2018.2808098 · Cited by 77
Self-citationPerformance analysis of a class of transient detection algorithms-a unified framework
Porat, B., & Friedlander, B. (1992) · IEEE Transactions on Signal Processing · doi:10.1109/78.157294 · Cited by 39
Data adaptive rank-shaping methods for solving least squares problems
Thorpe, A. J., & Scharf, L. L. (1995) · IEEE Transactions on Signal Processing · doi:10.1109/78.398720 · Cited by 35
Millefiori, L. M., Braca, P., & Willett, P. (2016) · IEEE Signal Processing Letters · doi:10.1109/lsp.2016.2605705 · Cited by 30
Self-citationPerformance Assessment of Vessel Dynamic Models for Long-Term Prediction Using Heterogeneous Data
Vivone, G., Millefiori, L. M., Braca, P., et al. (2017) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2017.2729622 · Cited by 27
Self-citationLong-term vessel kinematics prediction exploiting mean-reverting processes
Millefiori, L. M., Braca, P., Bryan, K., et al. (2016) · Cited by 11
Self-citationModel performance assessment for long-term vessel prediction using HFSW radar data
Vivone, G., Millefiori, L. M., Braca, P., et al. (2017) · Proceedings of the IEEE National Radar Conference · doi:10.1109/radar.2017.7944205 · Cited by 4
Self-citation
Flagged first, then by citations
Research works printed but not linked: 3
- d'afflisio, 0, Detecting stealth deviations from standard routes using the Ornstein-Uhlenbeck process
- alava, 2017, Massive Chinese fleet jeopardizes threatened shark species around the Galápagos marine reserve and waters off Ecuador: Implications for national and international fisheries policy, International Journal of Fisheries Research
- jakob, 2009, Adversarial modeling and reasoning in the maritime domain
Cited by
Sorted by citations
Soldi, G., Gaglione, D., Forti, N., Millefiori, L. M., Braca, P., Carniel, S., Simone, A. D., Iodice, A., Riccio, D., Daffina, F. C., et al. (2021) · IEEE Aerospace and Electronic Systems Magazine · doi:10.1109/maes.2021.3070884 · Cited by 44
“For decades, anomaly detection strategies have been explored and applied in maritime traffic monitoring [8], [14], [15], [29]–[33] in order to detect unexpected ship stops or unexpected changes in course, i.”
BackgroundMethodInfluentialSelf-citationHybrid Bernoulli Filtering for Detection and Tracking of Anomalous Path Deviations
Forti, N., Millefiori, L. M., & Braca, P. (2018) · 2018 21st International Conference on Information Fusion (FUSION) · doi:10.23919/icif.2018.8455567 · Cited by 14
Self-citation
Metadata
- Authors
- d'Afflisio, E., Braca, P., Millefiori, L. M., & Willett, P.
- Affiliations
- NATO Centre for Maritime Research and Experimentation (IT)
- University of Connecticut (US)
- Venue
- 2018 21st International Conference on Information Fusion (FUSION)
- Publisher
- IEEE
- Published
- 2018-07
- Pages
- 1171-1177
- OpenAlex
- W2889603650
- Cited by
- 33
- References
- 12
- Citations by year
- 2026: 1 · 2025: 3 · 2024: 4 · 2023: 2 · 2022: 5 · 2021: 9 · 2020: 4 · 2019: 4 · 2018: 1
- FWCI
- 1.79
- Type
- conference paper
- Language
- en
- Open access
- green
- ieeexplore.ieee.org
- Licence
- other-oa
- Locations
- International Conference on Information Fusion (FUSION) (publishedVersion)
- Florence Research (University of Florence) (submittedVersion, other-oa)
- Funders
- University of the Aegean
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Anomaly Detection Techniques and Applications
- Physical Sciences › Engineering › Ocean Engineering › Maritime Navigation and Safety
- Physical Sciences › Computer Science › Artificial Intelligence › Target Tracking and Data Fusion in Sensor Networks
- Keywords
- maritime anomaly detection, Ornstein-Uhlenbeck process, Automatic Identification System, hypothesis testing, maritime surveillance
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
