Open AccessProceedings Article
Anomaly detection in sea traffic - A comparison of the Gaussian Mixture Model and the Kernel Density Estimator
Rikard Laxhammar,Göran Falkman,Egils Sviestins +2 more
- pp 756-763
Reads0
Chats0
TLDR
This paper presents a first attempt to evaluate two previously proposed methods for statistical anomaly detection in sea traffic, namely the Gaussian Mixture Model and the adaptive Kernel Density Estimator, and indicates that KDE more accurately captures finer details of normal data.Abstract:
This paper presents a first attempt to evaluate two previously proposed methods for statistical anomaly detection in sea traffic, namely the Gaussian Mixture Model (GMM) and the adaptive Kernel Density Estimator (KDE). A novel performance measure related to anomaly detection, together with an intermediate performance measure related to normalcy modeling, are proposed and evaluated using recorded AIS data of vessel traffic and simulated anomalous trajectories. The normalcy modeling evaluation indicates that KDE more accurately captures finer details of normal data. Yet, results from anomaly detection show no significant difference between the two techniques and the performance of both is considered suboptimal. Part of the explanation is that the methods are based on a rather artificial division of data into geographical cells. The paper therefore discusses other clustering approaches based on more informed features of data and more background knowledge regarding the structure and natural classes of the data.read more
Citations
More filters
Journal ArticleDOI
Vessel Pattern Knowledge Discovery from AIS Data: A Framework for Anomaly Detection and Route Prediction
TL;DR: An unsupervised and incremental learning approach to the extraction of maritime movement patterns is presented here to convert from raw data to information supporting decisions, and is a basis for automatically detecting anomalies and projecting current trajectories and patterns into the future.
Proceedings ArticleDOI
Unsupervised Anomaly Detection via Variational Auto-Encoder for Seasonal KPIs in Web Applications
Haowen Xu,Wenxiao Chen,Nengwen Zhao,Zeyan Li,Jiahao Bu,Zhihan Li,Ying Liu,Youjian Zhao,Dan Pei,Yang Feng,Jie Chen,Zhaogang Wang,Honglin Qiao +12 more
TL;DR: In this paper, an unsupervised anomaly detection algorithm based on VAE is proposed, which greatly outperforms a state-of-the-art supervised ensemble approach and a baseline VAE approach, and its best F-scores range from 0.75 to 0.9.
Journal ArticleDOI
Exploiting AIS Data for Intelligent Maritime Navigation: A Comprehensive Survey From Data to Methodology
TL;DR: AIS data sources and relevant aspects of navigation in which such data are or could be exploited for safety of seafaring are surveyed, namely traffic anomaly detection, route estimation, collision prediction, and path planning.
Journal ArticleDOI
Online Learning and Sequential Anomaly Detection in Trajectories
Rikard Laxhammar,Göran Falkman +1 more
TL;DR: This article proposes and investigates the Sequential Hausdorff Nearest-Neighbor Conformal Anomaly Detector (SHNN-CAD) and the discords algorithm, a parameter-light algorithm that offers a well-founded approach to the calibration of the anomaly threshold.
Anomaly detection in vessel tracks using Bayesian networks
TL;DR: In this paper, the authors describe anomaly detection with data mined Bayesian Networks, learning them from real world Automated Identification System (AIS) data, and from supplementary data, producing both dynamic and static Bayesian network models.
References
More filters
Journal ArticleDOI
Maximum likelihood from incomplete data via the EM algorithm
Proceedings Article
Statistical analysis of motion patterns in AIS Data: Anomaly detection and motion prediction
TL;DR: In this article, a statistical analysis of vessel motion patterns in the ports and waterways using AIS ship self-reporting data is devoted to statistical analysis, which is carried out in the framework of adaptive kernel density estimation.
Proceedings Article
Anomaly detection for sea surveillance
TL;DR: In this paper, unsupervised clustering of normal vessel traffic patterns is proposed and implemented, where patterns are represented as the momentary location, speed and course of tracked vessels.
Proceedings ArticleDOI
Probabilistic associative learning of vessel motion patterns at multiple spatial scales for maritime situation awareness
TL;DR: An improved neurobiologically inspired algorithm for situation awareness in the maritime domain is presented, which takes real-time tracking information and learns motion pattern models on-the- fly, enabling the models to adapt well to evolving situations while maintaining high levels of performance.
Proceedings ArticleDOI
Maritime situation monitoring and awareness using learning mechanisms
TL;DR: This paper addresses maritime situation awareness by using cognitively inspired algorithms to learn behavioral patterns at a variety of conceptual, spatial, and temporal levels and combines two components: an unsupervised clustering algorithm, and a supervised mapping and labeling algorithm.