Trajectory pattern extraction and anomaly detection for maritime vessels

Karataş, Gözde; Karagöz, Pınar; Ayran, Orhan

doi:10.1016/j.iot.2021.100436

Cited by 39 publications

(20 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently methods that apply various machine learning algorithms for anomalies detection have also emerged in the literature, e.g., neural networks (Nguyen et al, 2021;Singh & Heymann, 2020;Venskus, Treigys, Bernatavičienė, Tamulevičius, & Medvedev, 2019;Zhao & Shi, 2019) or deep learning (Hoque & Sharma, 2020;Karataş et al, 2021). They are used to predict a vessel trajectory, and based on the comparison to normal routes, provide information about anomalous behaviour.…”

Section: Anomalies Detection: Approaches Methodsmentioning

confidence: 99%

“…Among clustering-based methods the DBSCAN algorithm is applied to detect anomalies in a ship's speed (Kraiman, Arouh, & Webb, 2002;Pallotta et al, 2013) to identify some popular entry or exit points to a particular area (Pallotta et al, 2013) or to identify loitering (Patino & Ferryman, 2017). Recently, DBSCAN was further combined with Recurrent Neural Network (Zhao & Shi, 2019) or the Long-Short Term Memory (LSTM) architecture (Karataş et al, 2021) to predict vessel trajectories and then detect anomalies.…”

Section: Anomalies Detection: Approaches Methodsmentioning

confidence: 99%

“…Another clustering method is the K-mean method used to detect various activities of ships (Tun, Chambers, Tan, & Ly, 2007). Hierarchical clustering methods are also used to learn the typical sailing patterns, which then can be combined with probabilistic methods (the Naïve Bayes classifier) (Zhen, Jin, Hu, Shao, & Nikitakos, 2017) or methods for measuring similarities between two trajectories (e.g., Longest Common Subsequence-LCS algorithm) (Karataş et al, 2021) to detect anomalous behaviour.…”

Section: Anomalies Detection: Approaches Methodsmentioning

confidence: 99%

“…Construction of the network-preceded by waypoints detection, route detection, and route decomposition-relies on the Douglas-Pecker algorithm for breakpoints detection (these will serve as nodes) along with a custom algorithm for creating traffic lanes (edges). Also Karataş, Karagoz, and Ayran (2021) extended TREAD by adding direction checking through bearing, time interval and course clustering. The clustered AIS messages are then used as an input to a classification algorithm (Random Forest) that provides a different prediction model per cluster.…”

Section: Ships Routes Predictionmentioning

confidence: 99%

See 3 more Smart Citations

Data analysis in the maritime domain

Stróżyna¹,

Abramowicz²,

Węcel³

et al. 2022

View full text Add to dashboard Cite

The book delivers a rich set of foundations, state-of-the-art knowledge, new approaches and methods for the purpose of anomalies detection, maritime traffic analysis as well as risk and reliability assessment. It addresses relevant research problems at the intersection of maritime transport in global economies, reliability and risk assessment, and information systems and data processing. The book provides a theoretical overview of available maritime data sources and approaches for maritime data analysis, as well as a set of novel tools and methods for maritime data retrieval, fusion, and analysis. The proposed methods are evaluated on real-life AIS data, covering the entire world and more than 200 thousands of vessels, illustrating how they may be used for anomaly detection and risk assessment. The primary audience of the book are researchers from the fields of computer science and maritime transport as well as logistics service providers, shipping companies and port authorities companies that need support in managing security, safety, and risk of maritime transport services in global economies by making use of large-scale data processing.

show abstract

Section: Anomalies Detection: Approaches Methodsmentioning

confidence: 99%

Section: Anomalies Detection: Approaches Methodsmentioning

confidence: 99%

Section: Anomalies Detection: Approaches Methodsmentioning

confidence: 99%

Section: Ships Routes Predictionmentioning

confidence: 99%

See 2 more Smart Citations

Data analysis in the maritime domain

Stróżyna¹,

Abramowicz²,

Węcel³

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Rong et al [ 9 ] introduced a data mining method for probabilistic analysis and anomaly detection of maritime behaviors applied to historical data and based on AIS trajectories and associated data on the Portuguese coast. Karatas et al [ 10 ] extended a Traffic Route Extraction for Anomaly Detection (TREAD) algorithm and applied it to the extraction of trajectories and the detection of unusual patterns. Chen et al [ 11 ] proposed a grid generation method that applied the vertical projection distance and a trajectory frequency pattern mining algorithm based on a vague grid sequence.…”

Section: Related Workmentioning

confidence: 99%

A Formal and Visual Data-Mining Model for Complex Ship Behaviors and Patterns

Suo

Zhang

et al. 2022

Sensors

View full text Add to dashboard Cite

The successful emergence of real-time positioning systems in the maritime domain has favored the development of data infrastructures that provide valuable monitoring and decision-aided systems. However, there is still a need for the development of data mining approaches oriented to the detection of specific patterns such as unusual ship behaviors and collision risks. This research introduces a CSBP (complex ship behavioral pattern) mining model aiming at the detection of ship patterns. The modeling approach first integrates ship trajectories from automatic identification system (AIS) historical data, then categorizes different vessels’ navigation behaviors, and introduces a visual-oriented framework to characterize and highlight such patterns. The potential of the model is illustrated by a case study applied to the Jiangsu and Zhejiang waters in China. The results show that the CSBP mining model can highlight complex ships’ behavioral patterns over long periods, thus providing a valuable environment for supporting ship traffic management and preventing maritime accidents.

show abstract