Maritime situation analysis framework: Vessel interaction classification and anomaly detection

Shahir, Hamed Yaghoubi; Glässer, Uwe; Shahir, Amir Yaghoubi; Wehn, Hans

doi:10.1109/bigdata.2015.7363883

Cited by 31 publications

(9 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Handayani and Sediono (2015) used machine learning algorithms called Bayesian networks (BN) for anomaly detection in vessel tracking. Shahir et al (2015) presented a novel approach to anomaly detection by representing patterns (a family of multi-vessel scenarios with common kinematic characteristics) using the left-to-right Hidden Markov Model (HMM) and classifying them using the Support Vector Machine (SVM) model.…”

Section: Maritime Surveillancementioning

confidence: 99%

Big data and artificial intelligence in the maritime industry: a bibliometric review and future research directions

Munim

Dushenko

Jimenez

et al. 2020

Maritime Policy & Management

246

107

View full text Add to dashboard Cite

This study provides a bibliometric review of 279 studies on the applications of big data and artificial intelligence (AI) in the maritime industry, published in 214 academic outlets, authored by 842 scholars. We extracted bibliographical data from the Web of Science database and analysed it using the Bibliometrix tool in R software. Based on citation analysis metrics, we revealed the most influential articles, journals, authors and institutions. Using the bibliographic coupling methodology, we identified four underlying research clusters: (1) digital transformation in maritime industry, (2) applications of big data from AIS, (3) energy efficiency and (4) predictive analytics. We analysed these clusters in detail and extracted future research questions. Besides, we present research collaboration networks on the institution and author level.

show abstract

Section: Maritime Surveillancementioning

confidence: 99%

Big data and artificial intelligence in the maritime industry: a bibliometric review and future research directions

Munim

Dushenko

Jimenez

et al. 2020

Maritime Policy & Management

246

107

View full text Add to dashboard Cite

show abstract

“…A predominant direction in the shipping industry is to focus on the functional development of technological artefacts and its relevance to human cognitive limitations [199][200][201][202][203][204], such as examining the operator's SA performance [205,206] or a usability study in a laboratory environment [207]. Although these constructs are useful to describe the information processing stages and ground design solution based on this "cognitivist approach" [154], they might be incapable of explaining what actually happen in the field.…”

Section: Energy Efficiency Optimisation Onboardmentioning

confidence: 99%

Towards a Pluralistic Epistemology: Understanding Human-Technology Interactions in Shipping from Psychological, Sociological and Ecological Perspectives

Man¹,

Lundh²,

MacKinnon³

2018

TransNav

View full text Add to dashboard Cite

In the shipping domain, many innovative technical systems have been designed and developed in the past decades, aiming to enable the maritime users to achieve the goal of safety, efficiency and effectiveness. The introduction of advanced technologies into workplaces have also created unprecedented challenges. Human users frequently find themselves in a supporting role to serve technology, being responsible for automation issues and blamed for "human errors" that sometimes result in tragic results. These challenges are closely associated with the design and use of technologies. Human-technology interactions has become an important multidisciplinary research topic for shipping. This article reviews theoretical concepts relative to the dimensions of psychology, sociology and ecology in Human Computer Interaction (HCI) in order to form a deeper understanding of human-technology interactions. This paper also discusses the theoretical constructs' practical relevance by showing how a few cases exemplifying ongoing development sectors in shipping, such as energy efficiency optimisation, supervisory control of autonomous unmanned ships, and ecosystems in engine control rooms, are understood with these theoretical perspectives. By presenting multidisciplinary understandings of human-technology interaction, this paper aims to derive knowledge pertinent to methodological approaches and philosophical stances of future maritime human factors and HCI research. http://www.transnav.eu the International Journal on Marine Navigation and Safety of Sea Transportation Volume 12 Number 4

show abstract

“…Recently, only limited effort has been devoted to the use of hybrid approaches for anomalous maritime vessel behaviour detection. Shahir et al (2014; 2015) combined data-driven machine learning methods with maritime background domain knowledge to detect anomalous vessel interaction patterns. In Kazemi et al (2013) a hybrid framework for anomaly detection based on the use of open data (contextual information and background knowledge) is proposed.…”

Section: Review Of Recent Research Work On Automatic Anomalous Maritmentioning

confidence: 99%

Study of Automatic Anomalous Behaviour Detection Techniques for Maritime Vessels

Sidibé

Gao

2017

J. Navigation

View full text Add to dashboard Cite

The maritime domain is the most utilised environment for bulk transportation, making maritime safety and security an important concern. A major aspect of maritime safety and security is maritime situational awareness. To achieve effective maritime situational awareness, recently many efforts have been made in automatic anomalous maritime vessel movement behaviour detection based on movement data provided by the Automatic Identification System (AIS). In this paper we present a review of state-of-the-art automatic anomalous maritime vessel behaviour detection techniques based on AIS movement data. First, we categorise some approaches proposed in the period 2011 to 2016 to automatically detect anomalous maritime vessel behaviour into distinct categories including statistical, machine learning and data mining, and provide an overview of them. Then we discuss some issues related to the proposed approaches and identify the trend in automatic detection of anomalous maritime vessel behaviour.

show abstract

Maritime situation analysis framework: Vessel interaction classification and anomaly detection

Cited by 31 publications

References 17 publications

Big data and artificial intelligence in the maritime industry: a bibliometric review and future research directions

Big data and artificial intelligence in the maritime industry: a bibliometric review and future research directions

Towards a Pluralistic Epistemology: Understanding Human-Technology Interactions in Shipping from Psychological, Sociological and Ecological Perspectives

Study of Automatic Anomalous Behaviour Detection Techniques for Maritime Vessels

Contact Info

Product

Resources

About