An integrated maritime reasoning and monitoring system

2005

Rule based reasoning and case based reasoning have emerged as two important and complementary reasoning methodologies in artificial intelligence (Al). This paper describes the approach for the development of CORMS AI, a decision support system which employs rule-based and case-based reasoning to assist NOAA's Center for Operational Oceanographic Products and Services watch standing personnel in monitoring the quality of marine environmental data and information.

The detection of anomalies has a critical role in situational assessment. In this paper, we break down the concept of anomaly in the maritime domain into different levels and relate them to the JDL fusion model. We also show how uncertain context knowledge can be encoded through Markov Logic Networks (MLNs) which offer a convenient framework leveraging both the expressive power of first order logic and the probabilistic uncertainty management of Markov networks. Every formula in the knowledge base is assigned a weight indicating its confidence. Different types of knowledge with associated uncertainty can therefore be fused together within MLNs and on-line inference can be performed as input data is processed by the system, and the formulas are grounded in the knowledge base. Promising examples are demonstrated on a sample set of rules for maritime event and anomaly detection.

International Journal of Intelligent Defence Support Systems, 2010

This paper describes a generic decision support architecture (DSA) for supporting maritime operations. The system's core is a decision support tool (DST), consisting of a risk assessment framework aimed at computing risks related to each action that can be performed on the maritime operation under consideration. In particular, the risks are computed for each action and for each class describing the forecasted condition of the environment (favourable, marginal, and unfavourable), according to their posterior probabilities. A fuzzy classifier is used to estimate such probabilities, starting from the forecast of the environmental variables affecting the operation. A distinctive feature of the implemented DSA is its flexibility: many different types of operations can be handled (amphibious landing, autonomous underwater vehicle (AUV) recovery, etc.) with no architectural change. The architecture has been tested both on synthetic data and on real data, the latter collected during two cruises carried out in Adriatic Sea and Ligurian Sea.

In maritime surveillance applications, the aim is to enhance the situation awareness of decision makers located in a central operations centre. Based on the maritime operational picture of the current situation at sea, a decision maker has to decide for specific actions, e.g., for sending out a coast guard boat to counter possible pirate attacks. In order to enable detailed situation awareness in the maritime domain it is necessary to support decision makers with automatic means for in time decisions. Automatic situation assessment (SA) services try to interpret the vessel's behaviour and can be employed as means of enhancing situation awareness. Such SA services have been developed on the basis of an object-oriented world model (OOWM), which is able to fuse object observations from different sensors and to keep the resulting estimated track data in a short-term memory. For enhancing the performance of the SA services, we propose the combination of static context knowledge with ...

2017

In this paper, we discuss a software architecture, which has been developed for the needs of the System for Intelligent Maritime Monitoring (SIMMO). The system bases on the state-of-the-art information fusion and intelligence analysis techniques, which generates an enhanced Recognized Maritime Picture and thus supports situation analysis and decision-making. The SIMMO system aims to automatically fuse an up-to-date maritime data from Automatic Identification System (AIS) and open Internet sources. Based on collected data, data analysis is performed to detect suspicious vessels. Functionality of the system is realized in a number of different modules (web crawlers, data fusion, anomaly detection, visualization modules) that share the AIS and external data stored in the system’s database. The aim of this article is to demonstrate how external information can be leveraged in maritime awareness system and what software solutions are necessary. A working system is presented as a proof of...

Pomorstvo

Most maritime accidents are caused by human error. To reduce these errors, increase safety, protect the marine environment, reduce the administrative burden, and optimize maritime trade, the International Maritime Organization (IMO) decided to implement a concept called e-Navigation. The term e-Navigation refers to the integration of the most modern information and communication systems, both on board and ashore. The research scope of this work is the safety of navigation of the ship during the port entrance. Particularly in this case, the elements that affect the safety of the ship during port entrance are analyzed in a case study of New York port. An adaptive model based on the Bayesian Belief Network (BBN) was created, which evaluates the decision-making elements and risk assessment for port entry. The model is adaptable in the context of the different port requirements. With the presented model, all entities (ships, shipping companies, and service providers) have insight into th...

Information Fusion, 2015

A generative model for modelling maritime vessel behaviour is proposed. The model is a novel variant of the dynamic Bayesian network (DBN). The proposed DBN is in the form of a switching linear dynamic system (SLDS) that has been extended into a larger DBN. The application of synthetic data fabrication of maritime vessel behaviour is considered. Behaviour of various vessels in a maritime piracy situation is simulated. A means to integrate information from context based external factors that influence behaviour is provided. Simulated observations of the vessels kinematic states are generated. The generated data may be used for the purpose of developing and evaluating counter-piracy methods and algorithms. A novel methodology for evaluating and optimising behavioural models such as the proposed model is presented. The log-likelihood, cross entropy, Bayes factor and the Bhattacharyya distance measures are applied for evaluation. The results demonstrate that the generative model is able to model both spatial and temporal datasets.

Situational awareness supports tactical decision making through fusion of information about intelligence, geography, environment, and the geopolitical situation. Advanced decision support systems will provide the decision maker with a number of hypotheses from which the evolving situation may be inferred, limited only by the computational capacity of available computer hardware. Hypothesis Management is needed to control of exponential growth in fusion hypotheses created from incoming data reports delivered by individuals and units connected by a Semantic Services Registry. A Model-Based Systems Engineering Process was applied to design a series of algorithms for a Hypothesis Management Engine that explicitly manage the creation, modification, storage, and filtering of hypotheses. The scenario environment is modeled with the support of a Maritime Domain Ontology, which represents relationships between entities of interest. The effectiveness of the Hypothesis Management Engine is evaluated through simulation of a contextually accurate, randomly generated Hypothesis Knowledge Base which must be updated with incoming track data and queried for inferential reasoning candidates meeting the System Operator's request. This paper summarizes our research results and delineates the planned interaction of the Hypothesis Management Engine with an inferential reasoning system.

Proceeding of the 33rd European Safety and Reliability Conference

The shipping industry increasingly relies on Information Technology (IT) and Operational Technology (OT), which undoubtedly improve operations but also jeopardize vessel safety and security. Risks may arise from vulnerabilities in the design, operation, integration, connection and maintenance of these systems, that external or internal threat agents could exploit. This paper presents a cyber-risk assessment model utilizing Bayesian Networks (BN) for real-time crisis classification of cyber security incidents attributed to detected vulnerabilities in the IT and OT systems on passenger ships. The model is part of a crisis classification module under development for the EU-funded project ISOLA, which visions an intelligent security superintendence ecosystem to enhance the existing ship security processes and the protective measures applied onboard passenger ships. ISOLA's services provide functions for continuous surveillance, including cyber security functions. The BN model receives specific IT and OT vulnerability data generated by a specialized ISOLA service and employs Bayesian probabilistic techniques to evaluate any identified vulnerability. The model performs real-time crisis classification of the cyber security-related incident, utilizing a six-level ascending scale for crisis taxonomy and generates relevant warnings to alert the crew and facilitate early detection of potential or actual safety-and security-threatening occurrences.