A Generalised Bayesian Inference Method for Maritime Surveillance Using Historical Data
In practice, maritime monitoring systems rely on manual work to identify the authenticities, risks, behaviours and importance of moving objects, which cannot be obtained directly through sensors, especially from marine radar. This paper proposes a generalised Bayesian inference-based artificial inte...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2019-02-01
|
Series: | Symmetry |
Subjects: | |
Online Access: | https://www.mdpi.com/2073-8994/11/2/188 |
_version_ | 1798038826262724608 |
---|---|
author | Jia Li Xiumin Chu Wei He Feng Ma Reza Malekian Zhixiong Li |
author_facet | Jia Li Xiumin Chu Wei He Feng Ma Reza Malekian Zhixiong Li |
author_sort | Jia Li |
collection | DOAJ |
description | In practice, maritime monitoring systems rely on manual work to identify the authenticities, risks, behaviours and importance of moving objects, which cannot be obtained directly through sensors, especially from marine radar. This paper proposes a generalised Bayesian inference-based artificial intelligence that is capable of identifying these patterns of moving objects based on their dynamic attributes and historical data. First of all, based on dependable prior data, likelihood information about objects of interest is obtained in terms of dynamic attributes, such as speed, direction and position. Observations on these attributes of a new object can be obtained as pieces of evidence profiled as probability distributions or generally belief distributions if ambiguity appears in the observations. Using likelihood modelling, the observed pieces of evidence are independent of the prior distribution patterns. Subsequently, Dempster’s rule is used to combine the pieces of evidence under consideration of their weight and reliability to identify the moving object. A real world case study of maritime radar surveillance is conducted to validate and prove the efficiency of the proposed approach. Overall, this approach is capable of providing a probabilistic and rigorous recognition result for pattern recognition of moving objects, which is suitable for any other actively detecting applications in transportation systems. |
first_indexed | 2024-04-11T21:45:40Z |
format | Article |
id | doaj.art-1f9b65ec39bd496589b6c90701cc5845 |
institution | Directory Open Access Journal |
issn | 2073-8994 |
language | English |
last_indexed | 2024-04-11T21:45:40Z |
publishDate | 2019-02-01 |
publisher | MDPI AG |
record_format | Article |
series | Symmetry |
spelling | doaj.art-1f9b65ec39bd496589b6c90701cc58452022-12-22T04:01:26ZengMDPI AGSymmetry2073-89942019-02-0111218810.3390/sym11020188sym11020188A Generalised Bayesian Inference Method for Maritime Surveillance Using Historical DataJia Li0Xiumin Chu1Wei He2Feng Ma3Reza Malekian4Zhixiong Li5Intelligent Transport System Research Center, Wuhan University of Technology, Wuhan 430068, ChinaIntelligent Transport System Research Center, Wuhan University of Technology, Wuhan 430068, ChinaCollege of Marine Sciences, Minjiang University, Fuzhou 350108, ChinaIntelligent Transport System Research Center, Wuhan University of Technology, Wuhan 430068, ChinaDepartment of Electrical, Electronic & Computer Engineering, University of Pretoria, Pretoria 0002, South AfricaSchool of Mechanical, Materials, Mechatronic and Biomedical Engineering, University of Wollongong, Wollongong, NSW 2522, AustraliaIn practice, maritime monitoring systems rely on manual work to identify the authenticities, risks, behaviours and importance of moving objects, which cannot be obtained directly through sensors, especially from marine radar. This paper proposes a generalised Bayesian inference-based artificial intelligence that is capable of identifying these patterns of moving objects based on their dynamic attributes and historical data. First of all, based on dependable prior data, likelihood information about objects of interest is obtained in terms of dynamic attributes, such as speed, direction and position. Observations on these attributes of a new object can be obtained as pieces of evidence profiled as probability distributions or generally belief distributions if ambiguity appears in the observations. Using likelihood modelling, the observed pieces of evidence are independent of the prior distribution patterns. Subsequently, Dempster’s rule is used to combine the pieces of evidence under consideration of their weight and reliability to identify the moving object. A real world case study of maritime radar surveillance is conducted to validate and prove the efficiency of the proposed approach. Overall, this approach is capable of providing a probabilistic and rigorous recognition result for pattern recognition of moving objects, which is suitable for any other actively detecting applications in transportation systems.https://www.mdpi.com/2073-8994/11/2/188Dempster’s ruleevidence distancepattern recognitionmaritime surveillance |
spellingShingle | Jia Li Xiumin Chu Wei He Feng Ma Reza Malekian Zhixiong Li A Generalised Bayesian Inference Method for Maritime Surveillance Using Historical Data Symmetry Dempster’s rule evidence distance pattern recognition maritime surveillance |
title | A Generalised Bayesian Inference Method for Maritime Surveillance Using Historical Data |
title_full | A Generalised Bayesian Inference Method for Maritime Surveillance Using Historical Data |
title_fullStr | A Generalised Bayesian Inference Method for Maritime Surveillance Using Historical Data |
title_full_unstemmed | A Generalised Bayesian Inference Method for Maritime Surveillance Using Historical Data |
title_short | A Generalised Bayesian Inference Method for Maritime Surveillance Using Historical Data |
title_sort | generalised bayesian inference method for maritime surveillance using historical data |
topic | Dempster’s rule evidence distance pattern recognition maritime surveillance |
url | https://www.mdpi.com/2073-8994/11/2/188 |
work_keys_str_mv | AT jiali ageneralisedbayesianinferencemethodformaritimesurveillanceusinghistoricaldata AT xiuminchu ageneralisedbayesianinferencemethodformaritimesurveillanceusinghistoricaldata AT weihe ageneralisedbayesianinferencemethodformaritimesurveillanceusinghistoricaldata AT fengma ageneralisedbayesianinferencemethodformaritimesurveillanceusinghistoricaldata AT rezamalekian ageneralisedbayesianinferencemethodformaritimesurveillanceusinghistoricaldata AT zhixiongli ageneralisedbayesianinferencemethodformaritimesurveillanceusinghistoricaldata AT jiali generalisedbayesianinferencemethodformaritimesurveillanceusinghistoricaldata AT xiuminchu generalisedbayesianinferencemethodformaritimesurveillanceusinghistoricaldata AT weihe generalisedbayesianinferencemethodformaritimesurveillanceusinghistoricaldata AT fengma generalisedbayesianinferencemethodformaritimesurveillanceusinghistoricaldata AT rezamalekian generalisedbayesianinferencemethodformaritimesurveillanceusinghistoricaldata AT zhixiongli generalisedbayesianinferencemethodformaritimesurveillanceusinghistoricaldata |