A Mutual Information-Based Bayesian Network Model for Consequence Estimation of Navigational Accidents in the Yangtze River

2019 ◽  
Vol 73 (3) ◽  
pp. 559-580 ◽  
Author(s):  
Bing Wu ◽  
Tsz Leung Yip ◽  
Xinping Yan ◽  
Zhe Mao

Navigational accidents (collisions and groundings) account for approximately 85% of mari-time accidents, and consequence estimation for such accidents is essential for both emergency resource allocation when such accidents occur and for risk management in the framework of a formal safety assessment. As the traditional Bayesian network requires expert judgement to develop the graphical structure, this paper proposes a mutual information-based Bayesian network method to reduce the requirement for expert judgements. The central premise of the proposed Bayesian network method involves calculating mutual information to obtain the quantitative element among multiple influencing factors. Seven-hundred and ninety-seven historical navigational accident records from 2006 to 2013 were used to validate the methodology. It is anticipated the model will provide a practical and reasonable method for consequence estimation of navigational accidents.

2013 ◽  
Vol 380-384 ◽  
pp. 4751-4756
Author(s):  
Ling Sun ◽  
Ze Sheng Zhu

This paper discuses a Bayesian-network method for building an aeration management model for high performance management of stored grain. This model is designed and implemented with a dividing-layer architecture, which is used to complete aeration management of a number of stored grain warehouses in order to increase stored grain safety and to decrease stored grain management cost.


2021 ◽  
Vol 13 (14) ◽  
pp. 7951
Author(s):  
Yuhong H. Cao ◽  
Jianxin X. You ◽  
Yongjiang J. Shi ◽  
Wei Hu

Through the establishment of a comprehensive evaluation index system, this paper analyzes the allocation of science and technology resources in the Yangtze River Delta urban agglomeration from 2014 to 2020, evaluates the allocation efficiency of science and technology resources from the perspective of multi input and output, and understands the advantages and disadvantages of regional resource allocation. The research results show that: (1) under the guidance of the national strategic policy of actively promoting the development of world-class urban agglomerations, the allocation efficiency of science and technology resources in various provinces and cities of the Yangtze River Delta continues to optimize, and the allocation level of some regions shows a rapid development trend; (2) R&D personnel and R&D funds are the core factors that affect the efficiency of science and technology resource allocation; (3) the marketization of resource allocation is helpful to improve its allocation efficiency; and (4) improving the transformation rate of scientific and technological achievements, opening up the channel for innovative products, technologies, and services to enter the market, and enabling innovative enterprises to make profits can provide strong and lasting incentives for the improvement of scientific and technological resource allocation efficiency. Based on the research conclusions, this paper puts forward countermeasures and suggestions to improve the allocation efficiency of scientific and technological resources in the Yangtze River Delta urban agglomeration from the aspects of human resources and material resources, and provides a theoretical reference for the coordinated and sustainable development of the Yangtze River Delta City Group under the background of the implementation of the urban agglomeration strategy and the construction of a scientific and technological infrastructure platform.


Author(s):  
Haoran Liu ◽  
Jean-Christophe Buvat ◽  
Lionel Estel ◽  
Isabelle Polaert

The aim is this paper is to study fault diagnosis in a continuous chemical process. An experimental system is built to be the research base and a model is proposed and trained to carry out the fault diagnosis in the process. A Bayesian network model with two-layer nodes structure is designed and Maximum likelihood estimation (MLE) is used to amend the conditional probability table (CPT) given by expert knowledge. Then a Monte Carlo method is applied to simplify the inference rules and the data samples collected from the experimental system has been used to test the model.


Author(s):  
Di Zhang ◽  
Xinping Yan ◽  
Zaili Yang ◽  
Jin Wang

Formal safety assessment (FSA), as a structured and systematic risk evaluation methodology, has been gradually and broadly used in the shipping industry nowadays around the world. Concerns have been raised to navigational safety of Yangtze River, known as China’s largest and the world busiest inland waterway. With the national development of the Middle and Western parts of China, the throughput and the passing ships in Yangtze River have been rapidly increasing during the past few decades. Meanwhile, accidents such as collisions, groundings, overturns, oil-spills and fires occur repeatedly, causing serious consequences. In view of this, attempts made in this paper are to evaluate the navigational risk of Yangtze River using the FSA concept and a Bayesian Network (BN) technique, so as to enhance the navigational safety in Yangtze River.


Sign in / Sign up

Export Citation Format

Share Document