Abstract
Risk assessment and management of marine disasters are the prerequisite of ocean exploitation and utilization. Marine disaster assessment is a complicated system engineering with high non-linearity and uncertainty. To deal with the problem, Bayesian network (BN) has become a powerful model used for disaster assessment due to its capability of expressing complex relationships and reasoning with uncertainty. However, scarce data sets and case samples of marine disasters pose an obstacle to BN modeling, particularly for structure and parameter learning. In our research, we combine expert knowledge with small sample to propose a new BN-based assessment model. Expert knowledge is regularly expressed and quantitatively incorporated into BN learning with DS evidence theory. Then, the genetic algorithm is adopted to search the optimal network parameters. Comparative experiments show that the new model has a better assessment accuracy (91.03%) than BPNN (61.34%) and SVM (70.67%), especially with small samples. The proposed model achieves the risk assessment of marine disasters under the small sample condition, providing the technical support for marine disaster prevention and mitigation.
Highlights
Based on knowledge constraint and limited data, we introduce DS evidence theory and genetic algorithm for Bayesian network (BN) learning, accomplishing the assessment modeling under the small sample condition
Aiming at parameter learning with a small sample size, we have proposed a GA-based parameter inversion algorithm (GA-conditional probability distribution (CPD)), and the effectiveness of this algorithm has been verified through simulation experiments (Li et al, 2018b)
Our research is focused on the risk assessment of marine disasters, which can provide basis for the development of nature-based solutions, such as hazard prevention and mitigation
Summary
The twenty-first century has been widely recognized as “A Century of Ocean.” Ocean, as the main space of marine development and security strategy, plays a significant role in safeguarding security, enriching resources, and expanding the development space for the economy and society. Step 1: Determine the connection probability distribution based on expert knowledge; Step 2: Build the prior constraint by DS combination rule and new score function; Step 3: Score the initial network structure G0 ≡ old_score; Step 4: Perform arc addition, arc reduction and arc rotation, FIGURE 1 | Knowledge fusion for BN structure learning. Bayesian Network Structure for Marine Disaster Assessment Following the same steps as above, the DS evidence theory is used to fuse the professional knowledge of three experts to obtain the connection probability distribution of the marine disaster network. The error function based on limited sample and expert knowledge is constructed and the genetic algorithm is used to search the optimal network parameters The accuracy of the BN-based assessment model is higher than that of BPNN and SVM, indicating that the proposed model has a better stability
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
