Abstract
The application of Bayesian network (BN) theory in risk assessment is an emerging trend. But in cases where data are incomplete and variables are mutually related, its application is restricted. To overcome these problems, an improved BN assessment model with parameter retrieval and decorrelation ability is proposed. First, multivariate nonlinear planning is applied to the feedback error learning of parameters. A genetic algorithm is used to learn the probability distribution of nodes that lack quantitative data. Then, based on an improved grey relational analysis that considers the correlation of variation rate, the optimal weight that characterizes the correlation is calculated and the weighted BN is improved for decorrelation. An improved risk assessment model based on the weighted BN then is built. An assessment of sea ice disaster shows that the model can be applied for risk assessment with incomplete data and variable correlation.
Highlights
Risk is the consequence of interactions between risk factors and risk-bearing objects (Grandell 1991) in a multidimensional and multilayered system
Based on an improved grey relational analysis that considers the correlation of variation rate, the optimal weight that characterizes the correlation is calculated and the weighted Bayesian network (BN) is improved for decorrelation
The probabilistic reasoning technique of BN can effectively achieve the fusion of uncertain information, which is vital for risk assessment
Summary
Risk is the consequence of interactions between risk factors and risk-bearing objects (Grandell 1991) in a multidimensional and multilayered system. Neither weight calculation in AHP nor affiliation determination in FCA takes advantage of objective data, indicating a relatively strong subjectivity and low credibility in assessment These methods have defects in describing nonlinear interactions between risk factors. Fuzzy mathematics theory (Zhang 2015), object-oriented analysis (Wang 2016), weight fusion (Liu 2016), and geographic information science (Gret-Regamey and Straub 2006) were introduced. These fields of study extract quantitative data from the original information and determine the structure and parameters automatically by intelligent algorithms. The model makes an attempt to break through the restrictions of BN and promote its application to risk assessment
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have