A Dynamic Weight Determination Approach Based on the Intuitionistic Fuzzy Bayesian Network and Its Application to Emergency Decision Making

This work develops an intuitionistic fuzzy Bayesian network to obtain the practical attribute weights under uncertain environment and develops a dynamic decision making approach integrating the prospect theory to solve the risk decision making problems.

Abstract

The weight information has been playing a key role in information fusion and dynamic decision making process. Most existing methods for determining weights under dynamic environments only derive the period weights by using the distribution functions of time series, but there is little investigation of the determination of dynamic attribute weights over time. To solve this issue, we first develop an intuitionistic fuzzy Bayesian network to obtain the practical attribute weights under uncertain environment. Then, we propose a conceptual framework for dynamic intuitionistic fuzzy decision making, and based on which, we develop a dynamic decision making approach integrating the prospect theory to solve the risk decision making problems. Furthermore, a case study involving the mine emergency decision making problem is presented to illustrate the application of our approach. Finally, we discuss the characteristics and limitations of our approach in detail.