Dynamic critical factors identification: A novel fuzzy DEMATEL method considering heterogeneous information

Identifying the critical factors and their interrelationships plays a critical role in system analysis. Fuzzy DEMATEL method is one of the popular techniques widely applied to identify the critical factors and analyze the interrelationship among them under fuzzy and uncertain environment. Different information types are often used to describe given problems in the real world, similar to how experts express their assessments due to their diverse knowledge backgrounds or individual preferences. However, in existing fuzzy DEMATEL studies, experts are allowed to use only a single information type to express their assessments, which cannot reflect the real-world situations. Additionally, dynamic evolution is atypical feature of practical problems. Factors associated with these problems, including critical factors, might change and update alongside this dynamic evolution. Nevertheless, such dynamic evolution has not been considered in existing fuzzy DEMATEL studies. To address the issues of heterogeneous information and dynamic evolution, this study proposes a novel method based on fuzzy DEMATEL that considers both dynamic evolution and heterogeneous information. The dynamic evolution is described not only from the perspective of time changes, but also information updates. The heterogeneous information includes numerical values, interval values, linguistic information, and hesitant fuzzy linguistic term information. The proposed method consists of five parts including problem definition, information gathering, information transformation, information aggregation, and dynamic critical factors identification. A reasonable way based on alpha-level sets is employed to handle the aggregated fuzzy information, and dynamic degrees of different factors at each moment are calculated for critical factors identification. A numerical example, related discussions, and comparison analysis are provided to demonstrate the novelty and superiority of the proposed method.