A dual linguistic scale-based digitization and exploitation method for scrap steel remanufacturing process selection. (April 2021)

• Record Type: Journal Article
• Authors: Wu, Xingli; Liao, Huchang
• Is Part Of: Engineering applications of artificial intelligence. Volume 100(2021)
• Publication Date: 2021-04
• Subjects: Multiple criteria decision making -- Dual linguistic scale -- Linguistic scale function -- Personalized semantics -- Scrap steel remanufacturing; Engineering -- Data processing -- Periodicals; Artificial intelligence -- Periodicals; Expert systems (Computer science) -- Periodicals; Ingénierie -- Informatique -- Périodiques; Intelligence artificielle -- Périodiques; Systèmes experts (Informatique) -- Périodiques; Artificial intelligence; Engineering -- Data processing; Expert systems (Computer science); Periodicals; 620.00285
• DOI: 10.1016/j.engappai.2021.104169
• Languages: English
• ISSNs: 0952-1976

Abstract

Abstract: Language is a preferred way for evaluators to express their opinions. As an important part of qualitative decision making, computing with words mainly focuses on transferring linguistic information to numerical values for operations. A significant challenge is how to model the meaning of linguistic information given by evaluators. This study aims to explore the principle of an evaluator to judge alternatives over different kinds of criteria and establish linguistic scale functions to simulate the personalized semantics of linguistic terms. In addition a dual linguistic scale in the form of linguistic terms and numerical meanings is developed to represent decision information. We then develop a method called the dual linguistic scale-based digitization and exploitation method to deduce the ranking of alternatives for multiple criteria decision-making problems, which considers the personalized cognition of evaluators and the personalized requirements of decision-makers for the trade-offs between criteria A case study concerning the scrap steel remanufacturing is conducted to demonstrate the validity of the proposed method. The results demonstrate that linguistic computational models have an influence on the ranking results of alternatives.