A circular intuitionistic fuzzy evaluation method based on distances from the average solution to support multiple criteria intelligent decisions involving uncertainty. (January 2023)

• Record Type: Journal Article
• Authors: Chen, Ting-Yu
• Is Part Of: Engineering applications of artificial intelligence. Volume 117:Part A(2023)
• Publication Date: 2023-01
• Subjects: Evaluation method based on distances from the average solution (EDAS) -- Circular intuitionistic fuzzy (C-IF) set -- Anchored datum-based measurement -- Site selection -- Multiple criteria decision analysis; 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.2022.105499
• Languages: English
• ISSNs: 0952-1976

Abstract

Abstract: This study aims to construct an evaluation method based on distances from the average solution (EDAS) based on circular intuitionistic fuzzy (C-IF) sets to support intelligent decision-making involving multiple criteria and intricate uncertainty. C-IF sets possess a resilient circular structure that can model decision-makers' hesitancy and indecision like intuitionistic fuzzy sets and can add ambiguity to fuzzy membership and nonmembership functions like type-2 fuzzy sets. Related to the existing literature on EDAS in uncertain environments, a new interpretation is needed so that the decision assistance procedure can exploit higher-order fuzzy membership functions as well as in type-2 fuzzy settings, and can address decision hesitancy as well as in IF settings. However, EDAS has not been studied to discuss its applicability in C-IF circumstances and make headway a suitable extension model, which forms a research question worth exploring. To address this issue, this study endeavors to construct a C-IF EDAS methodology and propound novel concepts and measurements that can improve the core techniques of traditional EDAS, enabling them to handle complicated C-IF information and treat highly equivocal and indistinct decision-making tasks. The C-IF analytical procedure for decision-making is mainly built upon two representations from semantic assessments, namely C-IF assessment ratings and C-IF importance weights. This study puts forth the concept of aggressive and conservative estimates to identify anchored datum-based measurements that provide new interpretations of positive distance and negative distance concerning the C-IF average solution; besides this study evolves an extended EDAS decision rule in C-IF circumstances. Based on an aggregated operation and a membership score function, anchored datum-based (normalized) weighted sums about positive/negative distances can be rendered to produce a joint appraisal score for a compromise ranking of available alternatives. To corroborate the applicability of the established notions and measurements, this study utilizes the C-IF EDAS model and decision procedure to tackle a realistic site selection issue for a pandemic hospital within C-IF environments. The suitability, robustness, and flexibility of the developed C-IF EDAS methodology are confirmed through some comparative analyses and experimental studies. First, this study verifies the correctness and trustworthiness of the executive outcomes from the viewpoints of membership, nonmembership, and vague score functions. Next, this study confirms the effectuality and rationality of the proposed C-IF EDAS by comprehensive comparison with several related methods. Furthermore, this study suggests a flexible way of setting appraisal and distance parameters in the C-IF EDAS to facilitate intelligent decision-making in reality. Finally, some conclusive discussions of the C-IF EDAS solution are systematically investigated to reveal its practicality and application merits in the realm of multiple criteria decision analysis with information uncertainty; it is also confirmed that the C-IF set is well suited as a fundamental of problem modeling within complex decision-making environments. Highlights: Enrich the evaluation method based on distances from the average solution (EDAS). Construct circular intuitionistic fuzzy (C-IF) EDAS methodology under uncertainty. Derive aggressive and conservative estimates for anchored datum-based measurements. Exploit the C-IF EDAS method to address the siting problem of a pandemic hospital. Comparative analysis and experimental study to show the advantages of C-IF EDAS.