MISO intuitionistic fuzzy inference system
Fuzzy Inference Systems (FIS) are widely used for decision-making through imprecise relation defined on qualitative imprecise inputs and outputs based on expert’s knowledge via fuzzy numbers. Even the fuzzy relation is based on the expert’s knowledge, it is not accounted with the expert’s lack of co...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Ayandegan Institute of Higher Education,
2025-03-01
|
| Series: | Journal of Fuzzy Extension and Applications |
| Subjects: | |
| Online Access: | https://www.journal-fea.com/article_209458_2bb3dfe0c880b620da3439bda7358f98.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Fuzzy Inference Systems (FIS) are widely used for decision-making through imprecise relation defined on qualitative imprecise inputs and outputs based on expert’s knowledge via fuzzy numbers. Even the fuzzy relation is based on the expert’s knowledge, it is not accounted with the expert’s lack of confidence / hesitancy, if any, involved in the relation between qualitative imprecise inputs and outputs because of their imprecise / fuzzy in nature. This research introduces an enhanced Intuitionistic Fuzzy Inference System (IFIS) to overcome the limitations of conventional Fuzzy Inference Systems (FIS) in handling imprecise, incomplete, and uncertain expert’s data by considering expert’s hesitancy / lack of knowledge in domain. IFIS extends traditional fuzzy models by incorporating intuitionistic fuzzification, intuitionistic IF-THEN implications, and intuitionistic defuzzification, all of which account for expert’s hesitation / lack of confidence if any due to lack of knowledge through an α - level hesitancy parameter. A Multi-Input Single-Output (MISO) intuitionistic fuzzy system is developed as a generalization of the Single-Input Single-Output (SISO) model. To demonstrate the utility of this approach, the study applies a trapezoidal intuitionistic fuzzy inference system (TIFIS) to model COVID-19 risk, assuming expert data may exhibit varying degrees of confidence. This novel framework significantly enhances decision-making processes in complex, uncertain environments, offering a robust alternative to existing FIS models. |
|---|---|
| ISSN: | 2783-1442 2717-3453 |