Abstract

Precision in the real world is covered by imprecision and arithmetic operations serve as the foundations of computation. Since the introduction of Fuzzy Cognitive mapping, the dynamic model used to establish the fuzzy cognitive map, used conventional arithmetic operations on asymmetric fuzzy sets.Therefore, for a cognitive map, to be completely fuzzy, it should incorporate the use of fuzzy arithmetic and fuzzy numbers in describing the concept nodes and the cause-effect lines defining its structure. It then can be stated that the necessary and sufficient condition for a cognitive map to be fully fuzzy is that its dynamic activity or operation, be achieved only through fuzzy mathematics.This paper presents an introductory analysis into the peculiar design of the fully fuzzy structure of the cognitive map.

Highlights

  • Today, the Fuzzy Cognitive Map (FCM) is an important computational intelligence approach to the classification, prediction, and monitoring of the behavior of complex systems [1]

  • Normalize the defuzzyfied ith concept value at time, t+1 End Loop End Loop End The structure of this type of fully fuzzy cognitive map may seem easy and intuitive to implement, but, as stated in [1], [9], [15], the mathematical operations described by the fuzzy dynamic equation present some difficulties in terms of uncertainty expansion arising during fuzzy calculations

  • The fuzzy cognitive map model basically reveals the dynamic influence of change in selected concepts on other concepts

Read more

Summary

INTRODUCTION

The Fuzzy Cognitive Map (FCM) is an important computational intelligence approach to the classification, prediction, and monitoring of the behavior of complex systems [1]. The first automated variant of the FFCM is the relational fuzzy cognitive map (RFCM), an automated approach that uses the arithmetic and algebra of fuzzy numbers for creating and optimizing the structure of fuzzy cognitive maps, as fully described by Slon in [1]. This fully fuzzy automated approach bypasses the use of rule-bases and rigidly defined linguistic values, with abstract numbers, which can be changed, depending on the speed or accuracy needs of a model

Structure of the FFCM
Parametric Identification of the FFCM
MODELING COMPLEX SYSTEMS AND MACHINES
Selected Applications
Hypothetical model Application
PROCESS CONTROL AND SUPERVISOR APPLICATION
Heat Exchanger Control Model
Supervisor Model
Findings
CONCLUSIONS AND FUTURE WORKS
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call