Hybrid system with fuzzy hierarchical evaluation model

Abstract

The paper examines a number of models to support decision-making in dynamic situations, which are characterized by poor structuring based on a hybrid system integrating a fuzzy hierarchical evaluation of the model and a fuzzy cognitive situation model. The paper presents a hybrid model based on cognitive maps and hierarchies to support Saati in solutions in dynamic situations and a fuzzy production model for modeling people's irrational behavior in behavioral economics. In creating a model of behavioral decision making, we took into account the modules responsible for the emotions of decision makers and the internal representation of the model. The model uses fuzzy logic and production rules. This approach makes the decision model intuitive due to the language variables that form production rules. Another advantage is the versatility and scalability obtained by switching to models with a large number of parameters. The report presents a model of a modular time series forecasting system. It consists of modules based on modular neural networks, a module that includes a hybrid cognitive hybrid card and a neural-fuzzy ANFIS network and modules for checking and summarizing the results. This article discusses in detail a module that combines a fuzzy cognitive map and a neurally fuzzy network. There is a built neural network and its structure is shown in combination with a blurred cognitive map based on the prognosisof the standard of living indicator