Detailing fuzzy cognitive map models through clustering and nesting for complex concepts

Analyzing complex information models, constructed from any collected data, is a challenging task. In recent years, new methodologies have emerged and been proposed to address various problems in this field. However, there is still a need for new, efficient, and user-friendly methods for data presentation and information modeling. This paper proposes a method for creating a nested structure based on fuzzy cognitive maps. In this method, each concept can be represented as another fuzzy cognitive map through clustering, which provides a more detailed and accurate representation of complex data and increases the convenience and efficiency of analyzing such information models. This nested structure is then optimized by applying evolutionary learning algorithms. Through a dynamic optimization process, the entire nested structure based on fuzzy cognitive maps is restructured to obtain important relationships between map elements at each level of nesting, as well as to determine the weight coefficients of these relationships based on available time series. This process allows for the discovery of hidden relationships between important map elements. The article proposes the application of this nested approach using the example of a fuzzy cognitive map of the influence of various social factors on becoming homeless.