A contextual fuzzy cognitive map framework for geographic information systems

Designing a system that is able to make use of quantitative and qualitative data for real world applications is a challenging problem. Traditional systems produce representational descriptions that are often not very useful to the human expert. To rectify this problem we propose a structure based on contextual fuzzy cognitive maps (CFCMs) for geographic information systems (GISs). Our framework builds this structure using both spatial and temporal information to gain quantitative and qualitative descriptions. In addition, these cognitive maps are able to provide generalized descriptions that reflect relationships between landmarks. Such a scheme is capable of producing cognitive descriptions similar to those a human expert might derive and use. In the paper, we illustrate the types of CFCMs we can generate using real census data, human expert knowledge, and quantitative data in the form of maps in a GIS. For a given goal, our system structure is hierarchical by context, multilayered by variations in data over periods of time, and semi-qualitative in that the CFCMs build causal links and relationships between landmarks and concepts