Spatial Fuzzy Classification In GIS

Spatial objects that are represented in a conventional GIS are generally considered to be crisp and represented by determinate boundaries. When objects change gradually and continuously over space, there are no crisp boundaries to differentiate them. The fuzzy objects, which have indeterminate spatial extent and boundaries, and must be presented accordingly in GIS. Crisp boundaries, specially in spatial objects (e.g. coastal zones )leads to crisp categorizing(categories with sharp boundaries)and exploring patterns is effected by crisp categorization. Using fuzzy operations make resulting patterns more close to real world and mimic it better. Therefore, using fuzzy concepts for data mining and exploring volumeness data warehouse is appropriate. In this article, we introduce a fuzzy approach for the most important task of data mining, called CLASSIFICATION. Algorithms used for this purpose re based on fuzzy set theory. We also applied commonly-used membership functions namely (Semantic Import(SI) and Fuzzy k-means). It is recognized that, compared with conventional crisp-based classification, the application of fuzzy logic to natural phenomena classification is more suitable, sense it mimics real world.