Fuzzy Spatial OQL for Fuzzy Knowledge Discovery in Databases

摘要

In this paper, we introduce a fuzzy spatial object query language, called FuSOQL, to select, process and mine data from Spatial Object-Oriented Databases (SOODB). Fuzzy set theory is introduced in this extension of OQL to handle spatial data. Afterwards, the knowledge discovery process is applied to the selected data. In our case, this data mining is done by means of a fuzzy decision tree based technique. An experiment on a region of France is conducted with this algorithm to discover classification rules related to houses and urban area.