A method for extracting rules from spatial data based on rough fuzzy sets

With the development of data mining and soft computing techniques, it becomes possible to automatically mine knowledge from spatial data. Spatial rule extraction from spatial data with uncertainty is an important issue in spatial data mining. Rough set theory is an effective tool for rule extraction from data with roughness. In our previous studies, Rough set method has been successfully used in the analysis of social and environmental causes of neural tube birth defects. However, both roughness and fuzziness may co-exist in spatial data because of the complexity of the object and the subjective limitation of human knowledge. The situation of fuzzy decisions, which is often encountered in spatial data, is beyond the capability of classical rough set theory. This paper presents a model based on rough fuzzy sets to extract spatial fuzzy decision rules from spatial data that simultaneously have two types of uncertainties, roughness and fuzziness. Fuzzy entropy and fuzzy cross entropy are used to measure accuracies of the fuzzy decisions on unseen objects using the rules extracted. An example of neural tube birth defects is given in this paper. The identification result from rough fuzzy sets based model was compared with those from two classical rule extraction methods and three commonly used fuzzy set based rule extraction models. The comparison results support that the rule extraction model established is effective in dealing with spatial data which have roughness and fuzziness simultaneously.