Research on attribute-oriented induction based on quantitative extended concept lattice and multi-granule association rule mining
Xiaoping Liu · Journal of systems engineering · 2009
High-level,more generational and reductive information is getting more interesting for users in KDD.Attribute-oriented Induction(AOI) has been already primarily used in data reduction,which generally takes the statistical information from original data into account.However,attribute-oriented induction based on quantitative extended concept lattice not only performs the task of AOI,but also carries out the generalization with multi-level and multi-attribute,while the generalization paths are not one and only.Finally,the proper generalization paths and thresholds on the Hasse diagram of quantitative extended concept lattice can be found,the required reasonable results can be easily gotten,moreover,multi-granule association rules with multi-level and multi-attribute are mined,different granule knowledge can be easily focused,and the relationships of transforms between different granule knowledge are discovered rapidly.