Apriori-based Rule Generation with Three-way Decisions for Heterogeneous and Uncertain Data

The framework of rule generation from table data sets is extended to that from several types of data, like heterogeneous and uncertain data. Some proper implications from tables (or information systems) are considered rules in rough set-based rule generation. We newly define granulated information systems for handling several types of data and propose a unified framework of rule generation. This unified framework can be a representative framework for rule generation from several data types. Some actual examples of the implemented software tool are also presented.