作者: Vili Podgorelec , Peter Kokol , Ivan Rozman
DOI:
关键词:
摘要: The paper presents a hybrid classification method of BNF grammar-based genetic programming and evolutionary decision tree induction, customized for the rule induction according to layered hierarchical scheme - AREX approach. It incorporates two original, independent algorithms which together solve problem automatic rules induction. is applied five real world databases (from medicine software engineering) results are compared those obtained with C5/See5 evaluate method's efficiency. Ideally, this will inspire future research in same area along similar lines.