In this paper we propose a novel (multi-)relational classification framework based on propositionalization. Propositionalization makes use of discovered relational association rules and permits to significantly reduce feature space through a feature reduction algorithm. The method is implemented in a Data Mining system tightly integrated with a relational database. It performs the classification at different granularity levels and takes advantage from domain specific knowledge in form of rules that support qualitative reasoning. An application of classification in real-world georeferenced census data analysis is reported.
Propositionalization Through Relational Association Rules Mining
CECI, MICHELANGELO;APPICE, ANNALISA;MALERBA, Donato
2005-01-01
Abstract
In this paper we propose a novel (multi-)relational classification framework based on propositionalization. Propositionalization makes use of discovered relational association rules and permits to significantly reduce feature space through a feature reduction algorithm. The method is implemented in a Data Mining system tightly integrated with a relational database. It performs the classification at different granularity levels and takes advantage from domain specific knowledge in form of rules that support qualitative reasoning. An application of classification in real-world georeferenced census data analysis is reported.File in questo prodotto:
Non ci sono file associati a questo prodotto.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.