|
Ansaf Salleb and Teddy Turmeaux and Christel Vrain and Cyril Nortet
Mining Quantitative Association Rules in a Atherosclerosis Dataset
, PKDD Discovery Challenge 2004 (co-located with the 6th European Conference
on Principles and Practice of Knowledge Discovery in Databases)
, 98--103
, sep
, 2004
|
|
Abstract
Mining association rules in databases has become a popular task in
data mining. However, most research has focused on
categorical attributes in relational table whereas in practice, this table
contains also numeric attributes. In this paper, we propose to
experiment QuantMiner, a genetic-based algorithm software for mining
quantitative association rules on a atherosclerosis dataset. We give some
experimental results obtained in both the description and the characterization
of this disease.
Keywords : data mining, association rule, numeric attribute, discretization,
categorical attribute, description, discrimination, evolutionary algorithm.
|
|