Abstract | ||
---|---|---|
We consider estimation of relevance of attributes used for classification. This estimation takes into account the predictive capabilities of the attributes. To this end, we are using Bayesian confirmation measure. The estimation is based on analysis of rule classifiers in classification tests. The attribute relevance measure increases when more rules involving this attribute suggest a correct decision, or when more rules that do not invole this attribute suggest an incorrect decision in the classification test; otherwise, the attribute relevance measure is decreasing. This requirement is satisfied by a monotonic Bayesian confirmation measure. Usefulness of the presented measure is verified experimentally. |
Year | DOI | Venue |
---|---|---|
2011 | 10.1007/978-3-642-24425-4_7 | RSKT |
Keywords | Field | DocType |
rule-based estimation,predictive capability,monotonic bayesian confirmation measure,classification test,rule classifier,correct decision,attribute relevance measure increase,incorrect decision,attribute relevance measure,bayesian confirmation measure,classification,decision rule | Decision rule,Monotonic function,Data mining,Rule-based system,Pattern recognition,Computer science,Relevance measure,Artificial intelligence,Machine learning,Bayesian probability | Conference |
Volume | ISSN | Citations |
6954.0 | 0302-9743 | 8 |
PageRank | References | Authors |
0.60 | 12 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jerzy Błaszczyński | 1 | 277 | 13.20 |
Roman Slowinski | 2 | 5561 | 516.06 |
Robert Susmaga | 3 | 370 | 33.32 |