"Criteria Ensembles in Feature Selection"@en . . . "3"^^ . . . "Criteria Ensembles in Feature Selection"@en . "Somol, Petr" . "P(1M0572), P(2C06019), P(GA102/08/0593), Z(AV0Z10750506)" . "2009-06-10+02:00"^^ . . "Springer-Verlag" . . "In feature selection the effect of over-fitting may lead to serious degradation of generalization ability. We introduce the concept of combining multiple feature selection criteria in feature selection methods with the aim to obtain feature subsets that generalize better. The concept is applicable with many existing feature selection methods. Here we discuss in more detail the family of sequential search methods. The concept does not specify which criteria to combine \u2013 to illustrate its feasibility we give a simple example of combining the estimated accuracy of k-nearest neighbor classifiers for various k.We perform the experiments on a number of datasets. The potential to improve is clearly seen on improved classifier performance on independent test data as well as on improved feature selection stability." . "Criteria Ensembles in Feature Selection" . "3"^^ . . "RIV/67985556:_____/09:00326643" . "Pudil, Pavel" . "Criteria Ensembles in Feature Selection" . . . . "feature selection; criterion; ensemble; combining criteria"@en . "Berlin Heidelberg" . . . "[B24DD5157524]" . "10"^^ . "RIV/67985556:_____/09:00326643!RIV10-MSM-67985556" . . "Reykjavik" . . . "3-642-02325-8" . "In feature selection the effect of over-fitting may lead to serious degradation of generalization ability. We introduce the concept of combining multiple feature selection criteria in feature selection methods with the aim to obtain feature subsets that generalize better. The concept is applicable with many existing feature selection methods. Here we discuss in more detail the family of sequential search methods. The concept does not specify which criteria to combine \u2013 to illustrate its feasibility we give a simple example of combining the estimated accuracy of k-nearest neighbor classifiers for various k.We perform the experiments on a number of datasets. The potential to improve is clearly seen on improved classifier performance on independent test data as well as on improved feature selection stability."@en . . . . . "Multiple Classifier Systems, LNCS 5519" . . "308547" . "Grim, Ji\u0159\u00ED" . . . .