Improving a dynamic ensemble selection method based on oracle information

Improving a dynamic ensemble selection method based on oracle information

Vriesmann, Leila Maria and De Souza Britto, Alceu and De Oliveira, Luiz Eduardo Soares and Sabourin, Robert and Ko, Albert Houng Ren

International Journal of Innovative Computing and Applications 2012

Abstract : This work evaluates some strategies to approximate the performance of a dynamic ensemble selection method to the oracle performance of its pool of weak classifiers. For this purpose, we evaluated different distance metrics in the K-nearest-oracles (KNORA) method, the use of statistics related to the class accuracy of each classifier in the pool and some additional information calculated by using a clustering process in the validation dataset. Moreover, different strategies are also evaluated to combine the results of the KNORA dynamic ensemble selection method with the results of its built-in K-nearest neighbour (KNN) used to define the neighbourhood of a test pattern during the ensemble creation. A strong experimental protocol based on more than 60,000 samples of handwriting digits extracted from NIST-SD19 was used to evaluate each strategy. The experiments have shown that the fusion of the KNORA results with the results of its built-in KNN is a very promising strategy. Copyright © 2012 Inderscience Enterprises Ltd.