Online pruning of base classifiers for Dynamic Ensemble Selection

作者：

Highlights：

• We propose a novel dynamic ensemble selection framework.

• The framework selects classifiers with decision boundaries crossing the local region.

• Results demonstrate the proposed framework outperform current techniques.

摘要

•We propose a novel dynamic ensemble selection framework.•The framework selects classifiers with decision boundaries crossing the local region.•Results demonstrate the proposed framework outperform current techniques.

论文关键词：Ensemble of classifiers,Dynamic ensemble selection,Classifier competence

论文评审过程：Received 4 December 2016, Revised 1 May 2017, Accepted 25 June 2017, Available online 28 June 2017, Version of Record 7 July 2017.

论文官网地址：https://doi.org/10.1016/j.patcog.2017.06.030