Linear classifier combination via multiple potential functions

作者：

Highlights：

• We propose anew approach to calculate a scoring function dedicated to linear base classifiers.

• The method is based on the distance of the object from the decision boundary and the distance to the class centroids.

• The proposed scoring function has the same nature for all base classifiers.

• The method is tested on several data sets and compared to reference methods.

摘要

•We propose anew approach to calculate a scoring function dedicated to linear base classifiers.•The method is based on the distance of the object from the decision boundary and the distance to the class centroids.•The proposed scoring function has the same nature for all base classifiers.•The method is tested on several data sets and compared to reference methods.

论文关键词：Linear classifier,Potential function,Ensemble of classifiers,Score function

论文评审过程：Received 12 December 2019, Revised 31 August 2020, Accepted 23 September 2020, Available online 28 September 2020, Version of Record 5 October 2020.

论文官网地址：https://doi.org/10.1016/j.patcog.2020.107681