Class label altering fuzzy min-max network and its application to histopathology image database

作者：

Highlights：

• CLAFMM, to alter the class label depending on a secondary training set, is proposed.

• CLAFMM is compared with FMM, EFMM and Kn-FMM networks for different databases.

• CLAFMM reduces the number of generated hyperboxes and increases the accuracy rate.

• CLAFMM is applied to histopathology image database to find the best magnifying factor.

• The magnifying factor of 40× provides best test accuracy.

摘要

•CLAFMM, to alter the class label depending on a secondary training set, is proposed.•CLAFMM is compared with FMM, EFMM and Kn-FMM networks for different databases.•CLAFMM reduces the number of generated hyperboxes and increases the accuracy rate.•CLAFMM is applied to histopathology image database to find the best magnifying factor.•The magnifying factor of 40× provides best test accuracy.

论文关键词：Class label altering fuzzy min max neural network,FMM network,Pattern classification,Hyperbox classifier,Histopathology image

论文评审过程：Received 4 September 2019, Revised 16 February 2021, Accepted 5 March 2021, Available online 13 March 2021, Version of Record 31 March 2021.

论文官网地址：https://doi.org/10.1016/j.eswa.2021.114880