A novel intelligent classification model for breast cancer diagnosis

作者：

Highlights：

• A novel intelligent classification method for breast cancer diagnosis is proposed.

• The novel method has considered the misclassification cost of the breast cancer tumor.

• The novel method called “IGSAGAW-CSSVM”, which applied IGSAGAW for feature selection and CSSVM perform for breast cancer classification.

• The classification results by our proposed method, Genetic Algorithm Wrapper and Baseline classification models are compared for WDBC and WBC data sets.

摘要

•A novel intelligent classification method for breast cancer diagnosis is proposed.•The novel method has considered the misclassification cost of the breast cancer tumor.•The novel method called “IGSAGAW-CSSVM”, which applied IGSAGAW for feature selection and CSSVM perform for breast cancer classification.•The classification results by our proposed method, Genetic Algorithm Wrapper and Baseline classification models are compared for WDBC and WBC data sets.

论文关键词：Support vector machine,Breast cancer diagnosis,Information gain,Cost-sensitive learning,Genetic algorithm

论文评审过程：Received 20 October 2017, Revised 16 August 2018, Accepted 18 October 2018, Available online 9 January 2019, Version of Record 9 January 2019.

论文官网地址：https://doi.org/10.1016/j.ipm.2018.10.014