Combining clustering and classification ensembles: A novel pipeline to identify breast cancer profiles

作者：

Highlights：

• Combining the outputs of the individual clustering algorithms results in unclustered data.

• A framework combining ensemble classification stage after the ensemble clustering stage is introduced.

• The proposed pipeline is employed on a novel real world breast cancer dataset and multiple standard datasets from UCI.

• The results show that by using the presented pipeline an improved classification is obtained.

摘要

•Combining the outputs of the individual clustering algorithms results in unclustered data.•A framework combining ensemble classification stage after the ensemble clustering stage is introduced.•The proposed pipeline is employed on a novel real world breast cancer dataset and multiple standard datasets from UCI.•The results show that by using the presented pipeline an improved classification is obtained.

论文关键词：Ensemble clustering,Ensemble classification,Class level fusion,Refining cluster results,Breast cancer,Pipeline

论文评审过程：Received 6 August 2017, Revised 1 April 2019, Accepted 8 May 2019, Available online 15 May 2019, Version of Record 28 May 2019.

论文官网地址：https://doi.org/10.1016/j.artmed.2019.05.002