Integration of aggressive bound tightening and Mixed Integer Programming for Cost-sensitive feature selection in medical diagnosis
作者：
Highlights：
• New MIP models for cost-sensitive feature selection are proposed.
• The models are robust enough to account for shared cost across feature groups.
• Aggressive bound tightening within Branch and Cut algorithm was used.
• The proposed cost-sensitive feature selection models outperformed existing feature selection techniques.
• The models improved the accuracy up by 10.3% and decreased the cost up to 96%.
摘要
•New MIP models for cost-sensitive feature selection are proposed.•The models are robust enough to account for shared cost across feature groups.•Aggressive bound tightening within Branch and Cut algorithm was used.•The proposed cost-sensitive feature selection models outperformed existing feature selection techniques.•The models improved the accuracy up by 10.3% and decreased the cost up to 96%.
论文关键词：Mixed Integer Linear Programming,Aggressive bound tightening,Feature selection,Shared costs,Cost-sensitive,Medical diagnosis
论文评审过程：Received 8 March 2020, Revised 6 June 2021, Accepted 10 September 2021, Available online 20 September 2021, Version of Record 21 September 2021.
论文官网地址：https://doi.org/10.1016/j.eswa.2021.115902
