Association rule mining based parameter adaptive strategy for differential evolution algorithms
作者：
Highlights：
• The proposed strategy extracts associations automatically from successful records.
• The proposed strategy incorporate the associations to generate new F and Cr values.
• The process of adaption for F and Cr introduces no extra control parameters.
• We propose a novel method to adapt F and Cr for Differential Evolution algorithms.
• Experiments show that the strategy could enhance performances to some extent.
摘要
•The proposed strategy extracts associations automatically from successful records.•The proposed strategy incorporate the associations to generate new F and Cr values.•The process of adaption for F and Cr introduces no extra control parameters.•We propose a novel method to adapt F and Cr for Differential Evolution algorithms.•Experiments show that the strategy could enhance performances to some extent.
论文关键词：Differential evolution,Association Rule Mining,Parameter adaption
论文评审过程：Received 14 June 2018, Revised 27 November 2018, Accepted 9 January 2019, Available online 11 January 2019, Version of Record 14 January 2019.
论文官网地址：https://doi.org/10.1016/j.eswa.2019.01.035
