A structure optimization method for extended belief-rule-based classification system
作者：
Highlights：
• Summarize the drawbacks of conventional EBRB systems and some existing work concerning attributes processing and rule activation.
• Propose an attribute optimization method to select key attributes and assign attribute weights for EBRB classification system.
• Propose an improved minimum centre distance rule activation method to activate appropriate EBRs for EBRB classification system.
• Experiments show SO-EBRB has good performance on accuracy, activation ratio, response time.
摘要
•Summarize the drawbacks of conventional EBRB systems and some existing work concerning attributes processing and rule activation.•Propose an attribute optimization method to select key attributes and assign attribute weights for EBRB classification system.•Propose an improved minimum centre distance rule activation method to activate appropriate EBRs for EBRB classification system.•Experiments show SO-EBRB has good performance on accuracy, activation ratio, response time.
论文关键词：Extended belief-rule-based system,Structure optimization,Attribute optimization,Rule activation,Classification,High dimension
论文评审过程：Received 31 October 2019, Revised 28 May 2020, Accepted 30 May 2020, Available online 2 June 2020, Version of Record 3 June 2020.
论文官网地址：https://doi.org/10.1016/j.knosys.2020.106096
