Scholarlink

This chapter explores practical applications of computational intelligence and feature selection across diverse domains. The first section addresses Fault Diagnosis in Industrial Processes, proposing the Improved Localized Feature Selection (LFS) method (Zhou Y, et al. in IEEE Trans Instrum Meas (2023), [1], based on Multi-Objective Binary Particle Swarm Optimization (LFS-MOBPSO). This approach optimizes conflicting objectives without resorting to balancing strategies, demonstrating superiority over existing methods in imbalanced scenarios.The second section tackles the Classification of DNA Microarray Data, presenting the Cooperative Coevolutionary Multiobjective Genetic Programming (CC-MOGP) (Qing Y, et al in Proceedings of the genetic and evolutionary computation conference (2021), [2]) approach. This method transforms multiclass problems, coevolves populations, and employs a cooperative coevolutionary Pareto archived evolution strategy.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Real-World Case Study

  • 章节

  • 发表日期：

    2025年

查看全文
  • Yu Zhou,
  • Xiao Zhang,
  • Sam Kwong

摘要

This chapter explores practical applications of computational intelligence and feature selection across diverse domains. The first section addresses Fault Diagnosis in Industrial Processes, proposing the Improved Localized Feature Selection (LFS) method (Zhou Y, et al. in IEEE Trans Instrum Meas (2023), [1], based on Multi-Objective Binary Particle Swarm Optimization (LFS-MOBPSO). This approach optimizes conflicting objectives without resorting to balancing strategies, demonstrating superiority over existing methods in imbalanced scenarios.The second section tackles the Classification of DNA Microarray Data, presenting the Cooperative Coevolutionary Multiobjective Genetic Programming (CC-MOGP) (Qing Y, et al in Proceedings of the genetic and evolutionary computation conference (2021), [2]) approach. This method transforms multiclass problems, coevolves populations, and employs a cooperative coevolutionary Pareto archived evolution strategy.