摘要
提出一种基于协同进化算法的复杂模糊分类系统的设计方法．该方法由以下3步组成:1)利用Simba算法进行特征变量选择;2)采用模糊聚类算法辨识初始的模糊模型;3)利用协同进化算法对所获得的初始模糊模型进行结构和参数的优化．协同进化算法由三类种群组成;规则数种群,规则前件种群和隶属函数种群;其适应度函数同时考虑模型的精确性和解释性,采用三类种群合作计算的策略．利用该方法对多个典型问题进行分类,仿真结果验证了方法的有效性．
A novel approach to construct complex fuzzy classification system based on cooperative coevolutionary（Co-evolution） algorithm is proposed in this paper. The approach is composed of three phases： 1） feature selection is accomplished by the Simba algorithm; 2） the initial fuzzy system is identified using the fuzzy clustering algorithm; 3） the structure and parameters of the fuzzy system are optimized by the Co-evolution algorithm. The Co-evolution algorithm owns three species including the number of fuzzy rules species, the premise structure species and the parameters species. Considering both precision and interpretability, the fitness function is calculated on the cooperation of individuals from the three species. The proposed approach had been applied to several benchmark problems, the results showed its validity.
出处
《控制理论与应用》
EI
CAS
CSCD
北大核心
2007年第1期32-38,共7页
Control Theory & Applications
基金
国家自然科学资助项目(60474034)
关键词
模糊分类系统
特征变量选择
协同进化算法
解释性
fuzzy classification systems
feature selection
fuzzy clustering
co-evolution algorithm
interpretability
