| 可理解模糊分类系统的分层演化学习 |
| |
| 引用本文： | 刘建成,蒋新华,吴今培.可理解模糊分类系统的分层演化学习[J].计算机工程与应用,2006,42(5):40-42. |
| |
| 作者姓名： | 刘建成 蒋新华 吴今培 |
| |
| 作者单位： | 中南大学信息科学与工程学院,长沙,410075 |
| |
| 基金项目： | 湖南省自然科学基金;湖南省科技计划 |
| |
| 摘 要： | 针对模糊系统的可理解性要求,结合微粒群算法和遗传算法各自的演化特点,采用两阶段学习策略,对模糊分类系统进行分层演化。首先利用微粒群算法优化各输入变量的语言值数目及对应的模糊集参数,形成候选规则集,再应用遗传算法选择规则,得到可理解的和精确的模糊分类系统。该方法几乎无需先验知识,可直接从实值数据获取模糊分类系统,应用典型分类问题为例说明其有效性。
|
| 关 键 词： | 模糊规则 分类 微粒群算法 遗传算法 |
| 文章编号： | 1002-8331-（2006）05-0040-03 |
| 收稿时间： | 2005-07 |
| 修稿时间： | 2005-07 |
A Hierarchical Evolvement Approach to Interpretable Fuzzy Classification System |
| |
| Liu Jiancheng,Jiang Xinhua,Wu Jinpei.A Hierarchical Evolvement Approach to Interpretable Fuzzy Classification System[J].Computer Engineering and Applications,2006,42(5):40-42. |
| |
| Authors: | Liu Jiancheng Jiang Xinhua Wu Jinpei |
| |
| Affiliation: | School of Information Science and Engineering,Central South University,Changsha 410075 |
| |
| Abstract: | The paper makes use of respective characteristics of genetic algorithm and particle swarm algorithm to build a two-stage evolvement strategy for learning accurate fuzzy rule-based classification system for interpretable requirement. Particle swarm algorithm is used to optimize each membership function of linguistic terms form each input variable, incorporate and form candidate rule bases.Genetic algorithm is utilized to select rules form the bases.The method requests scarcely any previous information and obtain fuzzy classification system from dates.The validity of the method has been demonstrated by typical classification problem. |
| |
| Keywords: | fuzzy rules classification particle swarm algorithm Genetic Algorithms |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
