基于半监督学习的变种群规模区间适应值交互式遗传算法
Interval-fitness interactive genetic algorithms with varying population size based on semi-supervised learning
摘要点击 1695  全文点击 1713  投稿时间:2009-12-20  修订日期:2010-06-08
查看全文  查看/发表评论  下载PDF阅读器
DOI编号  10.7641/j.issn.1000-8152.2011.5.CCTA091642
  2011,28(5):610-618
中文关键词  交互式遗传算法  区间适应值  半监督学习  代理模型  变种群规模
英文关键词  interactive genetic algorithms  interval fitness  semi-supervised learning  surrogate model  varying population size
基金项目  国家自然科学基金资助项目(60775044); 教育部新世纪优秀人才支持计划资助项目(NCET-07-0802); 江苏省自然科学基金资助项目(Bk2010186); 江苏省博士后基金资助项目(1001019C).
作者单位E-mail
孙晓燕 中国矿业大学 信息与电气工程学院 xysun78@126.com 
任洁 中国矿业大学 信息与电气工程学院  
巩敦卫 中国矿业大学 信息与电气工程学院  
中文摘要
      为了减轻用户疲劳并增强算法的搜索性能, 本文在变种群规模交互式遗传算法的基础上引入协同训练半监督学习方法, 提出基于半监督学习的变种群规模区间适应值交互式遗传算法. 根据对大规模种群的聚类结果, 给出标记样本和未标记样本的获取方法; 结合半监督协同学习器逼近误差的改变, 提出高可信度未标记样本的选择策略; 采用半监督协同学习机制训练两个径向基函数(RBF)神经网络, 构造精度高泛化能力强的代理模型; 在进化过程中, 利用代理模型估计大种群规模进化个体适应值, 并根据估计偏差更新代理模型. 算法的理论分析及其在服装进化设计系统中的应用结果说明了算法的有效性.
英文摘要
      In order to alleviate user fatigue and improve the performances of interactive genetic algorithms (IGAs) in exploration, we present the interval-fitness interactive genetic algorithms with varying population size based on a cotraining semi-supervised learning(CSSL). According to the clustering results of a large population, we develop the strategy for selecting unlabeled samples and labeled samples. Based on the approximation precision of two co-training learners, an efficient strategy for selecting high reliable unlabeled samples for labeling is given. Then, the CSSL mechanism is employed to train two radial basis function(RBF) neural networks in order to establish the surrogate model with high precision and good generalization ability. In the subsequent evolution, the surrogate model is used to estimate the fitness of an individual; in turn, the surrogate model is updated based on its estimation error. The proposed algorithm is analyzed and applied to a fashion evolutionary design system. The experimental results show its efficacy.