《计算机应用研究》|Application Research of Computers

基于适应值模糊灰模型的交互式进化计算

Interactive evolutionary computation based on fuzzy grey model of fitness

免费全文下载 (已被下载 次)  
获取PDF全文
作者 郭广颂,文振华,何琳琳,郝国生
机构 1.郑州航空工业管理学院 智能工程学院,郑州 450046;2.江苏师范大学 计算机科学与技术学院,江苏 徐州 221116
统计 摘要被查看 次,已被下载
文章编号 1001-3695(2019)06-030-1741-07
DOI 10.19734/j.issn.1001-3695.2018.01.0034
摘要 针对交互式进化计算过程的评价不确定性问题,对个体适应值预测方法进行了研究。对于个体精确数适应值类型,提出基于模糊灰模型FGM(1,1)预测模糊适应值的方法,降低噪声对适应值的影响。确定了用户满意度与适应值噪声强度的函数关系,构建了噪声强度衡量指标;建立模糊适应值支集宽度约束下的最小噪声强度线性规划,求取模糊适应值预测参数,通过模糊灰模型时间响应序列输出模糊适应值。采用NSGA-Ⅱ范式实现进化计算,并设计了新的个体序值比较方法和拥挤测度计算公式。将所提方法应用于烤漆门外观选型问题,并与已有典型方法比较。结果表明,所提方法在推荐个体质量、减轻用户疲劳、提高搜索效率等方面均有优越性。
关键词 适应值; 模糊; GM(1, 1)模型; 交互; 进化计算
基金项目 国家自然科学基金资助项目(61673196)
河南省科技攻关项目(172102210513)
河南省高等学校重点科研项目(18A120012)
本文URL http://www.arocmag.com/article/01-2019-06-030.html
英文标题 Interactive evolutionary computation based on fuzzy grey model of fitness
作者英文名 Guo Guangsong, Wen Zhenhua, He Linlin, Hao Guosheng
机构英文名 1.School of Intelligent Engineering,Zhengzhou University of Aeronautics,Zhengzhou 450046,China;2.College of Computer Science & Technology,Jiangsu Normal University,Xuzhou Jiangsu 221116,China
英文摘要 Aiming at solving uncertainty problem of interactive evolutionary computation, this paper studied the fitness prediction method. In order to more effectively reduce noise influence on fitness, this paper put forward a fuzzy fitness prediction method based on fuzzy grey model FGM(1, 1) with precise number fitness. First of all, it determined the relationship between noise intensity and fitness function and proposed noise intensity index. Then, it proposed a linear programming with fuzzy fitness set width under the restriction of noise intensity minimum, which is used to calculate fuzzy fitness prediction parameters. Finally, the time response sequence of fuzzy grey model output fuzzy fitness. NSGA-Ⅱ realized the evolutionary computation which have a new comparison method of individual sequence and their congestion measure calculation formula. The proposed method was applied to baked lacquer door design problem and compared with existing typical methods. The experimental results confirmend that the proposed algorithm has advantages in improving optimization quality and alleviating user fatigue while improving its efficiency in exploration.
英文关键词 fitness; fuzzy; GM(1, 1) model; interactive; evolutionary computation
参考文献 查看稿件参考文献
 
收稿日期 2018/1/19
修回日期 2018/3/5
页码 1741-1747
中图分类号 TP399;TP301.6
文献标志码 A