遗传算法模式理论研究

给出了多种交叉方式遗传算法的模式定理及相关的证明.该定理避免了遗传算法模式理论的不足,使模式理论更加准确、严格.     

蒙山脆枣与枣及酸枣亲缘关系的研究

以蒙山脆枣及山东省内的9个枣品种和32个酸枣类型(株系)为试材,采用形态学分析和RAPD分析,对蒙山脆枣与枣及酸枣的亲缘关系进行研究,并初步探讨了蒙山脆枣的起源及枣的演化过程。形态学性状数据主成分分析结果表明,蒙山脆枣第1主成分值为5.42,第2主成分值为0.64,介于枣品种和酸枣类型之间,地位较为特殊。对形态学性状数据聚类,结果表明,蒙山脆枣先与酸枣1号在6.40阈值处聚为一类,再与大枣品种的聚类群在11.75阈值处聚为1类之后,才与其它酸枣类型的聚类群聚为一类,显示出蒙山脆枣的分类地位介于枣和酸枣之间。进一步的RAPD分析结果表明,蒙山脆枣与酸枣亲缘关系较近。蒙山脆枣果实长2cm左右,外果皮较薄,中果皮较厚,平均单果重为3.64g,叶片纵横径为6.93cm×3.08cm,形态学性状与枣接近,推测蒙山脆枣可能为供试酸枣类型与枣品种的中间类型。     

A New Integrated Design Method Based on Fuzzy Matter-Element Optimization

This paper puts forward a new integrated design met ho d based on fuzzy matter-element optimization.On the based of analyzing the mod el of multi-objective fuzzy matter-element , the paper defines the m atter-element weightily and changes solving multi-objective fuzzy optimization into solving dependent function K(x) of the single-objective optimization according to the optimization criterion. The paper particularly describes the realization approach of GA process of multi -objective fuzzy matter-eleme...     

上海郊区居民和台湾高山族的体质比较

收集了上海郊区13个具有明显方言差异人群的头面部数据4项，和台湾高山族10个群体的参数进行聚类分析，发现上海郊区居民中的南方土著人群与台湾高山的遗传关系较近。     

The genetic diversity of cen-tral and peripheral popula-tions of ratlike hamster(Cricetulus triton)

The impact of habitat fragmentation and isolation on the genetic diversity of populations has attracted much attention in studies of meta-population and conservation biology. In this work, using the randomly amplified polymorphic DNA (RAPD) technique, we studied the genetic diversity of central, peripheral and peninsular populations of ratlike hamster, which were collected in five locations of the North China Plain and its surrounding areas, in 1999. The study revealed that, ⅰ) the genetic diversity of central population of Raoyang County＞the sub-central populations of Gu'an County and Taikang County＞the peripheral population of Shunyi District＞the peninsular population of Mentougou District; ⅱ) the genetic diversities of the five populations were positively correlated to the nearest distances to the peripheral line of population distribution; ⅲ) there were significant differences of gene frequencies of some RAPD fragments among the five populations. More RAPD fragments disappeared in peripheral populations than in central or sub-central populations. The frequencies of two RAPD fragments were correlated to the latitude. This study clearly indicated that the variation of the genetic diversities of the five populations was caused by edge effect and frag- mentation through the enhanced inbreeding and genetic drift, and thus supported the view that habitat fragmentation and related edge effect reduce the population genetic diversity.     

用遗传算法求解课程表问题

课程表问题是NP完全类问题.近些年来人们尝试着用进化算法求此问题.本文根据大学编排课表的特点设计了一种全新的编码和适应值函数,并应用遗传算法求解.试验说明了该方法的可行性和有效性.     

应用不定量凸模型的遗传算法解决结构设计的优化问题

针对不定静载荷和由不定搜索而产生的最不利情况 ,应用遗传算法来解决桁架的优化问题。说明了在考虑不定量的结构设计优化问题中 ,应用遗传算法实现的高效性。     

影响遗传规划基因内区的因素分析

通过众多的试验和分析 ,证实遗传规划的个体中存在基因内区 ,它对进化的收敛既有积极作用也有消极作用 .文中通过对有关遗传操作方法和参数的研究 ,定性地分析了它们对基因内区的影响 ,并指出抑制基因内区消极作用的途径 .     

复杂系统的遗传-模糊建模方法

针对复杂系统的模糊建模问题，提出了一种遗传．模糊建模新方法。首先，利用竞争学习算法对输入空间进行自适应聚类，基于聚类结果提取模糊模型的规则前件隶属函数参数，采用局部最小二乘法求得规则后件参数，从而初步建立起系统的T-S模糊模型。然后，对规则前、后件参数进行编码，借助于实值编码遗传算法优化模糊系统。最后，数字仿真结果验证了算法的可行性和有效性。