A genetic algorithm tutorial

This tutorial covers the canonical genetic algorithm as well as more experimental forms of genetic algorithms, including parallel island models and parallel cellular genetic algorithms. The tutorial also illustrates genetic search by hyperplane sampling. The theoretical foundations of genetic algorithms are reviewed, include the schema theorem as well as recently developed exact models of the canonical genetic algorithm.     

分层总线式群集系统设计

给出了一种基于通信效率和群集度比(T_e/I_l)构建有限层总线式松耦合并行系统的一般模型,并详细描述下一个6×6群系统的设计思想和实现过程,工作结果将指导这类系统的集成。     

Identifiability of distributions under competing risks and complementary risks model

Let X₁,X₂,…,X_p be p random variables with cdf's F₁(x),F₂(x),…,F_p(x)respectively. Let U = min(X₁,X₂,…,X_p) and V = max(X₁,X₂,…,X_p).In this paper we study the problem of uniquely determining and estimating the marginal distributions F₁,F₂,…,F_p given the distribution of U or of V.

First the problem of competing and complementary risks are introduced with examples and the corresponding identification problems are considered when the X₁'s are independently distributed and U(V) is identified, as well as the case when U(V) is not identified. The case when the X₁'s are dependent is considered next. Finally the problem of estimation is considered.     

Spatial Matching of Multiple Configurations of Points with a Bioinformatics Application

In this article, we present a general model to deal with the problem of matching multiple objects or configurations of points from a Bayesian point of view. We study both labeled and non labeled cases. Our model generalizes, in terms of non singular affine transformations and multiple configurations, previous two-terms matching models. As a practical application in Bioinformatics, we consider data from a microarray experiment of gorilla, bonobo, and human-cultured fibroblasts. We find out the matchings and the best affine transformation between the projections of genes on a two-dimensional space, obtained by a multidimensional scaling technique.     

Recursive Schemes for Calculating Common Cumulative Distributions

This article gives a method for obtaining accurate (5 decimal places) estimates of nine common cumulative distributions. Starting with a positive series expansion, we use the common ratio of each term to the preceding term and proceed as with a geometric series (the ratio may involve the term number). This avoids calculating terms in the the numerator or denominator which can be large enough to overflow or small enough to underflow the machine. The method is fast because it eliminates the necessity of calculating each term of the series in its entirety.     

Some characterization results for parallel systems with two heterogeneous exponential components

In this paper, we study ordering properties of lifetimes of parallel systems with two independent heterogeneous exponential components in terms of the likelihood ratio order (reversed hazard rate order) and the hazard rate order (stochastic order). We establish, among others, that the weakly majorization order between two hazard rate vectors is equivalent to the likelihood ratio order (reversed hazard rate order) between lifetimes of two parallel systems, and that the p-larger order between two hazard rate vectors is equivalent to the hazard rate order (stochastic order) between lifetimes of two parallel systems. Moreover, we extend the results to the proportional hazard rate models. The results derived here strengthen and generalize some of the results known in the literature.     

On the right spread ordering of parallel systems with two heterogeneous components

This article discusses the variability ordering of lifetimes of parallel systems with two independent heterogeneous exponential components in terms of the right spread order. It is proved, among others, that the reciprocal majorization order between the two hazard rate vectors implies the right spread order between the lifetimes of two parallel systems. The result is then extended to the proportional hazard rate model as well. The results established here extend and enrich those known in the literature.     

嵌套并联结构两阶段DEA下科技创新效率测度与分解

目前有许多研究将两阶段DEA模型应用到科技创新活动当中，一般将创新活动分为研发和转化两个阶段，为了进一步探讨不同转移转化方式下科技成果的转化效率以获得更多的详细信息，本文拓展了传统的两阶段DEA模型，考虑了嵌套并联结构的两阶段网络DEA模型，将科技创新活动分为科技成果研发阶段和科技成果转化阶段，并将科技成果转化阶段分为内部转化和外部转化两个并联子系统。本文选取14家中科院院属单位作为被评价对象，应用加权加法分解方法计算整体效率和各阶段子效率。通过将本文模型与传统两阶段模型进行对比发现，传统模型会低估科技成果转化效率。结果表明：整体科技创新效率均值偏低，科技成果研发效率均值高于科技成果转化效率均值，科技成果转化效率仍有很大的提升空间。科技成果转化阶段中内部转化效率普遍较高但是外部转化效率普遍较低，较低的外部转化效率是导致科技成果转化效率低下的主要原因。最后，本文将所有被评价单位分为四类机构，分析提高科技创新效率的实现路径，可以通过重点突破模式和渐进突破模式来实现整体效率的提高。     

基于Babel英汉平行语料库的英汉介词对比分析

介词是英汉两种语言中较为特殊的一类词，在实际使用中都非常活跃。通过对英汉介词的简要阐述，在以前的研究基础上，尝试基于Babel英汉平行语料库，对其中出现频率最高的前十个英语介词和汉语介词的使用频率，兼类情况及其对应关系做以对比分析，以期对英译汉中的介词翻译能有所启示。另外，介词在英译汉时可以采取直译、增译、省译和转译四种方法。