Proximity and priority: applying a gene expression algorithm to the Traveling Salesperson Problem

We describe an environment for evolutionary computation that supports the movement of information from genome to phenotype with the possibility of one or more intermediate transformations. Our notion of a phenotype is more than a simple alternate representation of the binary genome. The construction of a phenotype is sufficiently different from the genome as to require its generation by a procedure that we call a gene expression algorithm. We discuss various reasons why benefits should accrue when combining gene expression algorithms with conventional genetic algorithms and illustrate these ideas with an algorithm to generate approximate solutions to the Traveling Salesperson Problem. As in most genetic algorithms dealing with the TSP we run into the problem of an appropriate crossover operation for the strings that specify a permutation. To handle this issue we introduce a novel genome representation that admits a natural crossover operation and produces a permutation vector as an intermediate representation. The gene expression strategy offers an excellent opportunity for parallelization of the computation since the gene expression processing for each genome and the subsequent evaluation of the fitness function are computations that can be spread across many processors.     

交互式遗传算法在作曲中的应用

对交互式遗传算法作曲进行了一定的探讨.介绍了用遗传算法进行作曲的知识表示.通过将给定的乐谱转化成相应的编码,采用交互式遗传算法中的选择,交叉和变异算子产生新的乐曲.对交互式遗传算法作曲进行了仿真实验,讨论了实验步骤,给出了实验结果.仿真结果表明,设计的作曲系统可以产生出令人感兴趣的乐曲,具有一定的实际意义.     

Genetic algorithm with fuzzy logic controller for preemptive and non-preemptive job-shop scheduling problems

In this paper, we propose a new genetic algorithm (GA) with fuzzy logic controller (FLC) for dealing with preemptive job-shop scheduling problems (p-JSP) and non-preemptive job-shop scheduling problems (np-JSP). The proposed algorithm considers the preemptive cases of activities among jobs under single machine scheduling problems. For these preemptive cases, we first use constraint programming and secondly develop a new gene representation method, a new crossover and mutation operators in the proposed algorithm.However, the proposed algorithm, as conventional GA, also has a weakness that takes so much time for the fine-tuning of genetic parameters. FLC can be used for regulating these parameters.In this paper, FLC is used to adaptively regulate the crossover ratio and the mutation ratio of the proposed algorithm. To prove the performance of the proposed FLC, we divide the proposed algorithm into two cases: the GA with the FLC (pro-fGA) and the GA without the FLC (pro-GA).In numerical examples, we apply the proposed algorithms to several job-shop scheduling problems and the results applied are analyzed and compared. Various experiments show that the results of pro-fGA outperform those of pro-GA.     

一种改进的遗传聚类算法

给出了一种改进的基于遗传算法的聚类方法。传统的K-means算法局部搜索能力强,但是对初始化比较敏感,容易陷入局部最优值。基本的基于遗传算法的聚类算法是一种全局优化算法,但是其局部搜索能力较差,收敛速度慢。针对这两个方法所存在的问题,提出了一种改进的聚类算法。该方法结合了两个方法的优点,引入了K-means操作,再用遗传算法进行优化,并且在该方法中改进了遗传算法中的交叉算子,大大提高了基于遗传算法的聚类算法的局部搜索能力和收敛速度。     

基于外点法的混合遗传算法求解约束优化问题

提出了一种求解约束优化问题的混合遗传算法。它不是传统的在适应值函数中加一个惩罚项，而是在初始种群、交叉运算和变异运算过程中，把违反约束条件的个体用外点法处理设计出新的实数编码遗传算法。数值实验证明，新算法性能优于现有其他进化算法，是通用性强、高效稳健的方法。该方法兼顾了遗传算法和外点法的优点，既有较快的收敛速度，又能以非常大的概率求得约束优化问题全局最优解。     

生成树编码遗传算法种群退化分析及抑制方法

种群退化现象导致了遗传算法对解空间区域进行重复搜索,从而降低了算法的搜索效率和延缓了算法的收敛,这源于重组算子、采样误差和变异算子的反作用力。通过对生成树编码遗传算法的研究,分析了重组算子的种群退化现象。证明了在解决固定费用运输问题时,重组算子发生种群退化现象的一个充分条件及其概率。针对种群退化现象提出了基于概率选择模型抑制算法（Probabilistic Selection Model Crossover,PSDC）,对其有效性进行了分析证明。与小生境技术相比,它具有可以通过控制选择概率来抑制种群退化和不需要额外的时间开销两大优势,这为遗传算法的设计和应用提供了理论研究依据。     

基于遗传算法的QoS组播路由算法

提出了一种新的基于遗传算法的OoS组播路由算法。该算法具有预处理机制、树型结构编码、启发式初始种群生成和交叉策略、指导性变异过程。仿真结果表明,该算法的性能和效率都优于文中提到的其它现存算法。     

基于免疫遗传算法的复杂网络社区发现

针对大部分基于智能优化算法的社区发现方法存在的种群退化、寻优能力不强、计算过程复杂、需要先验知识等问题,提出了一种基于免疫遗传算法(GA)的复杂网络社区发现方法。算法将改进的字符编码和相应的遗传算子相结合,在不需要先验知识的情况下可自动获得最优社区数和社区划分方案;将免疫原理引入遗传算法的选择操作中,保持了群体多样性,改善了遗传算法所固有的退化现象;在初始化种群及交叉和变异算子中利用网络拓扑结构的局部信息,有效缩小了搜索空间,增强了寻优能力。计算机生成网络和真实网络上的仿真实验结果表明算法可自动获取最优社区数和社区划分方案并具有较高的精度,说明算法具有可行性和有效性。     

Addressing a nonlinear fixed-charge transportation problem using a spanning tree-based genetic algorithm

In this paper, we consider the fixed-charge transportation problem (FCTP) in which a fixed cost, sometimes called a setup cost, is incurred if another related variable assumes a nonzero value. To tackle such an NP-hard problem, there are several genetic algorithms based on spanning tree and Prüfer number representation. Contrary to the findings in previous works, considering the genetic algorithm (GA) based on spanning tree, we present a pioneer method to design a chromosome that does not need a repairing procedure for feasibility, i.e. all the produced chromosomes are feasible. Also, we correct the procedure provided in previous works, which designs transportation tree with feasible chromosomes. We show the previous procedure does not produce any transportation tree in some situations. Besides, some new crossover and mutation operators are developed and used in this work. Due to the significant role of crossover and mutation operators on the algorithm’s quality, the operators and parameters need to be accurately calibrated to ensure the best performance. For this purpose, various problem sizes are generated at random and then a robust calibration is applied to the parameters using the Taguchi method. In addition, two problems with different sizes are solved to evaluate the performance of the presented algorithm and to compare that performance with LINGO and also with the solution presented in previous work.     

Linear analysis of genetic algorithms

We represent simple and fitness-scaled genetic algorithms by Markov chains on probability distributions over the set of all possible populations of a fixed finite size. Analysis of this formulation yields new insight into the geometric properties of the three phase mutation, crossover, and fitness selection of a genetic algorithm by representing them as stochastic matrices acting on the state space. This indicates new methods using mutation and crossover as the proposal scheme for simulated annealing. We show by explicit estimates that for small mutation rates a genetic algorithm asymptotically spends most of its time in uniform populations regardless of crossover rate. The simple genetic algorithm converges in the following sense: there exists a fully positive limit probability distribution over populations. This distribution is independent of the choice of initial population. We establish strong ergodicity of the underlying inhomogeneous Markov chain for genetic algorithms that use any of a large class of fitness scaling methods including linear fitness scaling, sigma-truncation, and power law scaling. Our analysis even allows for variation in mutation and crossover rates according to a pre-determined schedule, where the mutation rate stays bounded away from zero. We show that the limit probability distribution of such a process is fully positive at all populations of uniform fitness. Consequently, genetic algorithms that use the above fitness scalings do not converge to a population containing only optimal members. This answers a question of G. Rudolph (IEEE Trans. on Neural Networks 5 (1994) 96–101). For a large set of fitness scaling methods, the limit distribution depends on the pre-order induced by the fitness function f, i.e. c c′ f(c) f(c′) on possible creatures c and c′, and not on the particular values assumed by the fitness function.     

Backward-chaining evolutionary algorithms

Starting from some simple observations on a popular selection method in Evolutionary Algorithms (EAs)—tournament selection—we highlight a previously-unknown source of inefficiency. This leads us to rethink the order in which operations are performed within EAs, and to suggest an algorithm—the EA with efficient macro-selection—that avoids the inefficiencies associated with tournament selection. This algorithm has the same expected behaviour as the standard EA but yields considerable savings in terms of fitness evaluations. Since fitness evaluation typically dominates the resources needed to solve any non-trivial problem, these savings translate into a reduction in computer time. Noting the connection between the algorithm and rule-based systems, we then further modify the order of operations in the EA, effectively turning the evolutionary search into an inference process operating in backward-chaining mode. The resulting backward-chaining EA creates and evaluates individuals recursively, backward from the last generation to the first, using depth-first search and backtracking. It is even more powerful than the EA with efficient macro-selection in that it shares all its benefits, but it also provably finds fitter solutions sooner, i.e., it is a faster algorithm. These algorithms can be applied to any form of population based search, any representation, fitness function, crossover and mutation, provided they use tournament selection. We analyse their behaviour and benefits both theoretically, using Markov chain theory and space/time complexity analysis, and empirically, by performing a variety of experiments with standard and back-ward chaining versions of genetic algorithms and genetic programming.     

一种基于改进遗传算法的路径测试用例生成方法

采用遗传算法求解路径覆盖的测试用例生成问题是软件测试自动化的研究热点。针对传统标准遗传方法搜索测试用例易产生早熟收敛和收敛速度较慢的不足,设计了自适应的交叉算子和变异算子,提高了算法的全局寻优能力。基于动态生成算法框架,通过程序静态分析,考虑了分支嵌套深度的影响,结合层接近度和分支距离法,提出一种新的适应度函数。实验结果表明,该算法在面向路径的测试用例生成上优于传统方法,提高了测试效率。     

柔性多面体搜索算法在遗传算法中的综合应用研究

首先分析了柔性多面体搜索算法和基本遗传算法两者结合的基础，提出了柔性多面体方向进化算子和柔性多面体交叉算子，以这两个新的遗传操作算子和柔性多面体搜索算法为基础，提出了两种新的混合遗传算法FP-HGA(Ⅰ)、FP-HGA(Ⅱ).在FP-HGA(Ⅰ)中，嵌入了柔性多面体方向进化算子和柔性多面体搜索算法；在FP-HGA(Ⅱ)中，嵌入了柔性多面体交叉算子，用FP-HGA(Ⅰ)、FP-HGA(Ⅱ)及SGA(Simple Genetic Algorithm)来求解Rosenbrock测试函数的最小值，FP-HGA(Ⅰ)和FPHGA(Ⅱ)算法和SGA算法的计算结果表明该混合遗传算法在收敛速度和精度方面均得到很大提高．     

多重群体遗传算法在多选择背包问题中的应用

为了解决多选择背包问题,引入了多重群体遗传算法作为求解方法,根据此问题的特点而制定了具体的杂交、变异方法,设计了遗传算法。在算法中以目标函数加惩罚函数为适应值评价函数,采用新陈代谢的选择策略,以更好地保持进化过程中的遗传多样性。实践表明,引入了多重群体遗传算法之后,求解此问题效率有明显的改善与提高。     

遗传算法的一种新颖编码研究

提出了一种新的基于N进制分部编码算子的遗传算法．该编码算子首先将每个基因值用N进制的浮点数表示，然后将其分为整数部分和小数部分，分别重新编码组成染色体；相应的选择、交叉、变异算子采用符号编码的思想，充分利用N进制浮点数的特点进行设计．在遗传算法开始阶段，该编码算子进行整数部分和小数部分的遗传操作，使得遗传算法在早期具有很强的全局搜索能力，避免陷入局部极值；在后期进行小数部分的遗传操作，使得遗传在后期具有很强的局部搜索能力，能够很快地搜索到全局极值．通过理论分析，证明了N进制分部编码算子与传统的浮点数编码和二进制编码算子相比具有优越性，并通过典型函数的仿真进行了验证．     

嵌套式模糊自适应遗传算法

针对简单遗传算法(SGA)收敛速度慢和早熟收敛现象,将模糊逻辑理论应用于遗传算法,并采用两级嵌套的遗传算法,随主遗传算法GA1求解优化问题的进化进程用模糊控制的方法自适应地调整遗传算法的交叉概率和变异概率;利用另一个遗传算法GA2优化模糊规则库,实现了一种嵌套式模糊自适应遗传算法(NFAGA)。仿真结果表明,这种算法的全局搜索收敛速度和解的质量明显优于SGA和一般的自适应遗传算法(AGA)。     

Fuzzy job shop scheduling problem with availability constraints

This paper presents the fuzzy job shop scheduling problem with availability constraints. The objective is to find a schedule that maximizes the minimum agreement index subject to periodic maintenance, non-resumable jobs and fuzzy due-date. A random key genetic algorithm (RKGA) is proposed for the problem, in which a novel random key representation, a new decoding strategy incorporating maintenance operation and discrete crossover (DX) are used. RKGA is applied to some fuzzy scheduling problem with availability constraints and compared with other algorithms. Computational results show that RKGA performs better than other algorithms.     

自适应遗传算法在机器人路径规划的应用

针对现有遗传算法在求解机器人路径规划存在的收敛速度慢、易陷入局部最优等缺点,提出一种基于自适应遗传算法的机器人路径规划方法。该方法引入逆转算子,增加插入算子和删除算子,提出新的自适应策略对交叉和变异概率进行调整,更好地避免陷入局部最优,提高算法寻优效率。该算法在MATLAB和Inte3D平台中进行算例验证,实验结果表明改进的自适应遗传算法比现有遗传算法更为有效。     

一种基于优化的自适应遗传算法的粒子滤波算法

针对粒子滤波的粒子退化现象及多样性损失问题,提出了一种新的基于优化的自适应遗传算法的粒子滤波算法。该算法首先依据每个采样时刻生成的粒子集合重要性权值作为适应度值,自适应的确定交叉、遗传的概率;然后对选出的粒子进行遗传操作,重新度量其粒子的权值并进行状态估计。该方法不仅保留了粒子的多样性,而且相对于普通的基于自适应遗传算法的粒子滤波算法,降低了高权值粒子交叉和变异的可能,使粒子的采样更接近于状态后验概率密度分布。实验结果表明,该算法有效提高了滤波精度。     

Conjugate schema and basis representation of crossover and mutation operators

In genetic search algorithms and optimization routines, the representation of the mutation and crossover operators are typically defaulted to the canonical basis. We show that this can be influential in the usefulness of the search algorithm. We then pose the question of how to find a basis for which the search algorithm is most useful. The conjugate schema is introduced as a general mathematical construct and is shown to separate a function into smaller dimensional functions whose sum is the original function. It is shown that conjugate schema, when used on a test suite of functions, improves the performance of the search algorithm on 10 out of 12 of these functions. Finally, a rigorous but abbreviated mathematical derivation is given in the appendices.