求解作业排序问题的一种改进修复约束满足算法

修复约束满足算法(修复法)是在完整初始解的基础上不断对变量进行修复,最终得到可行解.对此,提出一种求解flow shop排序问题的改进修复法(IRCS_WT),通过采用新的变量表达方式,设计了一种以启发式优化规则为指导的变量选择算法(LWT),并采用一种变量互换算法(LTEE)保证算法的全局搜索性能.将新算法应用于31个标准算例,与传统算法及遗传算法的优化结果进行比较,结果表明在相同运算时问下改进算法具有明显的优越性.     

求解SAT问题的退火遗传算法

提出一种将遗传算法与模拟退火算法相结合的SAT问题求解算法SAT-SAGA.该算法以遗传算法流程为主体,并把模拟退火机制融入其中,用以调整优化群体,防止陷入局部最优和出现早熟;在进化过程中算法采用了最优染色体保存策略,防止进化过程的发散.实验表明:该算法在求解速度、成功率和求解问题的规模等方面都有明显的改善.     

一种基于离散微粒群优化的数字曲线的多边形近似算法

数字曲线的多边形近似是图像分析研究领域的一个热点问题.获取数字曲线的优化多边形近似是一个复杂的问题,其计算复杂度非常高.微粒群算法是近些年来提出的一种新的优化方法,已经被广泛应用于各种优化问题的求解.提出了一种求解数字曲线的多边形近似问题的基于整数编码的离散微粒群算法(IPSO).IPSO通过重新定义标准微粒群算法的速度和位置更新公式中的加法、乘法和减法运算,使得算法能运行在离散的解空间.IPSO的位置向量修复机制保证了解的可行性,而局部优化器提高了算法的搜索精度.实验结果表明,IPSO求解的质量和求解的效率均优于遗传算法和0-1编码的微粒群算法.     

文化基因算法在多约束背包问题中的应用

文化基因算法是一种启发式算法,与一些经典数学方法相比,更适于求解多约束背包问题.文化基因算法是一种基于种群的全局搜索和基于个体的局部启发式搜索的结合体,针对多约束问题,提出采用贪婪策略通过违反度排序的方法处理多约束条件,全局搜索采用遗传算法,局部搜索采用模拟退火策略,解决具有多约束条件的0-1背包问题.通过对几个实例的求解,表明文化基因算法与标准遗传算法相比,具有更优的搜索性能.     

遗传算法中致死染色体的利用

提出一种基于免疫算子的致死染色体复活与利用方法。根据问题的特征信息,优秀染色体和致死染色体的基因信息提取疫苗,通过接种疫苗和免疫选择,以及在“活岛”和“死岛”进行致死染色体和非致死染色体的迁移,实现致死染色体的复活与利用。将算法应用于0-1背包问题,数值实验结果表明,该方法可以有效改善求解约束优化问题遗传算法的性能。     

遗传算法在无重复规格一维下料优化中的应用

在对无重复规格一维下料优化问题数学模型分析的基础上,提出了基于改进遗传算法的优化下料方案求解方法.具体做法是,以实数表示的各零件长度的一个排列作为一个染色体,对一个可能解进行编码,其中的每个零件长度为一个基因;同时,为了便于遗传算子的设计,对染色体的基因进行分段,同一段上的基因表示它们截自同一原材料;通过基于基因分段的杂交、变异获得优化解.实验结果表明该算法是解决无重复规格一维下料问题的可行算法.     

基于染色体易位的动态进化算法

针对采用二进制编码的进化算法在函数优化过程中会因为维度之间的相互干扰,导致部分低阶模式出现无法进行有效重组的现象,提出一种新的结合细胞学研究成果的进化算法——染色体易位的动态进化算法(CTDEA)。算法通过构建基因矩阵来模拟有机染色体在细胞内的结构化过程,并在基因矩阵的基础上对出现同质化的染色体短列实施模块化的易位操作,以此来维护种群的多样性;同时通过个体适应度划分种群的方式来维护精英个体,确保个体间的竞争压力,提升算法的寻优速度。实验结果表明,该进化算法与已有的遗传算法(GA)和分布估计算法相比较,在维护种群多样性方面有较大改进,能够将种群的多样性保持在0.25左右;且在寻优的精度、稳定性以及速度上也有明显的改进和提高。     

求解约束优化问题的粒子进化变异遗传算法

设计一种求解约束优化问题的粒子进化变异遗传算法(IGA_PSE).首先,分析候选解约束条件离差统计信息与约束违反函数之间的关系及其性质,基于约束条件离差统计信息提出一种改进约束处理方法;其次,基于粒子进化策略提出3种新变异算子;然后,讨论该算法早熟收敛的3种情况,并提出相应的种群多样化维持策略;最后,通过数值实验表明所提出的算法能够有效求解约束优化问题.     

基于多层染色体基因表达式程序设计的混合遗传进化算法

提出了一种新的基于多层染色体基因表达式程序设计的混合遗传进化算法:M-GEP-GA。 该算法在基因表达式程序设计的基础上引入了多层染色体，并采用与遗传算法相嵌套的二级演化方法。利用染色体构建的层次调用模型对个体进行表达，用基因表达式程序设计方法优化模型结构,遗传算法优化模型参数。通过对三组数据测试,与用单基因GEP、多基因GEP的结果进行对比,实验表明改进的算法具有更强的寻优能力和更高的稳定性。     

用改进的竞争Hopfield神经网络求解多边形近似问题

多边形近似是提取曲线特征点和简化曲线描述的一种重要方法.提出一种改进的Hopfield神经网络多边形近似算法,该算法利用选择拐点策略减少了搜索空间,重新定义了神经网络的能量函数,使其更能反映优化目标;引?入合并拆分搜索策略,有效帮助神经网络脱离局部最小值.实验结果表明,提出的改进算法是有效的,比其它算法如关键点检测法、竞争Hopfield神经网络、混沌Hopfield神经网络、遗传算法等具有更优的性能.     

基于遗传算法的多边形逼近3D数字曲线

首先对3D数字曲线进行简单的数据压缩．通过对该曲线上的点列进行二进制编码定义来表示数字曲线的染色体．二进制串中的每一个位称为基因，每一个逼近多边形和染色体形成1-1映射．目标函数使给定曲线和逼近多边形之间的均方差最小．构造了解决该问题的选择、交叉、变异三个算子．所得最优染色体中基因值为1的基因对应数字曲线的分界点．实验结果表明，该方法能够得到精确的逼近结果．     

多边形近似曲线的基于排序选择的拆分合并算法

将遗传算法的排序选择策略引入到传统的拆分与合并算法，提出一种基于排序选择策略的拆分与合并算法（RSM）来求解平面数字曲线的多边形近似，解决了传统的拆分与合并算法对初始解的依赖问题．用2条通用的benchmark曲线对RSM算法进行测试，结果表明该算法的性能优于遗传算法和传统的拆分与合并算法．将RSM算法应用于湖泊卫星图像的多边形近似，取得了较好的近似效果．     

求解非连通图旅行商问题的改进遗传算法

为了克服传统遗传算法的早熟收敛问题,提出改进遗传算法。采用基于旅行商遍历城市顺序的染色体编码,结合随机法与贪心法生成初始种群,提高遗传效率。通过执行优先保留交叉和平移变异操作,引入局部邻域搜索,给出最优解是否满足非连通约束的判据。最后,实验结果验证了该算法的有效性。     

混合分布估计算法求解随机Job shop 提前/拖期调度问题

针对加工时间具有随机特性的Job shop 调度问题, 提出基于分布估计算法的混合算法. 为增强分布估计算法的种群多样性, 定义了父代工序继承率并设计一种可保留父代个体优良结构特征的重组方法, 该方法在继承父代个体优良结构特征的同时避免了非法解的产生. 在个体选择评价阶段, 采用最优计算量分配策略为每个个体分配模拟量以提高个体评价的精确性. 仿真算例表明了所提出算法的有效性和鲁棒性.

     

Genetic particle swarm optimization for polygonal approximation of digital curves

Polygonal approximation is an important technique in image representation which directly impacts on the accuracy and efficacy of the subsequent image analysis tasks. This paper presents a new polygonal approximation approach based on particle swarm optimization (PSO). The original PSO is customized to continuous function value optimization. To facilitate the applicability of PSO to combinatorial optimization involving the problem in question, genetic reproduction mechanisms, namely crossover and mutation, are incorporated into PSO. We also propose a hybrid strategy embedding a segment-adjusting-and-merging optimizer into the genetic PSO evolutionary iterations to enhance its performance. The experimental results show that the proposed genetic PSO significantly improves the search efficacy of PSO for the polygonal approximation problem, and the hybrid strategy can accelerate the convergence speed but still with good-quality results. The performance of the proposed method is compared to existing approaches on both synthesized and real image curves. It is shown that the proposed hybrid genetic PSO outperforms the polygonal approximation approaches based on genetic algorithms and ant colony algorithms. The text was submitted by the author in English. Peng-Yeng Yin was born in 1966 and received his B.S., M.S. and Ph.D. degrees in Computer Science from National Chiao Tung University, Hsinchu, Taiwan, in 1989, 1991 and 1994, respectively. From 1993 to 1994, he was a visiting scholar at the Department of Electrical Engineering, University of Maryland, and the Department of Radiology, Georgetown University. In 2000, he was a visiting Associate Professor in the Visualization and Intelligent Systems Lab (VISLab) at the Department of Electrical Engineering, University of California, Riverside (UCR). He is currently a Professor at the Department of Information Management, National Chi Nan University, Nantou, Taiwan. His current research interests include image processing, pattern recognition, machine learning, computational biology, and evolutionary computation. He has published more than 70 articles in refereed journals and conferences. Dr. Yin received the Overseas Research Fellowship from the Ministry of Education in 1993 and Overseas Research Fellowship from the National Science Council in 2000. He is a member of the Phi Tau Phi Scholastic Honor Society and listed in Who’s Who in the World.     

Multi-level genetic algorithm for the resource-constrained re-entrant scheduling problem in the flow shop

The re-entrant flow shop scheduling problem (RFSP) is regarded as a NP-hard problem and attracted the attention of both researchers and industry. Current approach attempts to minimize the makespan of RFSP without considering the interdependency between the resource constraints and the re-entrant probability. This paper proposed Multi-level genetic algorithm (GA) by including the co-related re-entrant possibility and production mode in multi-level chromosome encoding. Repair operator is incorporated in the Multi-level genetic algorithm so as to revise the infeasible solution by resolving the resource conflict. With the objective of minimizing the makespan, Multi-level genetic algorithm (GA) is proposed and ANOVA is used to fine tune the parameter setting of GA. The experiment shows that the proposed approach is more effective to find the near-optimal schedule than the simulated annealing algorithm for both small-size problem and large-size problem.     

Observations on using genetic-algorithms for channel allocation in mobile computing

This paper highlights the potential of using genetic algorithms to solve cellular resource allocation problems. The objective in this work is to gauge how well a GA-based channel borrower performs when compared to a greedy borrowing heuristic. This is needed to establish how suited GA-like (stochastic search) algorithms are for the solution of optimization problems in mobile computing environments. This involves the creation of a simple mobile networking resource environment and design of a GA-based channel borrower that works within this environment. A simulation environment is also built to compare the performance of the GA-based channel-borrowing method with the heuristic. To enhance the performance of the GA, extra attention is paid to developing an improved mutation operator. The performance of the new operator is evaluated against the heuristic borrowing scheme. For a real-time implementation, the GA needs to have the properties of a micro GA strategy. This involves making improvements to the crossover operator and evaluation procedure so the GA can converge to a "good" solution rapidly.     

Derivative and GA-based methods in metamodeling of back-propagation neural networks for constrained approximate optimization

Artificial neural networks (ANN) have been extensively used as global approximation tools in the context of approximate optimization. ANN traditionally minimizes the absolute difference between target outputs and approximate outputs thereby resulting in approximate optimal solutions being sometimes actually infeasible when it is used as a metamodel for inequality constraint functions. The paper explores the development of the efficient back-propagation neural network (BPN)-based metamodel that ensures the constraint feasibility of approximate optimal solution. The BPN architecture is optimized via two approaches of both derivative-based method and genetic algorithm (GA) to determine interconnection weights between layers in the network. The verification of the proposed approach is examined by adopting a standard ten-bar truss problem. Finally, a GA-based approximate optimization of suspension with an optical flying head is conducted to enhance the shock resistance capability in addition to dynamic characteristics.     

GA-based principal component selection for production performance estimation in mineral processing

In this paper, a genetic algorithm (GA) based principal component selection approach is proposed for production performance estimation in mineral processing. The approach combines a modified GA with principal component analysis (PCA) in order to improve the estimation accuracy of production performance. In this context, the extended chromosome encoding, the fitness function formed by combining the prediction performance operator and the penalty function is designed based on the standard GA. Both the mutation allele number operator and the allele mutation possibility operator are also introduced in the mutation process of chromosome. The proposed approach can select the principal components which are crucial for estimation performance, and the useful message from PCA can guide the evolution of GA and accelerate the convergence process. The case studies have been carried out on the prediction of the production rate and concentrate grade of a mineral process and the experimental results show the effectiveness of the proposed approach.     

约束优化问题的改进遗传算法设计

遗传算子是影响遗传算法优化效果的重要因素,针对目前遗传算法研究中对约束优化问题求解的不足,提出基于退火思想的退火选择算子和加权适应度算子,并给出了退火选择算子和加权适应度算子设计方法及其计算过程.在此基础上与现有的遗传算子结合,提出一种新的改进遗传算法,分析了改进遗传算法与基于罚函数遗传算法之间在原理上的区别.最后以两个测试函数为算例对算法进行了性能测试,结果表明改进的遗传算法具有良好的优化性能,能获得更好的优化结果.