MDA-TOEPGA:A novel method to identify miRNA-disease association based on two-objective evolutionary programming genetic algorithm

The association between miRNA and disease has attracted more and more attention.Until now,existing methods for identifying miRNA related disease mainly rely on top-ranked association model,which may not provide a full landscape of association between miRNA and disease.Hence there is strong need of new computational method to identify the associations from miRNA group view.In this paper,we proposed a framework,MDA-TOEPGA,to identify miRNAdisease association based on two-objective evolutionary programming genetic algorithm,which identifies latent miRNAdisease associations from the view of functional module.To understand the miRNA functional module in diseases,the case study is presented.We have been compared MDA-TOEPGA with several state-of-the-art functional module algorithm.Experimental results showed that our method cannot only outperform classical algorithms,such as K-means,IK-means,MCODE,HC-PIN,and ClusterONE,but can also achieve an ideal overall performance in terms of a composite score consisting of f1,Sensitivity,and Accuracy.Altogether,our study showed that MDA-TOEPGA is a promising method to investigate miRNA-disease association from the landscapes of functional module.

Evolution Performance of Symbolic Radial Basis Function Neural Network by Using Evolutionary Algorithms

Radial Basis Function Neural Network(RBFNN)ensembles have long suffered from non-efficient training,where incorrect parameter settings can be computationally disastrous.This paper examines different evolutionary algorithms for training the Symbolic Radial Basis Function Neural Network(SRBFNN)through the behavior’s integration of satisfiability programming.Inspired by evolutionary algorithms,which can iteratively find the nearoptimal solution,different Evolutionary Algorithms(EAs)were designed to optimize the producer output weight of the SRBFNN that corresponds to the embedded logic programming 2Satisfiability representation(SRBFNN-2SAT).The SRBFNN’s objective function that corresponds to Satisfiability logic programming can be minimized by different algorithms,including Genetic Algorithm(GA),Evolution Strategy Algorithm(ES),Differential Evolution Algorithm(DE),and Evolutionary Programming Algorithm(EP).Each of these methods is presented in the steps in the flowchart form which can be used for its straightforward implementation in any programming language.With the use of SRBFNN-2SAT,a training method based on these algorithms has been presented,then training has been compared among algorithms,which were applied in Microsoft Visual C++software using multiple metrics of performance,including Mean Absolute Relative Error(MARE),Root Mean Square Error(RMSE),Mean Absolute Percentage Error(MAPE),Mean Bias Error(MBE),Systematic Error(SD),Schwarz Bayesian Criterion(SBC),and Central Process Unit time(CPU time).Based on the results,the EP algorithm achieved a higher training rate and simple structure compared with the rest of the algorithms.It has been confirmed that the EP algorithm is quite effective in training and obtaining the best output weight,accompanied by the slightest iteration error,which minimizes the objective function of SRBFNN-2SAT.

Web mining based on chaotic social evolutionary programming algorithm

With an aim to the fact that the K-means clustering algorithm usually ends in local optimization and is hard to harvest global optimization, a new web clustering method is presented based on the chaotic social evolutionary programming （CSEP） algorithm. This method brings up the manner of that a cognitive agent inherits a paradigm in clustering to enable the cognitive agent to acquire a chaotic mutation operator in the betrayal. As proven in the experiment, this method can not only effectively increase web clustering efficiency, but it can also practically improve the precision of web clustering.

An Evolutionary Algorithm Based on a New Decomposition Scheme for Nonlinear Bilevel Programming Problems

In this paper, we focus on a class of nonlinear bilevel programming problems where the follower’s objective is a function of the linear expression of all variables, and the follower’s constraint functions are convex with respect to the follower’s variables. First, based on the features of the follower’s problem, we give a new decomposition scheme by which the follower’s optimal solution can be obtained easily. Then, to solve efficiently this class of problems by using evolutionary algorithm, novel evolutionary operators are designed by considering the best individuals and the diversity of individuals in the populations. Finally, based on these techniques, a new evolutionary algorithm is proposed. The numerical results on 20 test problems illustrate that the proposed algorithm is efficient and stable.

Multi-objective Evolutionary Algorithms for MILP and MINLP in Process Synthesis

Steady-state non-dominated sorting genetic algorithm (SNSGA), a new form of multi-objective genetic algorithm, is implemented by combining the steady-state idea in steady-state genetic algorithms (SSGA) and the fitness assignment strategy of non-dominated sorting genetic algorithm (NSGA). The fitness assignment strategy is improved and a new self-adjustment scheme of is proposed. This algorithm is proved to be very efficient both computationally and in terms of the quality of the Pareto fronts produced with five test problems including GA difficult problem and GA deceptive one. Finally, SNSGA is introduced to solve multi-objective mixed integer linear programming (MILP) and mixed integer non-linear programming (MINLP) problems in process synthesis.

基于CGA的MPI程序分支覆盖测试套件生成

针对程序的分支覆盖测试,元启发式搜索技术已经被广泛应用于测试数据生成中。然而,当前的研究成果主要适用于串行程序。因此,为覆盖消息传递接口(Message Passing Interface,MPI)程序的分支,该文研究基于协同进化遗传算法(Co-evolutionary Genetic Algorithm,CGA)的测试套件生成方法(简称为:CGA生成法),该方法具有不受不可行分支影响的优势。首先,基于收集覆盖信息的探针,定义最小归一化分支距离,并以此设计出相应的适应度值函数;然后,使用CGA生成进化个体,并基于设计的适应度值函数,计算这些个体的适应值;最后,基于计算的适应值,选择子种群中代表个体,以构成合作种群。所提CGA生成法应用于7个基准MPI程序,并与其他多种方法进行比较。实验结果表明,CGA生成法的覆盖率通常高于其他搜索算法。

神经网络中克服局部最小的BP-EP混合算法

人工神经网络在很多领域有着成功的应用 .神经网络有许多学习算法 ,BP算法是前向多层神经网络的典型算法 ,但 BP算法有时会陷入局部最小解 .进化规划 (EP)是一种随机优化技术 ,它可以发现全局最优解 .当网络学习过程陷入局部最小时 ,利用 EP确定 BP算法中的学习速率 ,使学习过程逸出局部最小 .

一种基于并行GEP的复杂电路优化算法

数字电路设计的优化是演化硬件中的研究热点,传统的优化方法主要是利用代数法和卡诺图求解法,但是在规模较大时却难于求出或无法求出最优的电路结构。提出一种新的基于并行基因表达式程序设计优化复杂数字电路的算法(COPGEP),该算法通过各子种群之间优良个体的迁移,有效地传播优良个体,充分发挥了优良个体的导向作用,提高了传统GEP的全局寻优能力以及求解精度和收敛速度。通过仿真实验表明,该算法比传统GEP收敛速度更快,能够克服传统GEP算法在优化变量个数多于5个的数字逻辑电路时收敛速度慢,甚至不收敛等缺点。

一种改进的GEP方法及其在演化建模预测中的应用

为了提高预测的准确性,结合基于突变算子的基因表达式和一种基于群体搜索技术的演化算法,提出了改进的GEP方法,并用其对数据进行演化建模。实例测试的结果表明,使用改进的GEP方法得到的模型要优于GP和单纯的GEP方法得到的模型,本方法具有良好的拟合度和预测精度。

基于语义聚类的遗传规划算法比较

针对遗传规划算法容易陷入局部最优解与局部搜索过慢的问题,提出一种基于语义聚类的遗传规划算法(genetic programming algorithm based on semantic clustering,SCGP),比较不同聚类算法对SCGP表现的影响。同时提出一种基于子种群规模的自适应适应度函数,提高局部搜索能力。在多个基准问题上对比标准遗传规划、几何语义遗传规划、K均值聚类遗传规划与SCGP,实验结果表明,SCGP算法在拟合能力和泛化能力上都有较大改善。在诸多聚类方法中,层次聚类嵌入的SCGP算法在基准问题上的泛化能力最优,与标准遗传规划、几何语义遗传规划、K均值聚类遗传规划相比,分别提高了32.36%、61.29%、20.53%。

一种基于GEP的多层物流网络Prüfer编码优化算法

在对Prüfer编码研究的基础上,提出了一种基于基因表达式程序设计的多层物流网络Prüfer编码优化算法(GEPPCOA)。该算法一方面利用基因表达式程序设计的多基因结构特点,克服了传统演化算法中不能直接用个体表示多层物流模式的缺点;另一方面还对基因表达式程序设计原有的操作算子进行了针对Prüfer编码的改进。实验结果表明,使用GEPPCOA求解多层物流网络的Prüfer编码优化问题时,其各项支出费用性能指标均要好于传统的演化算法,提高了算法的收敛精度。

学习驱动的分布式异构混合流水车间批量流能效调度优化

本文研究了分布式异构混合流水车间批量流能效调度问题,其中每个工厂的加工效率不同,工件可以分割成若干子批进入加工系统.以最大完成时间和总能耗为优化目标,建立了混合整数规划模型.本文提出了一种学习驱动的多目标进化算法,包括学习驱动的全局搜索和局部搜索.引入Q学习作为学习引擎,以种群和非支配解集的评价作为环境反馈信号,通过不断的学习来动态指导搜索操作的选择;基于问题特征,设计了算法的状态集、动作集和奖励机制.Q学习的引入能够及时感知当前搜索的状态,减少搜索操作的盲目性,提高搜索的效率.通过对仿真数据集的测试,表明所提出算法能够有效地求解分布式异构混合流水车间批量流能效调度问题.

A Tentative Research on Complexity of Automatic Programming

In this paper, based on the following theoretical framework: Evolutionary Algorithms + Program Structures = Automatic Programming , some results on complexity of automatic programming for function modeling is given, which show that the complexity of automatic programming is an exponential function of the problem dimension N , the size of operator set ｜F｜ and the height of the program parse tree H . Following this results, the difficulties of automatic programming are discussed. Some function models discovered automatically from database by evolutionary modeling method are given, too.

模糊自适应多细胞GEP函数优化算法

为提高传统GEP算法的全局搜索能力,提出一种基于模糊控制的多细胞基因表达式编程算法(multicellular GEP algorithm based on fuzzy control,MGEP-FC)。通过构建模糊隶属函数,对算法的交叉率、变异率和实数集变异率的大小进行描述,根据种群中个体适应度值的集中和分散程度,动态调整遗传操作的交叉率、变异率和实数集变异率。为使种群的多样性在迭代过程中得到延续,设计一种遗传操作方案,将产生的新个体与父代种群结合构建临时种群,临时种群和子代种群的多样性均得到优化。12个Benchmark的函数寻优实验结果表明,该算法在稳定性、全局收敛能力和寻优速度等方面都得到了显著提升。

一种染色体自适应GEP算法

GEP是一种源于遗传算法(GA)和遗传编程(GP)的进化算法,结合了GA的定长线性编码和GP的树形解码,发现公式的能力很强。传统GEP在迭代过程中采用固定交叉率和变异率,对寻优过程造成巨大局限性。通过GEP种群染色体自适应,调整交叉率和变异率,有利于个体的个性化发展。4个benchmark函数的符号回归实验表明,改进后的GEP比传统GEP寻优效果更优。

Evolutionary programming CLEAN algorithm for UWB localization images of contiguous targets

In this article, a novel scattering center extraction method using genetic algorithm is proposed to deal with the ultra-wideband （UWB） localization image, which is called evolutionary programming （EP） CLEAN algorithm. Because of the UWB characters, the ideal point scattering model and EP method are used in the algorithm for optimizing the UWB localization images. After introducing the algorithm detail, the actual model is used to realize the EP CLEAN algorithm. Compared with the conventional localization imaging algorithm, this algorithm has advantages fitting the UWB characters such as accuracy, robustness, and better resolution, which are verified by the numerical simulations. Therefore the EP CLEAN algorithm could improve localization image performance to expand the UWB technique application.

多目标优化的演化算法

近年来 ,多目标优化问题求解已成为演化计算的一个重要研究方向 ,而基于Pareto最优概念的多目标演化算法则是当前演化计算的研究热点 .多目标演化算法的研究目标是使算法种群快速收敛并均匀分布于问题的非劣最优域 .该文在比较与分析多目标优化的演化算法发展的历史基础上 ,介绍基于Pareto最优概念的多目标演化算法中的一些主要技术与理论结果 ,并具体以多目标遗传算法为代表 ,详细介绍了基于偏好的个体排序、适应值赋值以及共享函数与小生境等技术 .此外 。

基因表达式程序设计的GRCM方法

基因表达式程序设计是一种基于基因组和表现型组的新型遗传算法,该算法在运行时具有很高的运行效率,实验表明在求解很多问题的时候比遗传程序设计在速度上优越两个数量级以上。在基因表达式的基础上,提出了基因阅读运算器方法,此方法不需要把染色体转换为表达式树,而是直接对染色体进行操作得到该染色体的适应值。实验表明,采用这种方法不仅简单有效,而且能提高运算的速度。

基于基因表达式编程的自动聚类方法

为了解决聚类算法不能自动聚类的问题,提出并实现了自动聚类算法GEP-Cluster算法。主要工作包括:1)研究了基于GEP进化的最优簇划分;2)提出了自动合并簇算法Auto Merge Cluster Algorithm;3)实现了不需预知簇个数的聚类;4)在合成数据集上的实验表明,采用GEP-Cluster算法在未知簇划分信息的情况下可对数据集自动进行聚类分析,聚类成功率达到96%。

一个通用的混合非线性规划问题的演化算法

提出了一种新的求解非线性规划问题的演化算法 .它是在郭涛算法的基础上提出来的 ,新算法的主要特点是引入了变维子空间 ,加入了子空间搜索过程和规范化约束条件以及增加了处理带等式约束的实数规划、整数规划、0 - 1规划和混合整数规划问题的功能 ,使之成为一种求解非线性规划 (NL P)问题的通用算法 .数值实验表明 ,新算法不仅是一种通用的算法 ,而且与已有算法的计算结果相比 ,其解的精确度也最好 .