检索结果-内蒙古大学图书馆

An efficient estimation of distribution algorithm with rank-one modification and population reduction

BIOSYSTEMS 2019年 181卷 58-70页

作者： Liang, Yongsheng Ren, Zhigang He, Miao Wang, Lin Cao, Jianfu Chen, An Pang, Bei Xi An Jiao Tong Univ Dept Automat Sci & Technol Sch Elect & Informat Engn 28 Xianning West Rd Xian 710049 Shaanxi Peoples R China Airworthiness Certificat Ctr CAAC Xian Aircraft Certificat Ctr Xian Shaanxi Peoples R China Northwest Univ Sch Informat Sci & Technol Xian Shaanxi Peoples R China Guangdong Xian Jiaotong Univ Acad Xian Shaanxi Peoples R China

As a type of model-based metaheuristic, estimation of distribution algorithms (EDAs) show certain advantages over other metaheuristics by using statistical learning method to estimate the distribution of promising solutions. However, the commonly-used Gaussian EDAs (GEDAs) usually suffer from premature convergence that severely limits their efficiency. In this paper, we first attempt to enhance the performance of GEDA by improving its model estimation method. The new estimation method shifts the weighted mean of high-quality solutions towards the fitness improvement direction and estimates the covariance matrix by taking the shifted mean as the center. Theoretical analyses show that the new covariance matrix is essentially a rank-one modification (R1M) of the original one. It could effectively adjust both the search scope and the search direction of GEDA, and thus improving the search efficiency. Furthermore, considering the importance of the population size tuning in GEDA, we develop a population reduction (PR) strategy which linearly reduces the population size throughout the evolution. By this means, the exploration and exploitation ability of GEDA could be balanced better in different search stages and a more proper utilization of limited computation resource can be achieved. Combining GEDA with the R1M and PR strategies, a novel EDA variant named EDA-R1M-PR is developed. The performance of EDA-R1M-PR was comprehensively evaluated and compared with that of several state-of-the-art evolutionary algorithms. Experimental results indicate that the R1M and PR strategies effectively enhance the global optimization ability of GEDA and the resultant EDA-R1M-PR significantly outperforms its competitors on a set of benchmark functions.

关键词： estimation of distribution algorithms Premature convergence Rank-one modification population reduction

来源：评论

学校读者我要写书评

暂无评论

Fast feature selection using a simple estimation of distribution algorithm: a case study on splice site prediction

引用

BIOINFORMATICS 2003年第SUP2期19卷 II179-II188页

作者： Saeys, Yvan Degroeve, Sven Aeyels, Dirk Van de Peer, Yves Rouze, Pierre Univ Ghent VIB Dept Plant Syst Biol B-9000 Ghent Belgium Univ Ghent SYSTeMS Res Grp B-9052 Zwijnaarde Belgium Univ Ghent Lab Associe INRA France B-9000 Ghent Belgium

Motivation: Feature subset selection is an important preprocessing step for classification. In biology, where structures or processes are described by a large number of features, the elimination of irrelevant and redundant information in a reasonable amount of time has a number of advantages. It enables the classification system to achieve good or even better solutions with a restricted subset of features, allows for a faster classification, and it helps the human expert focus on a relevant subset of features, hence providing useful biological knowledge. Results: We present a heuristic method based on estimation of distribution algorithms to select relevant subsets of features for splice site prediction in Arabidopsis thaliana. We show that this method performs a fast detection of relevant feature subsets using the technique of constrained feature subsets. Compared to the traditional greedy methods the gain in speed can be up to one order of magnitude, with results being comparable or even better than the greedy methods. This makes it a very practical solution for classification tasks that can be solved using a relatively small amount of discriminative features (or feature dependencies), but where the initial set of potential discriminative features is rather large.

关键词： Machine Learning Feature Subset Selection estimation of distribution algorithms Splice Site Prediction

来源：评论

学校读者我要写书评

暂无评论

A NOVEL MULTI-OBJECTIVE estimation OF distribution ALGORITHM BASED ON SENSITIVITY OF OBJECTIVE FUNCTION

引用

INTERNATIONAL JOURNAL OF INNOVATIVE COMPUTING INFORMATION AND CONTROL 2013年第6期9卷 2543-2566页

作者： Seo, Hyunshik Lee, Chaewoo Ajou Univ Dept Elect & Comp Engn San 5 Suwon 443749 South Korea

Most multi-objective optimization problems (MOPs) have a set of optimal trade-off solutions known as the Pareto-optimal solutions since the objectives in MOPs are usually in conflict with one another. Recently proposed estimation of distribution algorithms (EDAs) build a probability distribution model based on the probabilistic information about decision variables of solutions, and then produce new solutions from the model. In the algorithms, the modeling technique enables the initial large search space to be reduced to small promising solution space during the search. However, the existing EDAs might be inefficient at generating the promising solutions since they depend on the information extracted from the decision variables of current solutions expected to approach the optimal solutions. For effective modeling of the promising solutions, we firstly introduce new information about the relationship between decision variables and objective functions;this information is called sensitivity of objective function. Secondly, we propose a multi-objective estimation of distribution algorithm based on the sensitivity of objective function (MOEDA-S). In the MOEDA-S, the sensitivity-based distribution modeling adapts to the current search strategy such that the convergence-focused search at the beginning part of the search is changed to a diversity-focused search at the latter part of the search. MOEDA-S is compared with two other leading multi-objective evolutionary algorithms on a set of test instances. The simulation results show that MOEDA-S outperforms the two compared algorithms in terms of both convergence and diversity performances of the solutions.

关键词： Multi-objective optimization problems Multi-objective evolutionary algorithms estimation of distribution algorithms Variables sensitivity-based modeling

来源：评论

学校读者我要写书评

暂无评论

Exploring the probabilistic graphic model of a hybrid multi-objective Bayesian estimation of distribution algorithm

引用

APPLIED SOFT COMPUTING 2018年 73卷 328-343页

作者： Martins, Marcella S. R. Delgado, Myriam Luders, Ricardo Santana, Roberto Goncalves, Richard A. de Almeida, Carolina P. Univ Tecnol Fed Parana Curitiba Parana Brazil Univ Basque Country San Sebastian Spain State Univ Midwest Parana Guarapuava PR Brazil

The Hybrid Multi-objective Bayesian estimation of distribution Algorithm (HMOBEDA) has shown to be very competitive for Many Objective Optimization Problems (MaOPs). The Probabilistic Graphic Model (PGM) of HMOBEDA expands the possibilities for exploration as it provides the joint probability of decision variables, objectives, and configuration parameters of an embedded local search. This work investigates different sampling mechanisms of HMOBEDA, applying the considered approaches to two different combinatorial MaOPs. Moreover, the paper provides a broad set of statistical analyses on its PGM model. These analyses have been carried out to evaluate how the interactions among variables, objectives and local search parameters are captured by the model and how information collected from different runs can be aggregated and explored in a Probabilistic Pareto Front. In experiments, two variants of HMOBEDA are compared with the original version, each one with a different set of evidences fixed during the sampling process. Results for instances of multi-objective knapsack problem with 2-5 and 8 objectives show that the best variant outperforms the original HMOBEDA in terms of convergence and diversity in the solution set. This best variant is then compared with five state-of-the-art evolutionary algorithms using the knapsack problem instances as well as a set of MNK-landscape instances with 2, 3, 5 and 8 objectives. HMOBEDA outperforms all of them.

关键词： Multi-objective optimization estimation of distribution algorithms Automatic algorithm configuration

来源：评论

学校读者我要写书评

暂无评论

Inductive Logic Programming Through estimation of distribution Algorithm

Inductive Logic Programming Through Estimation of Distributi...

引用

IEEE Congress on Evolutionary Computation (CEC)

作者： Pitangui, Cristiano Grijo Zaverucha, Gerson Univ Fed Rio de Janeiro Rio De Janeiro RJ Brazil

ISBN: (纸本)9781424478354

Genetic algorithms (GAs) are known for their capacity to explore large search spaces and due to this ability, they were to some extent applied to Inductive Logic Programming (ILP) problem. Although estimation of distribution algorithms (EDAs) perform better in most problems when compared to standard GAs, this kind of algorithm have not been applied to ILP. This work presents an ILP system based on EDA. Preliminary results show that the proposed system is superior when compared to a "standard" GA and it is very competitive when compared to the state of the art ILP system Aleph.

关键词： Inductive Logic Programming estimation of distribution algorithms Probabilistic Models

来源：评论

学校读者我要写书评

暂无评论

An Novel estimation of distribution Algorithm for TSP

An Novel Estimation of Distribution Algorithm for TSP

引用

International Conference on Mechatronics, Robotics and Automation (ICMRA 2013)

作者： Yu, Fahong Liao, Weizhi Chen, Meijia Jiaxing Univ Coll Math & Informat Engn Jiaxing Peoples R China Guangxi Univ Guangxi Experiment Ctr Sci & Technol Nanning 530004 Peoples R China Jiaxing Univ Ctr Econom Managing Experiment Jiaxing Peoples R China Guangxi Teachers Educ Univ Coll Comp & Informat Engn Nanning Peoples R China

ISBN: (纸本)9783037858066

estimation of distribution algorithms (EDAs) is a method for solving NP-hard problem. But it is hard to find global optimization quickly for some problems, especially for traveling salesman problem (TSP) that is a classical NP-hard combinatorial optimization problem. To solve TSP effectively, a novel estimation of distribution algorithm (NEDA) is provided, which can solve the conflict between population diversity and algorithm convergence. The experimental results show that the performance of NEDA is effective.

关键词： traveling salesman problem estimation of distribution algorithms probabilistic model

来源：评论

学校读者我要写书评

暂无评论

Probabilistic Analysis of Pareto Front Approximation for a Hybrid Multi-objective Bayesian estimation of distribution Algorithm 6

Probabilistic Analysis of Pareto Front Approximation for a H...

引用

6th Brazilian Conference on Intelligent Systems (BRACIS)

作者： Martins, Marcella S. R. Delgado, Myriam Luders, Ricardo Santana, Roberto Goncalves, Richard A. de Almeida, Carolina P. Univ Tecnol Fed Parana Curitiba Parana Brazil Univ Basque Country Leioa Spain Midwest State Univ Parana Curitiba Parana Brazil

ISBN: (纸本)9781538624074

Metaheuristics that explore the decision variables space to construct probabilistic modeling from promising solutions, like estimation of distribution algorithms (EDAs), are becoming very popular in the context of Multi-objective Evolutionary algorithms (MOEAs). The probabilistic model used in EDAs captures certain statistics of problem variables and their interdependencies. Moreover, the incorporation of local search methods tends to achieve synergy of MOEAs' operators and local heuristics aiming to improve the performance. In this work, we aim to scrutinize the probabilistic graphic model (PGM) presented in Hybrid Multi-objective Bayesian estimation of distribution Algorithm (HMOBEDA), which is based on a Bayesian network. Different from traditional EDA-based approaches, the PGM of HMOBEDA provides the joint probability of decision variables, objectives, and configuration parameters of an embedded local search. HMOBEDA has shown to be very competitive on instances of Multi-Objective Knapsack Problem (MOKP), outperforming state-of-the-art approaches. Two variants of HMOBEDA are proposed in this paper using different sample methods. We aim to compare the learnt structure in terms of the probabilistic Pareto Front approximation produced at the end of evolution. Results on instances of MOKP with 2 to 8 objectives show that both proposed variants outperform the original approach, providing not only the best values for hypervolume and inverted generational distance indicators, but also a higher diversity in the solution set.

关键词： Multi-objective optimization estimation of distribution algorithms automatic algorithm configuration

来源：评论

学校读者我要写书评

暂无评论

On the convergence of an estimation of distribution algorithm based on linkage discovery and factorization 05

On the convergence of an estimation of distribution algorith...

引用

Genetic and Evolutionary Computation Conference

作者： Wright, Alden H. Pulavarty, S. V. P. M. Sandeep Univ Montana Missoula MT 59812 USA

ISBN: (纸本)1595930108

estimation of distribution algorithms construct an explicit model of the problem to be solved, and then use this model to guide the search for good solutions. For an important class of fitness functions, namely those with k-bounded epistasis, it is possible to construct a complete explicit representation of the fitness function by sampling the fitness function. A very natural model of the problem to be solved is the Boltzmann distribution of the fitness function, which is an exponential of the fitness normalized to a probability distribution. As the exponentiation factor (inverse temperature) of the Boltzmann distribution is increased, probability is increasingly concentrated on the set of optimal points. We show that for fitness functions of k-bounded epistasis that satisfy an additional property called the running intersection property, an explicit computable exact factorization of the Boltzmann distribution with an arbitrary exponentiation factor can be constructed. This factorization allows the Boltzmann distribution to be efficiently sampled, which leads to an algorithm which finds the optimum with high probability.

关键词： genetic algorithms estimation of distribution algorithms Boltzmann distribution factorization

来源：评论

学校读者我要写书评

暂无评论

estimation of distribution Algorithm based on a Multivariate Extension of the Archimedean Copula

Estimation of Distribution Algorithm based on a Multivariate...

引用

1st BRICS Countries Congress on Computational Intelligence / 11th Brazilian Congress on Computational Intelligence (BRICS-CCI and CBIC)

作者： de Mello, Harold D., Jr. Abs da Cruz, Andre V. Vellasco, Marley M. B. R. Pontifical Catholic Univ Rio de Janeiro Dept Elect Engn Rio De Janeiro RJ Brazil

ISBN: (纸本)9781479931941

This paper presents a Copula-based estimation of distribution Algorithm with Parameter Updating for numeric optimization problems. This model implements an estimation of distribution algorithm using a multivariate extension of the Archimedean copula (MEC-EDA) to estimate the conditional probability for generating a population of individuals. Moreover, the model uses traditional crossover and elitism operators during the optimization. We show that this approach improves the overall performance of the optimization when compared to other copula-based EDAs.

关键词： continuous numeric optimization evolutionary computation estimation of distribution algorithms copulas

来源：评论

学校读者我要写书评

暂无评论

Magnetic Particle Swarm Optimization with estimation of distribution

Magnetic Particle Swarm Optimization with Estimation of Dist...

引用

IEEE Congress on Evolutionary Computation (CEC)

作者： Prampero, Paulo S. Attux, Romis Fed Inst Sci Technol & Educ Sao Paulo Campus Salto Salto Brazil FEEC Univ Campinas Dept Comp Engn & Ind Automat Campinas Brazil

ISBN: (纸本)9781424478354

The magnetic particle swarm (MPS) algorithm is an approach based on the phenomenon dipole repulsion by a magnetic field. In this paper, a new version of this algorithm, which employs an estimation of distribution step as an additional search heuristic, is proposed and applied to seven well-known test functions for 30-dimensional, 120-dimensional and 1000-dimensional search spaces. The performance of the new approach is compared to that of benchmark differential evolution and estimation of distribution methods, and the results reveal its potential in terms of multimodal search in the context of complex optimization tasks.

关键词： particle swarm optimization magnetic particle swarm global search methods differential evolution estimation of distribution algorithms

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：