检索结果-内蒙古大学图书馆

IEEE Symposium Series on Computational Intelligence (SSCI)

作者： Simone Parisi Alexander Blank Tobias Viernickel Jan Peters Intelligent Autonomous Systems Group Technical University of Darmstadt Darmstadt Germany Max Planck Institute for Intelligent Systems Tübingen Germany

ISBN: (纸本)9781509042418

Many real-world applications are characterized by multiple conflicting objectives. In such problems, optimality is replaced by Pareto optimality and the goal is to find the Pareto frontier, a set of solutions representing different compromises among the objectives. Despite recent advances in multi-objective optimization, the selection, given the Pareto frontier, of a Pareto-optimal policy is still an important problem, prominent in practical applications such as economics and robotics. In this paper, we present a versatile approach for selecting a policy from the Pareto frontier according to user-defined preferences. Exploiting a novel scalarization function and heuristics, our approach provides an easy-to-use and effective method for Pareto-optimal policy selection. Furthermore, the scalarization is applicable in multiple-policy learning strategies for approximating Pareto frontiers. To show the simplicity and effectiveness of our algorithm, we evaluate it on two problems and compare it to classical multi-objective reinforcement learning approaches.

关键词： Approximation algorithms Heuristic algorithms optimization Gold Economics Robots Learning (artificial intelligence)

来源：评论

学校读者我要写书评

暂无评论

A multi objective FLND problem under uncertain environment using robust optimization: A heuristic approach and case study

A multi objective FLND problem under uncertain environment u...

引用

International Conference on Industrial Engineering (ICIE)

作者： Davood Shishebori Abolghasem Yousefi-Babadi Ashkan Davoudi Yazd University Yazd Iran University of Tehran Tehran Iran Mazandaran university of science and technology Mazamdaran Iran

ISBN: (纸本)9781509004591

In this paper, a robust multi objective mixed integer linear programming model is proposed for a robust facility location network design problem, which takes uncertain parameters (including demand and transfer costs) into the account. The proposed model simultaneously minimizes the total operating costs and maximizes the total coverage. Moreover, an investment budget constraint is raised on facility location and link construction. Therefore, this model determines the optimal locations of new facilities, link roads that should be constructed and also demand nodes covered by these facilities and link roads. Then, the proposed model is robust by suitable approaches. An efficient multi objective approach, based on Lp-metrics- is proposed and tested for several test problems. A practical case study, based on an integrated distribution system, is presented in detail to illustrate the application of the proposed mathematical model. Finally, a sensitivity analysis is done to provide an insight into the behavior of the proposed model in response to changes of key parameters of the problem.

关键词： Robustness Mathematical model optimization Investment Uncertainty Linear programming Stochastic processes

来源：评论

学校读者我要写书评

暂无评论

Genetic Algorithms in the Framework of Dempster-Shafer Theory of Evidence for Maintenance optimization Problems

引用

IEEE TRANSACTIONS ON RELIABILITY 2015年第2期64卷 645-660页

作者： Compare, Michele Zio, Enrico Politecn Milan Dept Energy I-20133 Milan Italy Ecole Cent Paris & Supelec European Fdn New Energy Elect France Syst Sci & Energet Challenge Paris France

The aim of this paper is to address the maintenance optimization problem when the maintenance models encode stochastic processes, which rely on parameters that are imprecisely known, and when these parameters are only determined through information elicited from experts. A genetic algorithms (GA)-based technique is proposed to deal with such uncertainty setting;this approach requires addressing three main issues: i) the representation of the uncertainty in the parameters and its propagation onto the fitness values;ii) the development of a ranking method to sort the obtained uncertain fitness values, in case of single-objective optimization;and iii) the definition of Pareto dominance, for multi-objective optimization problems. A known hybrid Monte Carlo-Dempster-Shafer Theory of Evidence method is used to address the first issue, whereas two novel approaches are developed for the second and third issues. For verification, a practical case study is considered concerning the optimization of maintenance for the nozzle system of a turbine in the Oil & Gas industry.

关键词： Evidence theory genetic algorithms pareto dominance maintenance optimization

来源：评论

学校读者我要写书评

暂无评论

A deterministic multiobjective optimizer

引用

COMPEL-THE INTERNATIONAL JOURNAL FOR COMPUTATION AND MATHEMATICS IN ELECTRICAL AND ELECTRONIC ENGINEERING 2015年第5期34卷 1351-1363页

作者： Alotto, Piergiorgio Capasso, Giampaolo Univ Padua Dipartimento Ingn Ind Padua Italy

Purpose - To the purpose of this paper is to show the main features of the Direct multisearch method and how it can be enhanced and hybridized without compromising its mathematical properties. Design/methodology/approach - The study is based on a mathematical analysis of the properties of the method which is then validated with analytical benchmarks and tested on a problem related to magnetic- assisted surgery. Findings - The presented multi-objective optimizer, based on an extension of the well-known Pattern Search (PS) method, due to its deterministic nature, enjoys provable convergence properties. Furthermore, the method is successfully extended by hybridizing it with some stochastic approaches in order to improve its performance. Numerical examples show the effectiveness of the developed approach which can be used as a general and robust tool for multi-objective optimization. In a specific application, related to magnetic- assisted surgery, the proposed algorithm achieved 100 percent detection accuracy under realistic test conditions. practical implications - Due to the provable convergence characteristics of the algorithm, the presented technique can be applied to problems where minima must be identified with very high accuracy. Originality/value - The paper presents enhanced and hybridized versions of the PS algorithm.

关键词： Electromagnetics Pareto optimization Pattern search Direct multisearch Deterministic optimization stochastic optimization

来源：评论

学校读者我要写书评

暂无评论

Bi-criterion procedures to support logistics decision making: cost and uncertainty

引用

JOURNAL OF THE OPERATIONAL RESEARCH SOCIETY 2015年第12期66卷 2086-2091页

作者： Rijpkema, Willem A. Hendrix, Eligius M. T. Rossi, Roberto Wageningen Univ NL-6706 KN Wageningen Netherlands Univ Malaga E-29071 Malaga Spain Univ Edinburgh Edinburgh Midlothian Scotland

In practical decision making, one often is interested in solutions that balance multiple objectives. In this study we focus on generating efficient solutions for optimization problems with two objectives and a large but finite number of feasible solutions. Two classical approaches exist, being the constraint method and the weighting method, for which a specific implementation is required for this problem class. This paper elaborates specific straightforward implementations and applies them to a practical allocation problem, in which transportation cost and risk of shortage in supplied livestock quality are balanced. The variability in delivered quality is modelled using a scenario-based model that exploits historical farmer quality delivery data. The behaviour of both implementations is illustrated on this specific case, providing insight in (i) the obtained solutions, (ii) their computational efficiency. Our results indicate how efficient trade-offs in bi-criterion problems can be found in practical problems.

关键词： multi-objective optimization allocation problems scenario-based modelling constraint method weighting method stochastic programming

来源：评论

学校读者我要写书评

暂无评论

Self-Configuring Ensemble of Neural Network Classifiers for Emotion Recognition in the Intelligent Human-Machine Interaction

Self-Configuring Ensemble of Neural Network Classifiers for ...

引用

IEEE Symposium Series Computational Intelligence

作者： Sopov, Evgenii Ivanov, Ilia Siberian State Aerosp Univ Dept Syst Anal & Operat Res Krasnoyarsk Russia

ISBN: (纸本)9781479975600

Reducing the dimensionality of datasets and configuring learning algorithms for solving particular practical tasks are the main problems in machine learning. In this work we propose multi-objective optimization approach to feature selection and base learners hyper-parameter optimization. The effectiveness of the proposed multi-objective approach is compared to the single-objective approach. We have chosen emotion recognition problem by audio-visual data as a benchmark for comparing the two mentioned approaches. We have chosen neural network as a base learning algorithm for testing the proposed approach to parameter optimization. As a result of multi-objective optimization applied to parameter configuration we get the Pareto set of neural networks with optimal parameter values. In order to get the single output, the Pareto optimal neural networks were combined into an ensemble. We have examined several ensemble model fusion techniques including voting, average class probabilities and meta-classification. According to results, multi-objective optimization approach to feature selection provides an average 2.8% better emotion classification rate on the given datasets than single-objective approach. multi-objective approach is 5.4% more effective compared to principal components analysis, and 13.9% more effective compared to not using any dimensionality reduction at all. multi-objective approach applied to neural networks parameter optimization provided on average 7.1% better classification rate than single-objective approach. The results suggest that the proposed multi-objective optimization approach is more effective at solving considered emotion recognition problem.

关键词： multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

Modeling and optimization of multi objective non-linear programming problem in intuitionistic fuzzy environment

引用

APPLIED MATHEMATICAL MODELLING 2015年第16期39卷 4617-4629页

作者： Singh, Sujeet Kumar Yadav, Shiv Prasad Indian Inst Technol Dept Math Roorkee 247667 Uttar Pradesh India

In dealing with real world practical optimization problems, a decision maker usually faces a state of uncertainty as well as hesitation, due to various unpredictable factors. Sometimes it is necessary to optimize, several non-linear and conflicting objectives simultaneously. To deal with the uncertain parameters which arise in such situations, intuitionistic fuzzy numbers are utilized. We formulate a multiobjective non-linear programming problem in intuitionistic fuzzy environment. We propose a linear ranking function and utilize it to convert the intuitionistic fuzzy model into a crisp model. After converting the problem into equivalent crisp problem, we propose a non-linear membership function and develop various approaches for solving it by using different operators and fuzzy programming technique. We apply our methodologies for justification to a numerical problem in manufacturing systems. (C) 2015 Elsevier Inc. All rights reserved.

关键词： multiple objective programming Intuitionistic fuzzy number Accuracy function Nonlinear programming

来源：评论

学校读者我要写书评

暂无评论

Sensitivity analysis of pareto solution sets of multiobjective optimization for a batch cooling crystallization process

Sensitivity analysis of pareto solution sets of multiobjecti...

引用

Indian Control Conference (ICC)

作者： Kilari Hemalatha Kalipatnapu Yamuna Rani Chemical Engineering Division CSIR-Indian Institute of Chemical Technology Academy of scientific and innovative research (AcSIR) CSIR-IICT Hyderabad Telangana India

An increased interest in pharmaceutical crystallization has been observed in recent years where the product quality is affected by variations in product crystal size distribution, purity, and morphology of the crystals which in turn affect the downstream processes such as filtration, milling, and eventually, formulation. Therefore, it is necessary to ascertain the optimal operation of the process in terms of optimal temperature policies in order to achieve the desired product crystal size distribution. In this work, the optimization of an unseeded batch cooling crystallization of paracetamol within a multi-objective framework is studied. The weight mean size and coefficient of variation of final crystals are considered as objectives, which give rise to a set of optimal solutions known as Pareto-optimal solutions using non-dominated sorting genetic algorithm. The present work focuses on evaluating the sensitivity of optimal solutions for induced disturbances and uncertainties in process model mismatch during practical applications through simulation and optimization. It has been observed that the selection of a cooling profile exerts a strong influence on final product crystal size distribution which reiterates the importance of optimization and control in batch cooling crystallization processes industrially at a large scale. Further, in this study, an initial attempt has been made to provide some directions regarding solution approaches to the sensitivity issues.

关键词： Crystallization Cooling optimization Solvents Trajectory

来源：评论

学校读者我要写书评

暂无评论

Towards the standardization of distributed Embodied Evolution

引用

INFORMATION SCIENCES 2015年 312卷 55-77页

作者： Prieto, A. Bellas, F. Trueba, P. Duro, R. J. Univ A Coruna Integrated Grp Engn Res Ferrol 15403 A Coruna Spain

The Embodied Evolution (EE) paradigm arose in the early 2000s as a response to the automatic design of distributed control systems in real time for teams of autonomous robots. The interest for this type of evolutionary approach has been increasing steadily, not only in its native field of robotics, but also in other fields related to distributed optimization problems since previous works have shown its capability to outperform traditional evolutionary techniques when the scenario requires an on-line coordination of the team. Most of the activity in this research field has been eminently practical, meaning that authors have focused their efforts on developing EE algorithms and variations adapted to solve very specific practical cases. The problem that arises is that, on one hand, all these dissimilar variations of the basic EE structure produce an unclear state of the art and, on the other, that there is a high dependence between the performance obtained by the algorithms and the specific problems where they have been tested, which complicates extrapolating conclusions to different scenarios. As a consequence, this work has two main objectives, namely, designing and implementing a standard EE algorithm that captures the more general principles of this paradigm and that can be applied to any distributed optimization problem, and analyzing how its parameters influence the performance of the algorithms in a set of theoretical representative problems so that objective and reliable conclusions about the behavior of EE can be obtained. At the same time, this work presents an analysis of the evaluation criteria required for coordination tasks when using decentralized distributed approaches, which has influenced both, the definition of the algorithm and the selection of experimental set to test it. (C) 2015 Elsevier Inc. All rights reserved.

关键词： Embodied Evolution Evolutionary computation Distributed optimization Collective intelligence multi-robot system

来源：评论

学校读者我要写书评

暂无评论

multi-objective optimization coupled with dimension-wise polynomial-based approach in smart well placement under model uncertainty

Multi-objective optimization coupled with dimension-wise pol...

引用

SPE Reservoir Simulation Symposium 2015

作者： Chang, Yuqing Petvipusit, Kurt R. Devegowda, Deepak University of Oklahoma United States International Research Institute of Stavanger Norway Imperial College London United Kingdom

ISBN: (纸本)9781510800618

Targeting hydrocarbon-rich zones and locating smart wells optimally are critical to oil and gas field development. With model uncertainty being one of the main considerations in well placement, there are several challenges associated with the statistical inference from objective distributions which are normally unknown a priori and the estimation may become computationally intensive. To overcome these challenges, we use a robust multi-objective optimization approach to handle model uncertainty and propose an efficient polynomial-based technique to accelerate optimization process. To handle model uncertainty, we implement an evolutionary multi-objective optimization algorithm (NSGA-II) with a mean-variance approach to seek robust solutions for well placement, where the robustness is considered for the uncertainty of formation characteristics. To assist the optimization process, we apply a polynomial-based sparse grid interpolation approach coupled with the multi-objective optimization algorithm. This workflow is demonstrated on a reservoir case study where the results indicate that the optimization approach leads to improved decision making capabilities by providing a suite of well planning solutions. This work highlights the advantage of utilizing the polynomial-based approach - The computational cost from multi-objective optimization can be substantially reduced in comparison to traditional approaches, which makes the proposed workflow more practical, rapid and repeatable, thus able to assist the decision making process in large field development. Copyright © 2015, Society of Petroleum Engineers.

关键词： Polynomials

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：