Many real-world problems often have several, usually conflicting objectives. Traditional multi-objective optimization problems (MOPs) usually search for the Pareto-optimal solutions for this predicament. A special cla...
详细信息
ISBN:
(纸本)9781479974924
Many real-world problems often have several, usually conflicting objectives. Traditional multi-objective optimization problems (MOPs) usually search for the Pareto-optimal solutions for this predicament. A special class of MOPs, the convex hull maximization problems which prefer solutions on the convex hull, has posed a new challenge for existing approaches for solving traditional MOPs, as a solution on the Pareto front is not necessarily a good solution for convex hull maximization. In this work, the difference between traditional MOPs and the convex hull maximization problems is discussed and a new evolutionary Convex Hull Maximization algorithm (ECHMA) is proposed to solve the convex hull maximization problems. Specifically, a Convex Hull-based sorting with Convex Hull of Individual Minima (CH-CHIM-sorting) is introduced, as well as a novel selection scheme, Extreme Area Extract-based selection (EAE-selection). Experimental results show that ECHMA significantly outperforms the existing approaches for convex hull maximization and evolutionarymulti-objective optimization approaches in achieving a better approximation to the convex hull more stably and with a more uniformly distributed set of solutions.
evolutionaryalgorithm provides a framework that is largely applicable to particular problems including multiobjective optimization problems, basically for the ease of their implementation and their capability to perf...
详细信息
evolutionaryalgorithm provides a framework that is largely applicable to particular problems including multiobjective optimization problems, basically for the ease of their implementation and their capability to perform efficient parallel search. Indeed, in some cases, expensive multiobjective optimization evaluations might be a challenge to restrict the number of explicit fitness evaluations in multiobjectiveevolutionaryalgorithms. Accordingly, this article presents a novel approach that tackles this problem so as to not only decrease the number of fitness evaluations but also to improve the performance. During evolution, our proposed approach selects fit individuals based on the knowledge acquired throughout the search, and performs explicit fitness evaluations on these individuals. A comprehensive comparative analysis of a wide range of well-established test problems, selected from both traditional and state-of-the-art benchmarks, has been presented. Afterward, the effectiveness of the obtained results is compared with some of the state-of-the-art methods using two well-known metrics-i.e. Hypervolume and Inverted Generational Distance (IGD). The experiments of our implemented approach is performed to illustrate that our proposal seems to be promising and would prove more efficient than other approaches in terms of both the performance and the computational cost.
The receiver operating characteristics (ROC) analysis has gained increasing popularity for analyzing the performance of classifiers. In particular, maximizing the convex hull of a set of classifiers in the ROC space, ...
详细信息
The receiver operating characteristics (ROC) analysis has gained increasing popularity for analyzing the performance of classifiers. In particular, maximizing the convex hull of a set of classifiers in the ROC space, namely ROCCH maximization, is becoming an increasingly important problem. In this work, a new convex hull-based evolutionarymulti-objectivealgorithm named ETriCM is proposed for evolving neural networks with respect to ROCCH maximization. Specially, convex hull-based sorting with convex hull of individual minima (CH-CHIM-sorting) and extreme area extraction selection (EAE-selection) are proposed as a novel selection operator. Empirical studies on 7 high-dimensional and imbalanced datasets show that ETriCM outperforms various state-of-the-art algorithms including convex hull-based evolutionarymulti-objectivealgorithm (CH-EMOA) and non-dominated sorting genetic algorithm II (NSGA-II).
Biologically inspired Autonomous Underwater Vehicles (AUVs) have been developed in the recent decades. Tis thesis focuses on the AUVs that are biologically inspired by snakes, called Underwater Snake Robots (USRs). A ...
详细信息
Biologically inspired Autonomous Underwater Vehicles (AUVs) have been developed in the recent decades. Tis thesis focuses on the AUVs that are biologically inspired by snakes, called Underwater Snake Robots (USRs). A well-known issue of the USRs, or any AUVs, is the long- term autonomy. To achieve this, energy efcient approaches are required. Many studies have considered single-objective optimization problems regarding the energy efciency of the USR, but almost none with multi-objective Optimization Problems (MOPs). Tis thesis presents MOPs of diferent locomotions of the USR. Te presented MOPs consider the energy efcient optimiza- tion of maximizing the forward velocity, while minimizing the power consumption of the USR. For computing the efcient motion paterns, two multi-objective evolutionary algorithms (MOEAs) called Non-dominated Sort Genetic algorithm II (NSGA-II), and Hypervolume Estimation Algo- rithm for multi-objective Optimization (HypE) are applied. A challenging topic of the USR, is their adaptability of diferent locomotions. Diferent locomotions of the USR give rise to diferent search spaces for optimization. We present simulation studies of the two most common snake locomotions: (i) lateral undulation and (ii) eel-like motion. Furthermore, we also present and in- vestigate three altered motion patern of the USR. Te aim of the altered locomotions is to let the MOEAs generate efcient locomotions through evolutionary, which we do not know the gait of. From the simulation results, it turns out that one of the altered motion patern approximates a motion similar to the lateral undulation. Tis motion patern is generated based on Fourier se- ries. Te obtained simulation results are based on optimization with optimal Genetic algorithm (GA) parameters, found by numerous presimulations of the MOPs. Since this is multi-objective optimization problems, the end results will be in the form of Pareto fronts. Tese Pareto fronts can be used as trade-ofs for selecting th
This paper proposes a fast evolutionaryalgorithm based on a tree structure for multi-objective optimization. The tree structure, named dominating tree (DT), is able to preserve the necessary Pareto dominance relation...
详细信息
This paper proposes a fast evolutionaryalgorithm based on a tree structure for multi-objective optimization. The tree structure, named dominating tree (DT), is able to preserve the necessary Pareto dominance relations among individuals effectively, contains the density information implicitly, and reduces the number of comparisons among individuals significantly. The evolutionaryalgorithm based on dominating tree (DTEA) integrates the convergence strategy and diversity strategy into the DT and employs a DT-based eliminating strategy that realizes elitism and preserves population diversity without extra time and space costs. Numerical experiments show that DTEA is much faster than SPEA2, NSGA-II and an improved version of NSGA-II, while its solution quality is competitive with those of SPEA2 and NSGA-II. Crown Copyright (C) 2009 Published by Elsevier B.V. All rights reserved.
This article demonstrates the practical applications of a multi-objective evolutionary algorithm (MOEA) namely population-based incremental learning (PBIL) for an automated shape optimization of plate-fin heat sinks. ...
详细信息
This article demonstrates the practical applications of a multi-objective evolutionary algorithm (MOEA) namely population-based incremental learning (PBIL) for an automated shape optimization of plate-fin heat sinks. The computational procedure of multi-objective PBIL is detailed. The design problem is posed to find heat sink shapes which minimize the junction temperature and fan pumping power while meeting predefined constraints. Three sets of shape design variables used in this study are defined as: vertical straight fins with fin height variation, oblique straight fins with steady fin heights, and oblique straight fins with fin height variation. The optimum results obtained from using the various sets of design variables are illustrated and compared. It can be said that, with this sophisticated design system, efficient and effective design of plate-fin heat sinks is achievable and the best design variables set is the oblique straight fins with fin height variation.
Clustering is an unsupervised learning technique that groups data into clusters using the entire conditions. However, sometimes, data is similar only under a subsetof conditions. Biclustering allows clustering of rows...
详细信息
ISBN:
(纸本)9781467372206
Clustering is an unsupervised learning technique that groups data into clusters using the entire conditions. However, sometimes, data is similar only under a subsetof conditions. Biclustering allows clustering of rows and columns of a dataset simultaneously. It extracts more accurate information from sparse datasets. In recent years, biclustering has found many useful applications in different fields and many biclustering algorithms have been proposed. Using both row and column information of data, biclustering requires the optimization of two conflicting objectives. In this study, a new multi-objectiveevolutionary biclustering framework using SPEA2 is proposed. A heuristic local search based on the gene and condition deletion and addition is added into SPEA2 and the best bicluster is selected usinga new quantitative measure that considers both its coherence and size. The performance of our algorithm is evaluatedusing simulated and gene expression data and compared with several well-known biclustering methods. The experimental results demonstrate better performance with respect to the size and MSR of detected biclusters and significant enrichment of detected genes.
Space station logistics strategy optimisation is a complex engineering problem with multiple objectives. Finding a decision-maker-preferred compromise solution becomes more significant when solving such a problem. How...
详细信息
Space station logistics strategy optimisation is a complex engineering problem with multiple objectives. Finding a decision-maker-preferred compromise solution becomes more significant when solving such a problem. However, the designer-preferred solution is not easy to determine using the traditional method. Thus, a hybrid approach that combines the multi-objective evolutionary algorithm, physical programming, and differential evolution (DE) algorithm is proposed to deal with the optimisation and decision-making of space station logistics strategies. A multi-objective evolutionary algorithm is used to acquire a Pareto frontier and help determine the range parameters of the physical programming. Physical programming is employed to convert the four-objective problem into a single-objective problem, and a DE algorithm is applied to solve the resulting physical programming-based optimisation problem. Five kinds of objective preference are simulated and compared. The simulation results indicate that the proposed approach can produce good compromise solutions corresponding to different decision-makers' preferences.
This paper presents an early attempt to solve one-to-many-to-one dynamic pickup-and-delivery problem (DPDP) by proposing a multi-objective memetic algorithm called LSH-MOMA, which is a synergy of multi-objective evolu...
详细信息
This paper presents an early attempt to solve one-to-many-to-one dynamic pickup-and-delivery problem (DPDP) by proposing a multi-objective memetic algorithm called LSH-MOMA, which is a synergy of multi-objective evolutionary algorithm and locality-sensitive hashing (LSH) based local search. Three objectives namely route length, response time, and workload are optimized simultaneously in an evolutionary framework. In each generation of LSH-MOMA, LSH-based rectification and local search are imposed to repair and improve the individual solutions. LSH-MOMA is evaluated on four benchmark DPDPs and the experimental results show that LSH-MOMA is efficient in obtaining optimal tradeoff solutions of the three objectives. (C) 2015 Elsevier Inc. All rights reserved.
Energy savings have become an essential consideration in sustainable manufacturing projects due to the associated environmental impacts and constraints on carbon emissions. In the past, machining operations primarily ...
详细信息
Energy savings have become an essential consideration in sustainable manufacturing projects due to the associated environmental impacts and constraints on carbon emissions. In the past, machining operations primarily examined technological consideration (e.g., machining quality) and neglected energy consumption. Therefore, this paper investigates an energy-efficient multi-pass turning operation problem and establishes a multi-objectivemulti-pass turning operations model. Energy consumption and machining quality are both considered in this problem. Although several models of this problem have considered these criteria, the objectives are usually combined into a single objective using a weighted sum approach, which results in poor non-dominated solutions. To obtain high quality trade-offs between the two challenging objectives, a novel multi-objective backtracking search algorithm is proposed to solve this multi-objective optimization problem. To verify the feasibility and validity of the proposed algorithm, it is compared with other classical multi-objective metaheuristics on multi-objectivemulti pass turning operations. This study's experimental results demonstrate that the proposed algorithm significantly outperforms other algorithms for this optimization problem, which is a significant result regarding practical application. (C) 2016 Elsevier Ltd. All rights reserved.
暂无评论