Showing papers on "Genetic algorithm published in 2003"
TL;DR: This study provides a rigorous analysis of the limitations underlying this type of quality assessment in multiobjective evolutionary algorithms and develops a mathematical framework which allows one to classify and discuss existing techniques.
Abstract: An important issue in multiobjective optimization is the quantitative comparison of the performance of different algorithms. In the case of multiobjective evolutionary algorithms, the outcome is usually an approximation of the Pareto-optimal set, which is denoted as an approximation set, and therefore the question arises of how to evaluate the quality of approximation sets. Most popular are methods that assign each approximation set a vector of real numbers that reflect different aspects of the quality. Sometimes, pairs of approximation sets are also considered. In this study, we provide a rigorous analysis of the limitations underlying this type of quality assessment. To this end, a mathematical framework is developed which allows one to classify and discuss existing techniques.
3,702 citations
TL;DR: In this paper, the authors used intrinsic and extrinsic measures of model performance to determine whether optimal models can be identified based on objective intrinsic criteria, without resorting to an independent test data set.
1,138 citations
TL;DR: In this paper, the authors considered the application of a genetic algorithm (GA) to the basic vehicle routing problem (VRP), in which customers of known demand are supplied from a single depot.
779 citations
TL;DR: It is shown that the improved GA performs better than the standard GA based on some benchmark test functions and a neural network with switches introduced to its links is proposed that can learn both the input-output relationships of an application and the network structure using the improvedGA.
Abstract: This paper presents the tuning of the structure and parameters of a neural network using an improved genetic algorithm (GA). It is also shown that the improved GA performs better than the standard GA based on some benchmark test functions. A neural network with switches introduced to its links is proposed. By doing this, the proposed neural network can learn both the input-output relationships of an application and the network structure using the improved GA. The number of hidden nodes is chosen manually by increasing it from a small number until the learning performance in terms of fitness value is good enough. Application examples on sunspot forecasting and associative memory are given to show the merits of the improved GA and the proposed neural network.
760 citations
TL;DR: It is argued that the development of newMOEAs cannot converge onto a single new most efficient MOEA because the performance of MOEAs shows characteristics of multiobjective problems.
Abstract: Over the last decade, a variety of evolutionary algorithms (EAs) have been proposed for solving multiobjective optimization problems. Especially more recent multiobjective evolutionary algorithms (MOEAs) have been shown to be efficient and superior to earlier approaches. An important question however is whether we can expect such improvements to converge onto a specific efficient MOEA that behaves best on a large variety of problems. In this paper, we argue that the development of new MOEAs cannot converge onto a single new most efficient MOEA because the performance of MOEAs shows characteristics of multiobjective problems. While we point out the most important aspects for designing competent MOEAs in this paper, we also indicate the inherent multiobjective tradeoff in multiobjective optimization between proximity and diversity preservation. We discuss the impact of this tradeoff on the concepts and design of exploration and exploitation operators. We also present a general framework for competent MOEAs and show how current state-of-the-art MOEAs can be obtained by making choices within this framework. Furthermore, we show an example of how we can separate nondomination selection pressure from diversity preservation selection pressure and discuss the impact of changing the ratio between these components.
732 citations
TL;DR: In this study, differential evolution has been analyzed as a candidate global optimization method for feed-forward neural networks and seems not to provide any distinct advantage in terms of learning rate or solution quality.
Abstract: An evolutionary optimization method over continuous search spaces, differential evolution, has recently been successfully applied to real world and artificial optimization problems and proposed also for neural network training However, differential evolution has not been comprehensively studied in the context of training neural network weights, ie, how useful is differential evolution in finding the global optimum for expense of convergence speed In this study, differential evolution has been analyzed as a candidate global optimization method for feed-forward neural networks In comparison to gradient based methods, differential evolution seems not to provide any distinct advantage in terms of learning rate or solution quality Differential evolution can rather be used in validation of reached optima and in the development of regularization terms and non-conventional transfer functions that do not necessarily provide gradient information
599 citations
TL;DR: This paper discusses several advanced genetic algorithms that have proved to be efficient in solving difficult design problems and gives an overview of applications of genetic algorithms to different domains of engineering design.
Abstract: Design is a complex engineering activity, in which computers are more and more involved. The design task can often be seen as an optimization problem in which the parameters or the structure describing the best quality design are sought. Genetic algorithms constitute a class of search algorithms especially suited to solving complex optimization problems. In addition to parameter optimization, genetic algorithms are also suggested for solving problems in creative design, such as combining components in a novel, creative way. Genetic algorithms transpose the notions of evolution in Nature to computers and imitate natural evolution. Basically, they find solution(s) to a problem by maintaining a population of possible solutions according to the ‘survival of the fittest’ principle. We present here the main features of genetic algorithms and several ways in which they can solve difficult design problems. We briefly introduce the basic notions of genetic algorithms, namely, representation, genetic operators, fitness evaluation, and selection. We discuss several advanced genetic algorithms that have proved to be efficient in solving difficult design problems. We then give an overview of applications of genetic algorithms to different domains of engineering design.
484 citations
01 Dec 2003
TL;DR: An evolutionary algorithm based framework, a combination of modified breeder genetic algorithms incorporating characteristics of classic genetic algorithms, is utilized to design an offline/online path planner for unmanned aerial vehicles (UAVs) autonomous navigation, providing near-optimal curved paths quickly and efficiently.
Abstract: An evolutionary algorithm based framework, a combination of modified breeder genetic algorithms incorporating characteristics of classic genetic algorithms, is utilized to design an offline/online path planner for unmanned aerial vehicles (UAVs) autonomous navigation. The path planner calculates a curved path line with desired characteristics in a three-dimensional (3-D) rough terrain environment, represented using B-spline curves, with the coordinates of its control points being the evolutionary algorithm artificial chromosome genes. Given a 3-D rough environment and assuming flight envelope restrictions, two problems are solved: i) UAV navigation using an offline planner in a known environment, and, ii) UAV navigation using an online planner in a completely unknown environment. The offline planner produces a single B-Spline curve that connects the starting and target points with a predefined initial direction. The online planner, based on the offline one, is given on-board radar readings which gradually produces a smooth 3-D trajectory aiming at reaching a predetermined target in an unknown environment; the produced trajectory consists of smaller B-spline curves smoothly connected with each other. Both planners have been tested under different scenarios, and they have been proven effective in guiding an UAV to its final destination, providing near-optimal curved paths quickly and efficiently.
453 citations
08 Apr 2003
TL;DR: In this paper, state-of-the-art MOEAs have been compared on the basis of their ability to converge to Pareto front, diversity of obtained non-dominated solutions and running time.
Abstract: MOEAs are getting immense popularity in the recent past, mainly because of their ability to find a wide spread of Pareto-optimal solutions in a single simulation run. Various evolutionary approaches to multi-objective optimization have been proposed since 1985. Some of fairly recent ones are NSGA-II, SPEA2, PESA (which are included in this study) and others. They all have been mainly applied to two to three objectives. In order to establish their superiority over classical methods and demonstrate their abilities for convergence and maintenance of diversity, they need to be tested on higher number of objectives. In this study, these state-of-the-art MOEAs have been investigated for their scalability with respect to the number of objectives (2 to 8). They have also been compared on the basis of -(1) Their ability to converge to Pareto front, (2) Diversity of obtained non-dominated solutions and (3) Their running time. Four scalable test problems (DTLZ1, 2, 3 and 6) are used for the comparative study.
451 citations
TL;DR: How genetic algorithms may be applied to experimental design for fMRI is described, and the GA framework is used to explore the space of possible fMRI design parameters, with the goal of providing information about optimal design choices for several types of designs.
437 citations
TL;DR: A unified extension of the basic method to predict not only the network structure but also its dynamics using a Genetic Algorithm and an S-system formalism is proposed and successfully inferred the dynamics of a small genetic network constructed with 60 parameters for 5 network variables and feedback loops using only time-course data of gene expression.
Abstract: Motivation: The modeling of system dynamics of genetic networks, metabolic networks or signal transduction cascades from time-course data is formulated as a reverse-problem. Previous studies focused on the estimation of only network structures, and they were ineffective in inferring a network structure with feedback loops. We previously proposed a method to predict not only the network structure but also its dynamics using a Genetic Algorithm (GA) and an S-system formalism. However, it could predict only a small number of parameters and could rarely obtain essential structures. In this work, we propose a unified extension of the basic method. Notable improvements are as follows: (1) an additional term in its evaluation function that aims at eliminating futile parameters; (2) a crossover method called Simplex Crossover (SPX) to improve its optimization ability; and (3) a gradual optimization strategy to increase the number of predictable parameters. Results: The proposed method is implemented as a C program called PEACE1 (Predictor by Evolutionary Algorithms and Canonical Equations 1). Its performance was compared with the basic method. The comparison showed that: (1) the convergence rate increased about 5-fold; (2) the optimization speed was raised about 1.5-fold; and (3) the number of predictable parameters was increased about 5-fold. Moreover, we successfully inferred the dynamics of a small genetic network constructed with 60 parameters for 5 network variables and feedback loops using only time-course data of gene expression.
TL;DR: The results indicate that the particle swarm optimization algorithm does locate the constrained minimum de-sign in continuous applications with very good precision, albeit at a much highercomputational cost than that of a typical gradient based optimizer.
Abstract: Gerhard Venter (gventer_vrand.conl) *Vanderpla(ds Research and Development, bit.1767 S 8th St'reef. Suite 100, Colorado Springs. CO 80906Jaroslaw Sobieszczanski-Sobieski (j.sobieski:_larc.nasa.gov) *A_4SA Lcmgley Research Ce,_terMS 240, Hampton, I:4 23681-2199The purpose of this paper is to show how the search algorithm, known as par-ticle swarm optimization performs. Here, particle swarm optimization ks appliedto structural design problems, but the method.has a much wider range of possi-ble applications. The paper's new contributions are improvements to the particleswarm optimization algorithm and conclusions and recommendations as to theutility of the algorithm. Results of numerical experiments for both continuousand discrete applications are presented in the paper. The results indicate that theparticle swarm optimization algorithm does locate the constrained minimum de-sign in continuous applications with very good precision, albeit at a much highercomputational cost than that of a typical gradient based optimizer. However, thetrue potential of particle swarm optimization is primarily in applications withdiscrete and/or discontinuous functions and variables. Additionally, particleswarm optimization has the potential of e3_icient computation with very largenumbers of concurrently operating processors.
TL;DR: In this article, the authors introduce a new technique called species conservation for evolving parallel subpopulations, which is based on the concept of dividing the population into several species according to their similarity.
Abstract: This paper introduces a new technique called species conservation for evolving parallel subpopulations. The technique is based on the concept of dividing the population into several species according to their similarity. Each of these species is built around a dominating individual called the species seed. Species seeds found in the current generation are saved (conserved) by moving them into the next generation. Our technique has proved to be very effective in finding multiple solutions of multimodal optimization problems. We demonstrate this by applying it to a set of test problems, including some problems known to be deceptive to genetic algorithms.
TL;DR: In this article, a taxonomy of real-coded genetic algorithms based on real-number representation is presented, where the crossover operator is used to generate the genes of the offspring of the parent from the parents.
Abstract: The main real-coded genetic algorithm (RCGA) research effort has been spent on developing efficient crossover operators. This study presents a taxonomy for this operator that groups its instances in different categories according to the way they generate the genes of the offspring from the genes of the parents. The empirical study of representative crossovers of all the categories reveals concrete features that allow the crossover operator to have a positive influence on RCGA performance. They may be useful to design more effective crossover models. © 2003 Wiley Periodicals, Inc. Genetic algorithms (GAs) are adaptive methods based on natural evolution that may be used for search and optimization problems. They process a population of search space solutions with three operations: selection, crossover, and mutation. 1‐3 Under their initial formulation, the search space solutions are coded using the binary alphabet; however, other coding types have been taken into account for the representation issue such as real coding. The real coding approach seems particularly natural when tackling optimization problems of parameters with variables in continuous domains. A chromosome is a vector of floating point numbers in which their size is kept the same as the length of the vector, which is the solution to the problem. GAs based on real-number representation are called real-coded GAs
TL;DR: In this paper, a modified price penalty factor is proposed to solve the combined economic emission dispatch (CEED) problem by considering both the economy and emission objectives, which is converted into a single objective function using a Price Penalty Factor approach.
Abstract: Economic load dispatch (ELD) and economic emission dispatch (EED) have been applied to obtain optimal fuel cost and optimal emission of generating units, respectively. Combined economic emission dispatch (CEED) problem is obtained by considering both the economy and emission objectives. This biobjective CEED problem is converted into a single objective function using a price penalty factor approach. A novel modified price penalty factor is proposed to solve the CEED problem. In this paper, evolutionary computation (EC) methods such as genetic algorithm (GA), micro GA (MGA), and evolutionary programming (EP) are applied to obtain ELD solutions for three-, six-, and 13-unit systems. Investigations showed that EP was better among EC methods in solving the ELD problem. EP-based CEED problem has been tested on IEEE 14-, 30-, and 118-bus systems with and without line flow constraints. A nonlinear scaling factor is also included in EP algorithm to improve the convergence performance for the 13 units and IEEE test systems. The solutions obtained are quite encouraging and useful in the economic emission environment.
03 Nov 2003
TL;DR: This paper presents a special genetic algorithm, which especially takes into account the existing bounds on the generalization error for support vector machines (SVMs), which is compared to the traditional method of performing cross-validation and to other existing algorithms for feature selection.
Abstract: The problem of feature selection is a difficult combinatorial task in machine learning and of high practical relevance, e.g. in bioinformatics. genetic algorithms (GAs) offer a natural way to solve this problem. In this paper, we present a special genetic algorithm, which especially takes into account the existing bounds on the generalization error for support vector machines (SVMs). This new approach is compared to the traditional method of performing cross-validation and to other existing algorithms for feature selection.
TL;DR: The results demonstrate the capabilities of the proposed approach to generate true and well-distributed Pareto-optimal nondominated solutions of the multiobjective EED problem in one single run.
TL;DR: A self-adaptive fitness formulation for solving constrained optimization problems by representing the constraint violations by a single infeasibility measure, which requires no parameter tuning and can be used as a fitness evaluator with any evolutionary algorithm.
Abstract: A self-adaptive fitness formulation is presented for solving constrained optimization problems. In this method, the dimensionality of the problem is reduced by representing the constraint violations by a single infeasibility measure. The infeasibility measure is used to form a two-stage penalty that is applied to the infeasible solutions. The performance of the method has been examined by its application to a set of eleven test cases from the specialized literature. The results have been compared with previously published results from the literature. It is shown that the method is able to find the optimum solutions. The proposed method requires no parameter tuning and can be used as a fitness evaluator with any evolutionary algorithm. The approach is also robust in its handling of both linear and nonlinear equality and inequality constraint functions. Furthermore, the method does not require an initial feasible solution.
13 Jul 2003
TL;DR: In this article, the authors considered a phasor measurement unit (PMU) placement problem requiring simultaneous optimization of two conflicting objectives, such as minimizing the number of PMUs and maximization of the measurement redundancy.
Abstract: The paper considers a phasor measurement unit (PMU) placement problem requiring simultaneous optimization of two conflicting objectives, such as minimization of the number of PMUs and maximization of the measurement redundancy. The objectives are in conflict, since the improvement of one of them leads to the deterioration of another. Instead of unique optimal solution, it exists a set of best trade-offs between competing objectives, the so-called Pareto-optimal solutions. A specially tailored nondominated sorting genetic algorithm (NSGA) for PMU placement problem is proposed as a methodology to find these Pareto-optimal solutions. The algorithm is combined with the graph-theoretical procedure and a simple GA to reduce initial number of the PMU's candidate locations. The NSGA parameters are carefully set by performing a number of trial runs and evaluating the NSGA performances based on the number of distinct Pareto-optimal solutions found in the particular run and the distance of the obtained Pareto front from the optimal one. Illustrative results on the 39-bus and 118-bus IEEE systems are presented.
TL;DR: In this paper, a niched Pareto genetic algorithm (NPGA) based approach is proposed to solve the multiobjective environmental/economic dispatch (EED) problem, which is formulated as a non-linear constrained multi-objective optimization problem.
01 Sep 2003
TL;DR: An efficient two-step genetic algorithm is described that has been used to build a tool for mapping an application, described by a parameterized task graph, on to a NoC architecture with a two dimensional mesh of switches as a communication backbone.
Abstract: Network on Chip (NoC) is a new paradigm for designing core based System on Chip which supports high degree of reusability and is scalable. In this paper we describe an efficient two-step genetic algorithm that has been used to build a tool for mapping an application, described by a parameterized task graph, on to a NoC architecture with a two dimensional mesh of switches as a communication backbone. The computational resources in NoC consist of a set of heterogeneous IP cores. Our algorithm finds a mapping of the vertices of the task graph to available cores so that the overall execution time of the task graph is minimized. We have developed a NoC architecture specific communication delay model to estimate the execution time. Our algorithm is able to handle large task graphs and provide near optimal mapping in a few minutes on a PC platform. Our tool also provides facilities for specifying NoC architecture, generation and viewing synthetic task graphs and viewing the progress of the genetic algorithm as it converges to a solution.
TL;DR: In this article, a new optimization technique based on genetic algorithms (GA) for the determination of the cutting parameters in machining operations has been proposed, which can be integrated into an intelligent manufacturing system for solving complex machining optimization problems.
Abstract: The paper proposes a new optimization technique based on genetic algorithms (GA) for the determination of the cutting parameters in machining operations. In metal cutting processes, cutting conditions have an influence on reducing the production cost and time and deciding the quality of a final product. This paper presents a new methodology for continual improvement of cutting conditions with GA. It performs the following: the modification of recommended cutting conditions obtained from a machining data, learning of obtained cutting conditions using neural networks and the substitution of better cutting conditions for those learned previously by a proposed GA. Experimental results show that the proposed genetic algorithm-based procedure for solving the optimization problem is both effective and efficient, and can be integrated into an intelligent manufacturing system for solving complex machining optimization problems.
TL;DR: New genetic algorithms are developed, extending the representation and operators previously designed for the single-mode version of the problem with makespan minimisation as the objective and a new fitness function for the individuals who are infeasible is defined.
Abstract: In this paper we consider the Multi-Mode Resource-Constrained Project Scheduling Problem with makespan minimisation as the objective. We have developed new genetic algorithms, extending the representation and operators previously designed for the single-mode version of the problem. Moreover, we have defined a new fitness function for the individuals who are infeasible. We have tested different variants of the algorithm and chosen the best to be compared to different heuristics previously published, using standard sets of instances included in PSPLIB. Results illustrate the good performance of our algorithm.
TL;DR: The aim is to design efficient cGAs by treating them as estimation of distribution algorithms (EDAs) for solving difficult optimization problems without compromising on memory and computation costs.
Abstract: This paper describes two elitism-based compact genetic algorithms (cGAs)-persistent elitist compact genetic algorithm (pe-cGA), and nonpersistent elitist compact genetic algorithm (ne-cGA). The aim is to design efficient cGAs by treating them as estimation of distribution algorithms (EDAs) for solving difficult optimization problems without compromising on memory and computation costs. The idea is to deal with issues connected with lack of memory by allowing a selection pressure that is high enough to offset the disruptive effect of uniform crossover. The pe-cGA finds a near optimal solution (i.e., a winner) that is maintained as long as other solutions generated from probability vectors are no better. The ne-cGA further improves the performance of the pe-cGA by avoiding strong elitism that may lead to premature convergence. It also maintains genetic diversity. This paper also proposes an analytic model for investigating convergence enhancement.
TL;DR: A review of the use of genetic algorithms to solve operations problems and the designs of the genetic algorithms used to solve them is provided.
Abstract: Operations managers and scholars in their search for fast and good solutions to real-world problems have applied genetic algorithms to many problems. While genetic algorithms are promising tools for problem solving, future research will benefit from a review of the problems that have been solved and the designs of the genetic algorithms used to solve them. This paper provides a review of the use of genetic algorithms to solve operations problems. Reviewed papers are classified according to the problems they solve. The basic design of each genetic algorithm is described, the shortcomings of the current research are discussed and directions for future research are suggested.
TL;DR: In this paper, a new model to deal with the short-term generation scheduling problem for hydrothermal systems is proposed using genetic algorithms (GAs), the model handles simultaneously the subproblems of shortterm Hydrothermal coordination, unit commitment, and economic load dispatch.
Abstract: A new model to deal with the short-term generation scheduling problem for hydrothermal systems is proposed. Using genetic algorithms (GAs), the model handles simultaneously the subproblems of short-term hydrothermal coordination, unit commitment, and economic load dispatch. Considering a scheduling horizon period of a week, hourly generation schedules are obtained for each of both hydro and thermal units. Future cost curves of hydro generation, obtained from long and mid-term models, have been used to optimize the amount of hydro energy to be used during the week. In the genetic algorithm (GA) implementation, a new technique to represent candidate solutions is introduced, and a set of expert operators has been incorporated to improve the behavior of the algorithm. Results for a real system are presented and discussed.
TL;DR: The goal of this research is to develop an efficient scheduling method based on genetics algorithm to address JSSP, and the proposed approach yields significant improvement in solution quality.
TL;DR: The MPGA is extended to scheduling problems with three objectives: makespan, TWT, and total weighted completion times (TWC), and also performs better than MOGA.
TL;DR: A new diversity-preserving mechanism is presented, the Genetic Diversity Evaluation Method (GeDEM), which considers a distance-based measure of genetic diversity as a real objective in fitness assignment and provides a dual selection pressure towards the exploitation of current non-dominated solutions and the exploration of the search space.
Abstract: A key feature of an efficient and reliable multi-objective evolutionary algorithm is the ability to maintain genetic diversity within a population of solutions. In this paper, we present a new diversity-preserving mechanism, the Genetic Diversity Evaluation Method (GeDEM), which considers a distance-based measure of genetic diversity as a real objective in fitness assignment. This provides a dual selection pressure towards the exploitation of current non-dominated solutions and the exploration of the search space. We also introduce a new multi-objective evolutionary algorithm, the Genetic Diversity Evolutionary Algorithm (GDEA), strictly designed around GeDEM and then we compare it with other state-of-the-art algorithms on a well-established suite of test problems. Experimental results clearly indicate that the performance of GDEA is toplevel.
10 Nov 2003
TL;DR: This study relates to the determination of a practical method using genetic algorithm in order to obtain the best performance of the production system by solving the flexible job shop scheduling problem according to a set of some criteria.
Abstract: In this paper, we are interested in the multiobjective optimization of the schedule performance in the flexible job shops. The flexible job shop scheduling problem (FJSP) is known in the literature as one of the hardest combinatorial optimization problems and presents many objectives to be optimized. In this way, we aim to solve such a problem according to a set of some criteria, which characterize the feasible solutions of such a problem. The studied criteria are the following: the makespan, the workload of the critical machine, and the total workload of all the machines. Our study relates to the determination of a practical method using genetic algorithm in order to obtain the best performance of the production system. The solution performance is evaluated by comparing the values of the different values of the criteria with the corresponding lower bounds.