scispace - formally typeset
Search or ask a question

Showing papers on "Crossover published in 1996"


Journal ArticleDOI
TL;DR: This paper presents a genetic algorithm (GA) solution to the unit commitment problem using the varying quality function technique and adding problem specific operators, satisfactory solutions to theunit commitment problem were obtained.
Abstract: This paper presents a genetic algorithm (GA) solution to the unit commitment problem. GAs are general purpose optimization techniques based on principles inspired from the biological evolution using metaphors of mechanisms such as natural selection, genetic recombination and survival of the fittest. A simple GA algorithm implementation using the standard crossover and mutation operators could locate near optimal solutions but in most cases failed to converge to the optimal solution. However, using the varying quality function technique and adding problem specific operators, satisfactory solutions to the unit commitment problem were obtained. Test results for power systems of up to 100 units and comparisons with results obtained using Lagrangian relaxation and dynamic programming are also reported.

1,119 citations


03 Oct 1996
TL;DR: Why crowding methods over the last two decades have not made effective niching methods is determined and a series of tests and design modifications results in the development of a highly effective form of crowding, called deterministic crowding.
Abstract: Niching methods extend genetic algorithms to domains that require the location and maintenance of multiple solutions. Such domains include classification and machine learning, multimodal function optimization, multiobjective function optimization, and simulation of complex and adaptive systems. This study presents a comprehensive treatment of niching methods and the related topic of population diversity. Its purpose is to analyze existing niching methods and to design improved niching methods. To achieve this purpose, it first develops a general framework for the modelling of niching methods, and then applies this framework to construct models of individual niching methods, specifically crowding and sharing methods. Using a constructed model of crowding, this study determines why crowding methods over the last two decades have not made effective niching methods. A series of tests and design modifications results in the development of a highly effective form of crowding, called deterministic crowding. Further analysis of deterministic crowding focuses upon the distribution of population elements among niches, that arises from the combination of crossover and replacement selection. Interactions among niches are isolated and explained. The concept of crossover hillclimbing is introduced. Using constructed models of fitness sharing, this study derives lower bounds on the population size required to maintain, with probability $\gamma$, a fixed number of desired niches. It also derives expressions for the expected time to disappearance of a desired niche, and relates disappearance time to population size. Models are presented of sharing under selection, and sharing under both selection and crossover. Some models assume that all niches are equivalent with respect to fitness. Others allow niches to differ with respect to fitness. Focusing on the differences between parallel and sequential niching methods, this study compares and further examines four niching methods--crowding, sharing, sequential niching, and parallel hillclimbing. The four niching methods undergo rigorous testing on optimization and classification problems of increasing difficulty; a new niching-based technique is introduced that extends genetic algorithms to classification problems.

974 citations


Journal ArticleDOI
TL;DR: Several modifications to the basic genetic procedures are proposed including a new fitness-based crossover operator (fusion), a variable mutation rate and a heuristic feasibility operator tailored specifically for the set covering problem.

670 citations


Journal ArticleDOI
TL;DR: In this paper, a multi-objective genetic algorithm was proposed for flow shop scheduling with a concave Pareto front and the performance of the algorithm was examined by applying it to the flowshop scheduling problem with two objectives: minimizing the makespan and minimizing the total tardiness.

502 citations


Proceedings ArticleDOI
19 Jun 1996
TL;DR: The performance of DE on a testbed of 15 functions is compared with a variety of recently published results encompassing many different methods and DE converged for all 15 functions and was the fastest method for solving 11 of them.
Abstract: Differential evolution (DE) is a powerful yet simple evolutionary algorithm for optimizing real-valued multi-modal functions. Function parameters are encoded as floating-point variables and mutated with a simple arithmetic operation. During mutation, a variable-length, one-way crossover operation splices perturbed best-so-far parameter values into existing population vectors. A novel sampling technique adaptively scales the step-size of perturbations as the population evolves. DE's selection criterion demands that improved vectors always be accepted. The performance of DE on a testbed of 15 functions is compared with a variety of recently published results encompassing many different methods. DE converged for all 15 functions and was the fastest method for solving 11 of them. DE's performance on the remaining 4 functions was competitive.

442 citations


Journal ArticleDOI
TL;DR: This paper applies a genetic algorithm to flowshop scheduling problems and examines two hybridizations of the genetic algorithm with other search algorithms, showing two hybrid genetic algorithms: genetic local search and genetic simulated annealing.

396 citations


Journal ArticleDOI
TL;DR: This paper reports on the most extensive set of experiments to date on the location and nature of the crossover point in satisfiability problems, finding no evidence of any hard problems in the under-constrained region.

348 citations


Book ChapterDOI
01 Jan 1996
TL;DR: How genetic programming can evolve the circuit for a difficult-to-design low-pass filter is described.
Abstract: This paper describes an automated process for designing analog electrical circuits based on the principles of natural selection, sexual recombination, and developmental biology. The design process starts with the random creation of a large population of program trees composed of circuit-constructing functions. Each program tree specifies the steps by which a fully developed circuit is to be progressively developed from a common embryonic circuit appropriate for the type of circuit that the user wishes to design. The fitness measure is a user-written computer program that may incorporate any calculable characteristic or combination of characteristics of the circuit. The population of program trees is genetically bred over a series of many generations using genetic programming. Genetic programming is driven by a fitness measure and employs genetic operations such as Darwinian reproduction, sexual recombination (crossover), and occasional mutation to create offspring. This automated evolutionary process produces both the topology of the circuit and the numerical values for each component. This paper describes how genetic programming can evolve the circuit for a difficult-to-design low-pass filter.

277 citations


Journal ArticleDOI
TL;DR: Schema analysis of the algorithm shows that a sexual reproduction with the generalized mutation operator preserves the global convergence property of a genetic algorithm thus establishing the fundamental theorem of the GA for the algorithm.

228 citations



Journal ArticleDOI
TL;DR: In this article, a new method for inversion of surface-wave dispersion data is introduced, which successfully utilizes recently developed genetic algorithms as a global optimization method, which usually consist of selection, crossover, and mutation of individuals in a population.
Abstract: A new method for inversion of surface-wave dispersion data is introduced. This method successfully utilizes recently developed genetic algorithms as a global optimization method. Such algorithms usually consist of selection, crossover, and mutation of individuals in a population. To facilitate convergence to an optimal solution, we added elite selection, which ensures that the “best” individual with the smallest misfit value is not excluded from the succeeding generation, and dynamic mutation, which contains a generation-variant mutation probability. Using synthetic and observed earthquake data, we examined the applicability of this genetic surface-wave inversion method in deducing an S -wave profile for sedimentary layers from short- and intermediate-period surface-wave dispersion data. We demonstrated that the method is robust and can be used to interpret surface-wave dispersion data.

Book ChapterDOI
22 Sep 1996
TL;DR: This paper introduces a new permutation representation for job shop scheduling and shows that a genetic algorithm using an operator which preserves the absolute order also obtains a superior solution quality.
Abstract: In this paper we concentrate on job shop scheduling as a representative of constrained combinatorial problems. We introduce a new permutation representation for this problem. Three crossover operators, different in tending to preserve the relative order, the absolute order, and the position in the permutation, are defined. By experiment we observe the strongest phenotypical correlation between parents and offspring when respecting the absolute order. It is shown that a genetic algorithm using an operator which preserves the absolute order also obtains a superior solution quality.

01 Jan 1996
TL;DR: The effects of elitism, single point and uniform crossover, creep mutation, different random number seeds, population size, niching and the number of children per pair of parents on the performance of the GA for this problem were studied.
Abstract: This paper presents results from the first known application of the genetic algorithm (GA) technique for optimizing the performance of a laser system (chemical, solid-state, or gaseous). The effects of elitism, single point and uniform crossover, creep mutation, different random number seeds, population size, niching and the number of children per pair of parents on the performance of the GA for this problem were studied. Micro-GAs (μGA) were also tested. The best overall performer was the uniform crossover μGA with a population size of 5. The uniform crossover μGA was also able to find the global maximum of an order-3 deceptive function which the other tested GAs failed to optimize.

ReportDOI
01 Jan 1996
TL;DR: PGAPack as mentioned in this paper is a parallel genetic algorithm library that is intended to provide most capabilities desired in a genetic algorithm package, in an integrated, seamless, and portable manner, including the ability to be called from Fortran or C. Easy integration of hill-climbing heuristics.
Abstract: PGAPack is a parallel genetic algorithm library that is intended to provide most capabilities desired in a genetic algorithm package, in an integrated, seamless, and portable manner. Key features of PGAPack are as follows: Ability to be called from Fortran or C. Executable on uniprocessors, multiprocessors, multicomputers, and workstation networks. Binary-, integer-, real-, and character-valued native data types. Object-oriented data structure neutral design. Parameterized population replacement. Multiple choices for selection, crossover, and mutation operators. Easy integration of hill-climbing heuristics. Easy-to-use interface for novice and application users. Multiple levels of access for expert users. Full extensibility to support custom operators and new data types. Extensive debugging facilities. Large set of example problems.

Journal ArticleDOI
TL;DR: It is shown that potentially useful treatment beams can be chosen based on geometric heuristics and that a genetic algorithm can be constructed to find an optimal combination of beams based on a formal objective function.
Abstract: The thesis of this report is that potentially useful treatment beams can be chosen based on geometric heuristics and that a genetic algorithm (GA) can be constructed to find an optimal combination of beams based on a formal objective function. The paper describes the basic principles of a GA and the particular implementation developed. The code represents each plan in the population as two paired lists comprised of beam identifiers and relative weights. Reproduction operators, which mimic sexual reproduction with crossover, mutation, cloning, spontaneous generation, and death, manipulate the lists to grow optimal plans. The necessary gene pool is created by software modules which generate beams, distribute calculation points, obtain clinical constraints, add wedges, and calculate doses. The code has been tested on a set of artificial patients and on four clinical cases: prostate, pancreas, esophagus, and glomus. All demonstrated consistent results, indicating that the code is a reliable optimizer. Additional experiments compared the results for a full set of open beams to the geometrically selected set and the GA code with simulated annealing. Geometric selection of beam directions did not significantly compromise optimization quality. Compared to simulated annealing, the genetic algorithm was equally able to optimize the objective function, and calculations suggest it may be the faster method when the number of beams to be considered exceeds approximately 70.

Journal ArticleDOI
TL;DR: In this work a population of binary strings or ‘chromosomes’ are used, which represent the coded truss design variables, a ‘fitness’ as a ranking measure of the adaptability to the environment, selection criteria and mechanical natural operators such as crossover and mutation are used to improve the population.
Abstract: Genetic algorithms, a search technique which combines Darwinian ‘survival-of-the-fittest’ with randomized well structured information, is applied to the problems of real-world truss optimization. In this work a population of binary strings or ‘chromosomes’, which represent the coded truss design variables, a ‘fitness’ as a ranking measure of the adaptability to the environment, selection criteria and mechanical natural operators such as crossover and mutation are used to improve the population, so that over the generations the genetic algorithm gets better and better and at the end of the convergence, a ‘rebirth’ of the population is used to improve the usual process. An overview of the genetic algorithm will be described, continuing the rebirth effect; then, the chromosome representation of trusses is exposed. Afterwards, the objective scalar function is defined taking into account that it seems reasonable in real world to optimize trusses in minimum weight trying, at the same time, to use the minimum number of cross-section types obtained from the market. It also seems reasonable to have the possibility to change the shape of the conceptual design, moving some joints. To simulate nearly real conditions, several load cases, constraints in the elastic joint displacements, ultimate tensile and elastic and plastic buckling in the bars have been taken into account. A hyperstatic 10 bars truss is subjected to a deep analysis in different situations in order to evaluate with other authors when possible as truss optimization with two criteria and buckling effect has not been found in specialized literature. A 160-bar transmission tower is also optimized.

Book
01 Dec 1996
TL;DR: This chapter contains sections titled: Introduction: Adaptive and Self-Adaptive Evolutionary Computations, A Nonstandard Genetic Program, Two Self- Adaptive Crossover Operators, Experiments, Results, Postmortem Parameter Analysis, Discussion, and Conclusion.
Abstract: This chapter contains sections titled: Introduction: Adaptive and Self-Adaptive Evolutionary Computations, A Nonstandard Genetic Program, Two Self-Adaptive Crossover Operators, Experiments, Results, Postmortem Parameter Analysis, Discussion, Conclusion

28 Jul 1996
TL;DR: This paper concentrates on the interaction between the standard crossover operator and a restriction on tree depth demonstrated by the MAX problem, which involves returning the largest possible value for given function and terminal sets and maximum tree depth.
Abstract: The Crossover operator is common to most implementations of Genetic Programming (GP). Often, there is some form of restriction on the size of trees in the GP population. This paper concentrates on the interaction between the standard crossover operator and a restriction on tree depth demonstrated by the MAX problem, which involves returning the largest possible value for given function and terminal sets and maximum tree depth. Some characteristics and inadequacies of crossover in normal use are highlighted and discussed. Subtree discovery and movement takes place mostly near the leaf nodes, with nodes near the root left untouched, where diversity drops quickly to zero in the tree population. GP is then unable to create fitter trees via the crossover operator, leaving a mutation operator as the only common, but ineffective, route to discovery of fitter trees.

Journal ArticleDOI
TL;DR: The development of a computer model based on genetic algorithms, an optimization tool capable of overcoming combinatorial explosion, to solve the pavement maintenance-rehabilitation trade-off problem at the network level is described.
Abstract: This paper describes the development of a computer model (known as PAVENET-R) based on genetic algorithms, an optimization tool capable of overcoming combinatorial explosion, to solve the pavement maintenance-rehabilitation trade-off problem at the network level. The formulation of the PAVENET-R model is described in detail. An integer coding scheme is selected for parameter representation in the model. Two genetic-algorithm operators, namely the crossover operator and the mutation operator, are used. A “change table” encodes constraints to the genetic-algorithm operations to ensure that only valid offspring are generated from a parent pool. Four numerical examples of road networks of 30 pavement segments, each with different relative costs of rehabilitation and maintenance activities, are analyzed to demonstrate the trade-off relationship between pavement rehabilitation and maintenance activities. The detailed maintenance and rehabilitation schedules of the solutions, and the convergence characteristics of each solution are presented.

Proceedings ArticleDOI
28 Apr 1996
TL;DR: Genetic algorithms are used in order to group cells in an efficient way, while preserving bandwidth, and Elitism, linear normalization of chromosoma and edge-based crossover are used to speed up the convergence time, allowing near-optimal solutions to be obtained in an acceptable computation time.
Abstract: As the subscriber population grows and the network capabilities are enhanced, mobility management and resource management become increasingly critical in (micro-) cellular networks. Moreover, coverage areas are increasingly enlarged, possibly requiring the adoption of partitions to facilitate management activities. Location areas constitute an important strategy of location management, used to reduce signaling traffic caused by location updating and paging messages in cellular networks. Due to the very large state spaces to be searched, the determination of optimal LA's represents a NP-hard combinatorial optimization problem. In this paper, genetic algorithms are used in order to group cells in an efficient way, while preserving bandwidth. Elitism, linear normalization of chromosoma and edge-based crossover are used to speed up the convergence time, allowing near-optimal solutions to be obtained in an acceptable computation time.

Journal Article
TL;DR: A new experimental evidence on usefulness of so-called geometrical crossover is discussed, which might be used for a boundary search for particular problems and enhances also the effectiveness of evolutionary algorithms (based on oating point representation) in a signi cant way.
Abstract: Numerical optimization problems enjoy a signi cant popularity in evolutionary computation community; all major evolutionary techniques (genetic algorithm, evolution strategies, evolutionary programming) have been applied to these problems. However, many of these techniques (as well as other, classical optimization methods) have di culties in solving some real-world problems which include non-trivial constraints. For such problems, very often the global solution lies on the boundary of the feasible region. Thus it is important to investigate some problem-speci c operators, which search this boundary in an e cient way. In this study we discuss a new experimental evidence on usefulness of so-called geometrical crossover, which might be used for a boundary search for particular problems. This operator enhances also the e ectiveness of evolutionary algorithms (based on oating point representation) in a signi cant way.

Proceedings ArticleDOI
20 May 1996
TL;DR: This paper introduces a new crossover, the job based order crossover (JOX), which can preserve characteristics very well and introduces a mutation for maintaining a diversity of population without disrupting characteristics.
Abstract: We propose a genetic algorithm for job shop scheduling problems. The proposed method uses a job sequence matrix. This paper introduces a new crossover, the job based order crossover (JOX), which can preserve characteristics very well. JOX preserves the order of each job on all machines between parents and their children, taking account of the dependency among machines. Since the children generated by JOX are not always feasible, we propose a technique to transform them into active schedules by using the Giffler and Thompson method (B. Giffler and G.L. Thompson, 1969). Furthermore, we introduce a mutation for maintaining a diversity of population without disrupting characteristics. By applying the proposed method to Fisher and Thompson's 10/spl times/10 and 20/spl times/5 problems (H. Fisher and G.L. Thompson, 1963), we show its usefulness.

Book ChapterDOI
22 Sep 1996
TL;DR: Using job-shop scheduling problem benchmarks, MSXF was evaluated in a GA framework as a high-level crossover working on the critical path of a schedule and showed promising performance for the proposed method.
Abstract: In this paper, multi-step crossover (MSX) and a local search method are unified as a single operator called MSXF MSX and MSXF utilize a neighborhood structure and a distance measure in the search space In MSXF, a solution, initially set to be one of the parents, is stochastically replaced by a relatively good solution in the neighborhood, where the replacement is biased toward the other parent After a certain number of iterations of this process, the best solution from those generated is selected as an offspring Using job-shop scheduling problem benchmarks, MSXF was evaluated in a GA framework as a high-level crossover working on the critical path of a schedule Experiments showed promising performance for the proposed method

Journal ArticleDOI
TL;DR: The ISRX operator is identified to play a significant role in improving the performance of the genetic algorithm, and the results show that the algorithm greatly reduces the computation time and its solution is very close to the optimal solution.

Book ChapterDOI
22 Sep 1996
TL;DR: It is found that increasing the mutation rate can significantly improve the generalization capabilities of GP and greatly extends the number of generations the GP system can train before the population converges.
Abstract: Ordinarily, Genetic Programming uses little or no mutation. Crossover is the predominant operator. This study tests the effect of a very aggressive use of the mutation operator on the generalization performance of our Compiling Genetic Programming System (‘CPGS’). We ran our tests on two benchmark classification problems on very sparse training sets. In all, we performed 240 complete runs of population 3000 for each of the problems, varying mutation rate between 5% and 80%. We found that increasing the mutation rate can significantly improve the generalization capabilities of GP. The mechanism by which mutation affects the generalization capability of GP is not entirely clear. What is clear is that changing the balance between mutation and crossover effects the course of GP training substantially — for example, increasing mutation greatly extends the number of generations for which the GP system can train before the population converges.

Proceedings Article
03 Dec 1996
TL;DR: In a large-scale empirical comparison of problems that have been reported in GA literature, it is shown that on many problems, simpler algorithms can perform significantly better than GAs.
Abstract: The genetic algorithm (GA) is a heuristic search procedure based on mechanisms abstracted from population genetics. In a previous paper [Baluja & Caruana, 1995], we showed that much simpler algorithms, such as hillclimbing and Population-Based Incremental Learning (PBIL), perform comparably to GAs on an optimization problem custom designed to benefit from the GA's operators. This paper extends these results in two directions. First, in a large-scale empirical comparison of problems that have been reported in GA literature, we show that on many problems, simpler algorithms can perform significantly better than GAs. Second, we describe when crossover is useful, and show how it can be incorporated into PBIL.

Proceedings ArticleDOI
20 May 1996
TL;DR: The authors apply a novel selection rule, the Thermodynamical Genetic Algorithm (TDGA), proposed by N. Mori et al. (1995) to the traveling salesman problem (TSP), and propose an adaptive annealing schedule of the temperature in TDGA.
Abstract: For successful applications of the genetic algorithm, there are two important points to be considered. The first point is the design of the fitness landscape introduced by the representation of the solution as a gene and searching operations such as crossover and mutation. The second is control of the convergence brought about by the selection operation. In the conventional implementation of GA, these two points are mutually dependent, i.e., a suitable selection pressure varies largely depending on, e.g., the crossover operator. Hence, it requires much trial-and-error effort to find a nice configuration of GA. The authors apply a novel selection rule, the Thermodynamical Genetic Algorithm (TDGA) proposed by N. Mori et al. (1995) to the traveling salesman problem (TSP), and propose an adaptive annealing schedule of the temperature in TDGA. Computer simulation with several crossover operators for TSP shows that TDGA reduces the mutual dependency between the fitness landscape and the convergence process.

Book ChapterDOI
TL;DR: This chapter focuses on optimal crossover designs, which are to use a number of available units for several measurements at different occasions to achieve the same precision as inferences based on within subject information.
Abstract: Publisher Summary This chapter focuses on optimal crossover designs. The principal idea associated with crossover designs is to use a number of available units for several measurements at different occasions. One possible motive for using a crossover design is that a crossover design requires fewer subjects for the same number of observations. This can obviously be an important consideration when subjects are scarce and when including a large number of subjects in the experiment can be prohibitively expensive. Another possible motive for using crossover designs is that these designs provide within subject information about treatment differences. In many applications, the different subjects would exhibit large natural differences, and inferences concerning treatment comparisons based on between subject information—available if subject effects are assumed to be random effects—would require a much larger replication of the treatments to achieve the same precision as inferences based on within subject information.

Proceedings Article
Hideo Matsuda1
01 Jan 1996
TL;DR: A genetic algorithm for exploring the best score tree is developed: randomly generated alternative trees are rearranged so that their scores are improved by utilizing crossover and mutation operators.
Abstract: This paper presents a method to construct phylogenetic trees from amino acid sequences. Our method uses a maximum likelihood approach which gives a confidence score for each possible alternative tree. Based on this approach, we developed a genetic algorithm for exploring the best score tree: randomly generated alternative trees are rearranged so that their scores are improved by utilizing crossover and mutation operators. In a test of our algorithm on a data set of EF-1 alpha sequences, we found that the performance of our algorithm is comparable to that of other tree-construction methods.

Proceedings Article
04 Aug 1996
TL;DR: An efficient probabilistic method for finding the optimal setting for a critical local search parameter, Maxflips, is presented and important details of two differing versions of WSAT are discussed.
Abstract: Local search algorithms, particularly GSAT and WSAT have attracted considerable recent attention primarily because they are the best known approaches to several hard classes of satisfiability problems. However, replicating reported results has been difficult because the setting of certain key parameters is something of an art, and because details of the algorithms, not discussed in the published papers, can have a large Impact on performance. In this paper we present an efficient probabilistic method for finding the optimal setting for a critical local search parameter, Maxflips, and discuss important details of two differing versions of WSAT. We then apply the optimization method to study performance of WSAT on satisfiable instances of Random 3SAT at the crossover point and present extensive experimental results over a wide range of problem sizes. We find that the results are well described by having the optimal value of Maxflips scale as a simple power of the number of variables, n, and the average run time scale sub-exponentially (basically as nlog(n)) over the range n = 25,...,400.