There is a great deal of information to be gained from studying the details within a GA run. This paper investigates the roles of crossover and mutation by observing the actions and eeects of individual occurrences of each genetic operation. The observations are compared with some of the common expectations of these operators.
A critical part of the design of eeective EAs is to obtain a proper balance between exploration and exploitation. A key element of this balance is the selection algorithm used. Although we have for some time now understood the relative diierences between various selection methods for standard centralized EAs, our understanding of decentralized EAs has been less complete. In this paper we present analysis tools and results which provide considerable insight into the properties of various decentralized selection methods, including the selection pressures they induce. Understanding this permits a more informed choice of selection methods when designing and implementing spatially structured EAs.
A learning classifier system, EpiCS, was used to de rive a continuous measure of disease risk in a series of 250 individuals. Using the area under the receiver-ope rating characteristic curve, this measure was compared wit h the risk estimate derived for the same individuals by logistic regression. Over 20 training-testing trial s, risk estimates derived by EpiCS were consistently more accurate (mean area=0.97, SD=0.01) than that derive d by logistic regression (mean area=0.89, SD=0.02). The areas for the trials with minimum and maximum classification performance on testing were signific antly greater (p=0.019 and p<0.001, respectively) than th e area for the logistic regression curve. This inves tigation demonstrated the ability of a learning classifier s ystem to produce output that is clinically meaningful in diagnostic classification.
In this paper we describe a method for improving genetic-algorithm-based optimization using case-based learning. The idea is to utilize the sequence of points explored during a search to guide further exploration. The proposed method is particularly suitable for continuous spaces with expensive evaluation functions, such as arise in engineering design. Empirical results in two engineering design domains and across diierent representations demonstrate that the proposed method can signiicantly improve the eeciency and reliability of the GA optimizer. Moreover, the results suggest that the modiication makes the genetic algorithm less sensitive to poor choices of tuning parameters such as mutation rate.
This paper describes a non-generational genetic algorithm for multiobjective optimization. The tness of each individual in the population is calculated incrementally based on the degree in which it is dominated in the Pareto sense, or close to other individuals. The closeness of individuals is measured using a sharing function. The performance of the algorithm presented is compared to previous eeorts on three multiobjec-tive optimization problems of growing dii-culty. The behavior of each algorithm is analyzed with regard to the visited search space, the quality of the nal population attained, and the percentage of non-dominated individuals in the population through time. According to all these performance measures, the algorithm presented clearly outperforms previous eeorts based on generational genetic algorithms.
Most niching methods create and maintain subpopulations of individuals characterized by some similarities. This paper defines the clearing procedure as a niching method that supplies the available resources of a niche only to the best individuals of each subpopulation: the winners. The clearing is naturally adapted to elitist strategies. Elitist clearing preserves good individuals from the destructive effects of genetic drift and reproduction operators, while maintaining a high level of diversity. These properties can dramatically improve the performance of genetic algorithms used for multimodal optimization. The basic clearing procedure selects the winners for reproduction. A standard selection operator then generates a competition between the winners from every subpopulation. This paper shows, through experiments, that this kind of over-selection is harmful. The concept of clearing based selection operator that ensures an equal number of offspring to every winner, regardless of its fitness is introduced. The experiments involve both easy and difficult multimodal function optimizations. They show that a clearing based selection operator can reduce the premature convergence rate, compared to a clearing procedure associated with an SUS selection. 1 GENETIC ALGORITHMS AND MULTIMODAL OPTIMIZATION A simple genetic algorithm (Goldberg, 1989) (SGA) is suitable for searching for the optimum of unimodal functions in a bounded search space. However, both experiments and analysis show that the SGA cannot find the multiple global maxima of a multimodal function (Goldberg, 1989)(Mahfoud, 1995). This limitation can be overcome by a mechanism that creates and maintains several subpopulations within the search space, in such a way that each highest maximum of the multimodal function can attract one of them. These mechanisms are referred to as “niching methods” (Mahfoud, 1995). Most niching methods gather together the individuals which present some similarities into subpopulations. Regulating mechanisms are necessary to stabilize these subpopulations generation by generation. These mechanisms can be implemented within the operators that are applied at each generation of the genetic algorithm: ◊ the selection operator selects the individuals for the reproduction process; ◊ the reproduction operator modifies the selected individuals to generate new individuals. This operator can be composed of several elementary operators such as the crossover and the mutation; ◊ the substitution operator determines which individuals must disappear from the current population to make room for the new ones. The sharing method (Goldberg, Richardson, 1987) is a niching mechanism which interferes with the selection operator. It is based on the sharing of limited renewal resources, between individuals characterized by some similarities, according to the principle stated by J.H. Holland in 1975 (Holland, 1992). The basic method is known for its reliability, however, it suffers from some drawbacks such as the requirement of large population sizes, and its algorithmic complexity which is O(n2), where n is the size of the population. It is also necessary to know the value of parameter σshare which strongly depends on the distances between the searched maxima. This latter parameter is often difficult to estimate. These drawbacks have been removed in part by the works of Goldberg et al. (1992) and Yin and Germay (1993). The restricted mating techniques take place within the reproduction operator. They allow the individuals to mate preferably if they belong to a same subpopulation. The membership of an individual is determined through the value of a label concatenated to its genotype. The label, also named tag bits, can mutate, allowing the individuals to change of subpopulation: this is a migration mechanism. This kind of method does not increase the algorithmic complexity, from which derives its advantage. Furthermore it can be naturally implemented on parallel machines (Cantú-Paz, 1995). W. Spears combines this concept with the sharing method to improve its reliability (Spears, 1995). The behavior of this technique facing difficult problems is a topical question. The crowding (De Jong, 1975) takes place within the substitution operator. According to this method, a new individual replaces the most similar individual from a sample of the population. The deterministic crowding (Mahfoud, 1995) improves the method, leading towards a better reliability. This technique does not affect the complexity of the genetic algorithm. Mahfoud showed that this method was able to solve hard problems, but it requires a great number of evaluations of the fitness function, compared to some other techniques. The clearing procedure previously presented in (Petrowski, 1996) also derives from the niching principle stated by J.H. Holland like the sharing method. But, instead of evenly sharing the available resources among the individuals of a subpopulation, the clearing procedure supplies these resources only to the best individuals of each subpopulation. It is applied at the selection operator level. Its reliability is similar to that of the basic sharing method with a lower complexity and much smaller population sizes. This paper first presents the basic clearing procedure and subsequently an elitist variant. Next, some improvements are proposed to reduce the complexity and to control the subpopulations into an easier and more efficient way. The utility of a selection operator associated with a clearing procedure is then discussed and the concept of “clearing based selection operator” is introduced. Section 3 describes some tests on both easy and difficult functions. Finally, these results are compared with those obtained from sharing and deterministic crowding. 2 CLEARING THE SEARCH SPACE
This paper presents models that predict the speedup of two cases that bound the possible topologies and migration rates of parallel genetic algorithms (GAs). The rst bounding case is a parallel GA with completely isolated demes or subpopulations and for this case the model and the experiments show that the speedup is not very signiicant when more demes are used. The second model predicts the speedup when each deme communicates with every other deme using a maximal migration rate. For this case, we show that when the communication time is not constant there is a combination of number of demes and deme size that maximizes the speedup. The models are validated with computational experiments using functions of varying dii-culty.
Objects Having Cavities and Holes Ilkka Ikonen William E. Biles Department of Industrial Engineering University of Louisville Louisville, KY 40292 Anup Kumar Rammohan K. Ragade John C. Wissel Engineering Math and Computer Science Dept University of Louisville Abstract In this paper we describe a unique threedimensional bin-packing problem with nonconvex parts having holes and cavities. Parts can be arranged in any orientation and location in the packing cylinder, where parts oat like in a weightless environment. The solution approach utilizes a genetic algorithm (GA) which represents a solution for the problem as a three-dimensional chromosome. Each dimension in the chromosome is an ordered list of integers. As a function evaluator we have developed a packing simulator, which utilizes actual CAD le of parts, when packing parts. Part intersection calculations are based on methods common in computational geometry.
The appropriate choice of the genotype → phenotype mapping in combination with the mutation operator is important for a successful evolutionary search process. We suggest a measure to quantify the quality of this combination by addressing the question whether the relation among distances is carried over from one space to the other. Search processes which do not destroy the neighbourhood structure are termed strongly causal. We apply the proposed measure to parameter and structure optimisation problems in order to assess the combination (mapping, mutation operator) and at the same time to be able to propose improved settings.
In this paper we first review the main results in the theory of schemata in Genetic Programming (GP) emphasising their strengths and weaknesses. In particular we summarise a new schema theory we have recently developed for GP with one-point crossover and point mutation which is based on a definition of schema quite close to the one used in genetic algorithms. Then we study the creation, propagation and disruption of this new form of schemata in real runs, for standard crossover, one-point crossover and selection only. Finally, we discuss these results in the light our GP schema theorem.
This paper presents a genetic algorithm for the restrictive channel routing problem. The major difference of the algorithm from already known genetic algorithms for this problem consists of the use of information about horizontal and vertical constraints in chromosome encoding that allow prevention of “illegal” solutions. This representation leads to lower complexity, because solution repairing procedures become unnecessary. Moreover, the search space is greatly reduced. Competitive experimental results proving the consistency of the approach were obtained. Genetic Algorithm For Restrictive Channel Routing Problem
