Showing papers on "Selection (genetic algorithm) published in 1995"

Bayesian Model Selection in Social Research

Abstract: It is argued that P-values and the tests based upon them give unsatisfactory results, especially in large samples. It is shown that, in regression, when there are many candidate independent variables, standard variable selection procedures can give very misleading results. Also, by selecting a single model, they ignore model uncertainty and so underestimate the uncertainty about quantities of interest. The Bayesian approach to hypothesis testing, model selection, and accounting for model uncertainty is presented. Implementing this is straightforward through the use of the simple and accurate BIC approximation, and it can be done using the output from standard software. Specific results are presented for most of the types of model commonly used in sociology. It is shown that this approach overcomes the difficulties with P-values and standard model selection procedures based on them. It also allows easy comparison of nonnested models, and permits the quantification of the evidence for a null hypothesis of interest, such as a convergence theory or a hypothesis about societal norms.

Randomized Algorithms

Abstract: For many applications, a randomized algorithm is either the simplest or the fastest algorithm available, and sometimes both. This book introduces the basic concepts in the design and analysis of randomized algorithms. The first part of the text presents basic tools such as probability theory and probabilistic analysis that are frequently used in algorithmic applications. Algorithmic examples are also given to illustrate the use of each tool in a concrete setting. In the second part of the book, each chapter focuses on an important area to which randomized algorithms can be applied, providing a comprehensive and representative selection of the algorithms that might be used in each of these areas. Although written primarily as a text for advanced undergraduates and graduate students, this book should also prove invaluable as a reference for professionals and researchers.

Genetic Algorithms, Tournament Selection, and the Effects of Noise.

Abstract: Abstr act . Tournament select ion is a useful and rob ust select ion mechanism commonly used by genet ic algorithms (GAs). The selecti on pr essure of to urnament select ion direc tly varies wit h the tournam en t size-the more compe t it ors , t he higher the resulting select ion pr essur e. This pap er develops a model, based on order stat ist ics, that can be used to quantita tively predict th e resul ting select ion pr essure of a tournament of a given size. T his mo del is used to pr edict the convergence ra tes of GAs utili zing tournament selection. While to urnament selection is often used in conjunct ion wit h noisy (imperfect) fitness fun cti ons, lit tl e is understood abo ut how the noise affect s the resul ting select ion pr essur e. The model is extended to quantit atively pred ict t he select ion pressure for tournam ent select ion utili zing noisy fitn ess functions . Given the to urnament size and noise level of a noisy fitness fun ct ion , the exte nded mod el is used to pr ed ict t he resu lt ing select ion pr essure of to urnament select ion . T he accuracy of the mod el is verified using a simple test domain, t he onemax (bit-count ing) domain . T he model is shown to accurately predict t he convergence ra te of a GA using tournament select ion in the onemax domain for a wide range of t ournament sizes and noise levels. T he model develop ed in this paper has a number of immediat e pra cti cal uses as well as a number of longer term rami fica tions. Immediately, t he mod el may be used for determ ining appropria te ra nges of cont rol para meters , for est imat ing stopping times to achieve a spec ified level of solution qua lity , and for approximating convergence t imes in impor tant classes offunction evaluatio ns that utilize sampling . Longer term, the approach of this st udy may be applied to bet ter underst an d

Visualizing and quantifying natural selection

Abstract: Modern methods of analysis are enabling researchers to study natural selection at a new level of detail. Multivariate statistical techniques can Identify specific targets of selection and provide parameter estimates that fit into equations for evolutionary change. A more Intuitive understanding of the form of selection can be provided through graphical representation of selection surfaces. Combinations of quantitative and visual analyses are providing researchers with new insights into the details of natural selection in the wild.

Evolution and extinction in a changing environment: a quantitative-genetic analysis.

Abstract: Because of the ubiquity of genetic variation for quantitative traits, virtually all populations have some capacity to respond evolutionarily to selective challenges. However, natural selection imposes demographic costs on a population, and if these costs are sufficiently large, the likelihood of extinction will be high. We consider how the mean time to extinction depends on selective pressures (rate and stochasticity of environmental change, and strength of selection), population parameters (carrying capacity, and reproductive capacity), and genetics (rate of polygenic mutation). We assume that in a randomly mating, finite population subject to density-dependent population growth, individual fitness is determined by a single quantitative-genetic character under Gaussian stabilizing selection with the optimum phenotype exhibiting directional change, 'or random fluctuations, or both. The quantitative trait is de- termined by a finite number of freely recombining, mutationally equivalent, additive loci. The dynamics of evolution and extinction are investigated, assuming that the population is initially under mutation-selection-drift balance. Under this model, in a directionally changing environment, the mean phenotype lags behind the optimum, but on the average evolves parallel to it. The magnitude of the lag determines the vulnerability to extinction. In finite populations, stochastic variation in the genetic variance can be quite pronounced, and bottlenecks in the genetic variance temporarily can impair the population's adaptive capacity enough to cause extinction when it would otherwise be unlikely in an effectively infinite population. We find that maximum sustainable rates of evolution or, equivalently, critical rates of environmental change, may be considerably less than 10% of a phenotypic standard deviation per generation.

Test selection based on finite state models

Abstract: A method for the selection of appropriate test case, an important issue for conformance testing of protocol implementations as well as software engineering, is presented. Called the partial W-method, it is shown to have general applicability, full fault-detection power, and yields shorter test suites than the W-method. Various other issues that have an impact on the selection of a suitable test suite including the consideration of interaction parameters, various test architectures for protocol testing and the fact that many specifications do not satisfy the assumptions made by most test selection methods (such as complete definition, a correctly implemented reset function, a limited number of states in the implementation, and determinism), are discussed. >

Design and Analysis of Experiments for Statistical Selection, Screening, and Multiple Comparisons

Abstract: The Rationale of Selection, Screening and Multiple Comparisons. Selecting the Best Treatment in a Single-Factor Normal Response Experiment Using the Indifference-Zone Approach. Selecting a Subset Containing the Best Treatment in a Normal Response Experiment. Multiple Comparison Approaches for Normal Response Experiments. Problems Involving a Standard or Control Treatment in Normal Response Experiments. Selection Problems in Two-Factor Normal Response Experiments. Selecting Best Treatments in Single-Factor Bernoulli Response Experiments. Selection Problems for Categorical Response Experiments. Appendices. References. Indexes.

MOGA: multi-objective genetic algorithms

Abstract: In this paper, we propose a .framework of genetic algorithms to search for Pareto optimal solutions (i.e., non-dominated solutions) of multi-ohjectiv,e optimizution problems. Our approuch d!fers from single-objective genetic algorithms in its selection proceduiae and elite preserve strategy. The selection procedure in our genetic algorithms selects individuals for a cromover operation based on a weighted sum of multiple ohjective functions. The characteristic feature of the selection procedure is that the weights attached to the multiple objective ,functions are not constant but rundomly specified for each selection. 7he elite preserve strategy in our genetic algorithms uses multiple elite solutions instead of a single eliie solution. That is, a certain number of individuals are selected from a tentative set of Pareto optimal solutions and inherited to the next generation as elite individuals.

Predicting microevolutionary responses to directional selection on heritable variation

Abstract: Microevolution of quantitative traits in the wild can be predicted from a knowledge of selection and genetic parameters. Testing the predictions requires measurement of the offspring of the selected group, a requirement that is difficult to meet. We present the results of a study of Darwin's finches on the Galapagos island of Daphne Major where this requirement is met. The study demonstrates microevolutionary consequences of natural selection.

The Ant Colony Metaphor for Searching Continuous Design Spaces

Abstract: This paper describes a form of dynamical computational system—the ant colony—and presents an ant colony model for continuous space optimisation problems. The ant colony metaphor is applied to a real world heavily constrained engineering design problem. It is capable of accelerating the search process and finding acceptable solutions which otherwise could not be discovered by a GA. By integrating the Pareto optimality concept within the selection mechanism in GAs and Ant Colony it is possible to treat both hard and soft constraints. Hard constraints participate in a penalty term while soft constraints become part of a multi-criteria formulation of the problem.

Predictive Model Selection

Abstract: We consider the problem of selecting one model from a large class of plausible models. A predictive Bayesian viewpoint is advocated to avoid the specification of prior probabilities for the candidate models and the detailed interpretation of the parameters in each model. Using criteria derived from a certain predictive density and a prior specification that emphasizes the observables, we implement the proposed methodology for three common problems arising in normal linear models: variable subset selection, selection of a transformation of predictor variables and estimation of a parametric variance function. Interpretation of the relative magnitudes of the criterion values for various models is facilitated by a calibration of the criteria. Relationships between the proposed criteria and other well-known criteria are examined

Genetic Algorithms as a Tool for Wavelength Selection in Multivariate Calibration

Abstract: A comparison of multiple linear regression (MLR) with partial least-squares (PLS) regression is presented, for the multivariate modeling of hydroxyl number in a certain polymer of a heterogeneous near-IR spectroscopic data set. The MLR model was performed by selecting the variables with a genetic algorithm. A good model could be obtained with both methods. It was shown that the MLR and PLS solutions are very similar. The two models include the same number of variables, and the first variables in each model have similar, chemically understandable functions. It is concluded that both solutions are equivalent and that each has some advantages and disadvantages. This also means that even in very complex situations such as here, MLR can replace PLS in certain cases.

Path Selection and Route Preference in Human Navigation: A Progress Report

Abstract: Two critical characteristics of human wayfinding are destination choice and path selection. Traditionally, the path selection problem has been ignored or assumed to be the result of minimizing procedures such as selecting the shortest path, the quickest path or the least costly path. In this paper I draw on existing literature from cognitive mapping and cognitive distance, to define possible route selection criteria other than these traditional ones. Experiments with route selection on maps and in the field are then described and analyzed to determine which criteria appear to be used as the environment changes and as one increases the number of nodes along a path (i.e., as trip chaining replaces a simple Origin-Destination (O-D) pairing.

A Mathematical Analysis of Tournament Selection

Abstract: Genetic Algorithms are a common probabilis-tic optimization method based on the model of natural evolution. One important operator in these algorithms is the selection scheme used to prefer better individuals. In this paper a new description model for selection schemes is introduced that operates on the tness distribution of the population. With this method an extensive mathematical analysis of the tournament selection scheme is carried out that allows an exact prediction of the tness values after selection. Furthermore several new properties of tournament selection are derived.

Nest site selection : a trade-off between concealment and view of the surroundings ?

Abstract: For most birds, nest predation is the main cause of reproductive failure. Many species reduce predation by hiding their nests in vegetation. However, it is unclear whether they maximize cover around nests. Individuals may benefit also by keeping potential predators, food, and conspecifics in view, and selection of nest site may be a trade-off between concealment and visibility. We examined this idea in the Song Thrush Turdus philomelos, which builds cup-shaped nests in trees. For artificial nests, the risk of predation decreased when nests were more concealed within individual trees. However, Song Thrushes did not maximize concealment of nests within trees but selected intermediate concealment from the range of concealment available. The proportion of destroyed natural nests was not related to degree of nest concealment. Song Thrushes also selected patches of intermediate tree density, but tree density did not influence predation rate of artificial nests. These results are consistent with the trade-off hypothesis, which deserves more attention in future studies of nest site selection.

Measuring the effects of pairing success, extra-pair copulations and mate quality on the opportunity for sexual selection

Abstract: Sexual selection can act through variation in the number of social mates obtained, variation in mate quality, or variation in success at obtaining extra-pair fertilizations. Because within-pair fertilizations (WPF) and extra-pair fertilizations (EPF) are alternate routes of reproduction, they are additive, rather than multiplicative, components of fitness. We present a method for partitioning total variance in reproductive success (a measure of the opportunity for selection) when fitness components are both additive and multiplicative and use it to partition the variance into components that correspond to each mechanism of sexual selection. Computer simulations show that extra-pair fertilizations can either increase or decrease total variance, depending on the covariance between within-pair and extra-pair success. Simulations also suggest that for socially monogamous species, extra-pair fertilizations have a greater effect than variation in mate quality or pairing status on the opportunity for selection. Application of our model to data gathered for a population of red-winged blackbirds (Agelaius phoeniceus) indicates that most of the variance in male reproductive success was attributable to within-pair sources of variance. Nevertheless, extra-pair copulations increased the opportunity for selection because males varied both in the proportion of their social young that they sired and in the number of extra-pair mates that they obtained. Furthermore, large and positive covariances existed between the number of extra-pair mates a male obtained and both social pairing success and within-pair paternity, indicating that, in this population, males preferred as social mates also were preferred as extra-pair mates.

The “prince” technique: Fitts' law and selection using area cursors

Abstract: In most GUIs, selection is effected by placing the point of the mouse-driven cursor over the area of the object to be selected. Fitts' law is commonly used to model such target acquisition, with the term A representing the amplitude, or distance, of the target from the cursor, and W the width of the target area. As the W term gets smaller, the index of difficulty of the task increases. The extreme case of this is when the target is a point. In this paper, we show that selection in such cases can be facilitated if the cursor is an area, rather than a point. Furthermore, we show that when the target is a point and the width of the cursor is W, that Fitts' law still holds. An experiment is presented and the implications of the technique are discussed for both 2D and 3D interfaces.

System and method for networking and controlling vending machines

Abstract: A vending machine control system and method for controlling vending of items from one or more vending machines having a coin acceptor interface and selection controls for selecting items to vend. Control system and method are provided for sending and receiving information to and from each of the vending machines to control the vending of items to users. Network system and method are connected to each of the coin acceptor interfaces for facilitating communication between the control system and the vending machine.

Control of neuronal pathway selection by the Drosophila LIM homeodomain gene apterous

Abstract: The Drosophila apterous gene encodes a LIM homeodomain protein expressed embryonically in a small subset of differentiating neurons. To establish the identity of these neurons and to study the role of apterous in their development, we made apterous promoter fusions to an axon-targeted reporter gene. We found that all apterous-expressing neurons are interneurons that choose a single pathway within the developing central nervous system. In apterous mutants, these neurons choose incorrect pathways and fail to fasciculate with one another. Our results indicate that apterous functions to control neuronal pathway selection and suggest that other vertebrate and invertebrate members of the LIM homeodomain class of proteins may serve similar functions.

Good genes and old age: Do old mates provide superior genes?

Abstract: It has been suggested that female preference for older mates in species without parental care has evolved in response to an alleged higher genetic quality of older individuals. This is based on the widespread assumption that viability selection produces older individuals that are genetically superior to younger individuals. In contrast, we propose that the oldest individuals rarely are genetically superior. Quantitative genetic models of life history evolution indicate that young to intermediately aged individuals are likely to possess the highest breeding values of fitness. This conclusion is based on four arguments: 1) Viability selection on older individuals may decrease or at least not substantially increase breeding values of fitness, because there may exist negative genetic correlations between late-age and early-age life history parameters, 2) Fertility selection is likely to raise the fitness of gametes produced by young individuals more than those produced by old individuals, because the covariance between fertility and fitness often decreases with age, 3) The history of selection on their parents makes younger individuals more fit than older individuals, 4) Germ-line mutations, which are generally deleterious, significantly decrease the breeding value of fitness of an individual throughout its lifespan, especially in males. Therefore, females that mate with the oldest males in a population are doing so for reasons other than to obtain offspring of high genetic quality.

Optimising selection of units from speech databases for concatenative synthesis.

Abstract: Concatenating units of natural speech is one method of speech synthesis. Most such systems use an inventory of xed length units, typically diphones or triphones with one instance of each type. An alternative is to use more varied, non-uniform units extracted from large speech databases containing multiple instances of each. The greater variability in such natural speech segments allows closer modeling of naturalness and di erences in speaking styles, and eliminates the need for specially-recorded, single-use databases. However, with the greater variability comes the problem of how to select between the many instances of units in the database. This paper addresses that issue and presents a general method for unit selection.

Natural Selection and Ecotypic Differentiation in Impatiens Pallida

Abstract: One possible response of plant populations to heterogeneous environments is genetic adaptation resulting in the formation of distinct ecotypes Genetic adaptation to stressful environments may affect both the limits to species boundaries and the potential for response to a changing environment Reciprocal transplant experiments have frequently been used to describe ecotypic differentiation and to infer the role of natural selection when there is evidence for home site advantage The demonstration of a home site advantage, however, does not reveal which plant characters are responsible for conferring increased fitness on populations planted in their native site Here, we combine the classic reciprocal transplant experiment with multivariate regression analysis of selection to ask a series of questions relevant to understanding adaptive genetic differentiation in natural plant pop- ulations Impatiens pallida plants from a mesic floodplain and a dry hillside site were reciprocally transplanted We initially presumed the hillside to be a stressful site for Impatiens given its sparser population of consistently smaller individuals This study describes the two environments from the perspective of the plant to ask whether it is stressful In addition, we investigate genetic differentiation between populations and ask whether the two pop- ulations are distinctly adapted to their home sites To identify traits that may be important for conferring home site advantage, we quantify present-day natural selection in these sites and ask whether the observed selective forces can explain genetic differences Finally, because phenotypic correlations may play an important role in a population's response to its environment, we investigate relationships among traits to determine the extent to which they are genetically and/or environmentally controlled The large reduction in total seed production when plants from both populations were grown on the hillside supported our initial bias that this site was stressful to Impatiens In addition, the higher relative fitness of each population planted in its native site demonstrated that these populations represent distinct ecotypes Genetic differences between populations were observed for several life history and morphological characters In particular, plants from the hillside population were smaller and produced cleistogamous flowers earlier than floodplain plants Selection analysis revealed that, while there is strong selection favoring early flowering on the hillside, there is no advantage to early flowering for plants grown on the floodplain An increased developmental rate, which allows plants to produce seeds before they succumb to drought stress, appears to be the most important mechanism re- sponsible for the greater relative fitness of the hillside population in its native site While greater total plant leaf area is favored by selection on the floodplain, there is no evidence for selection on this trait on the hillside Phenotypic covariances among traits differed between sites and populations, resulting in differences in the action of indirect selection There is evidence that indirect selection on correlated traits is responsible for some of the observed genetic differences