Página 14 dos resultados de 3086 itens digitais encontrados em 0.032 segundos

"Abordagem genética para seleção de um conjunto reduzido de características para construção de ensembles de redes neurais: aplicação à língua eletrônica" ; A genetic approach to feature subset selection for construction of neural network ensembles: an application to gustative sensors

Ferreira, Ednaldo José
Fonte: Biblioteca Digitais de Teses e Dissertações da USP Publicador: Biblioteca Digitais de Teses e Dissertações da USP
Tipo: Dissertação de Mestrado Formato: application/pdf
Publicado em 10/08/2005 Português
Relevância na Pesquisa
45.97%
As características irrelevantes, presentes em bases de dados de diversos domínios, deterioram a acurácia de predição de classificadores induzidos por algoritmos de aprendizado de máquina. As bases de dados geradas por uma língua eletrônica são exemplos típicos onde a demasiada quantidade de características irrelevantes e redundantes prejudicam a acurácia dos classificadores induzidos. Para lidar com este problema, duas abordagens podem ser utilizadas. A primeira é a utilização de métodos para seleção de subconjuntos de características. A segunda abordagem é por meio de ensemble de classificadores. Um ensemble deve ser constituído por classificadores diversos e acurados. Uma forma efetiva para construção de ensembles de classificadores é por meio de seleção de características. A seleção de características para ensemble tem o objetivo adicional de encontrar subconjuntos de características que promovam acurácia e diversidade de predição nos classificadores do ensemble. Algoritmos genéticos são técnicas promissoras para seleção de características para ensemble. No entanto, a busca genética, assim como outras estratégias de busca, geralmente visam somente a construção do ensemble, permitindo que todas as características (relevantes...

Algoritmos para o custo médio a longo prazo de sistemas com saltos markovianos parcialmente observados; Algorithms for the long run average cost for linear systems with partially observed Markov jump parameters

Silva, Carlos Alexandre
Fonte: Biblioteca Digitais de Teses e Dissertações da USP Publicador: Biblioteca Digitais de Teses e Dissertações da USP
Tipo: Tese de Doutorado Formato: application/pdf
Publicado em 13/08/2012 Português
Relevância na Pesquisa
45.97%
Neste trabalho procuramos determinar o controle ótimo para problemas de custo médio a longo prazo (CMLP) de sistemas lineares com saltos markovianos (SLSMs) com observação parcial dos estados da cadeia de Markov, e, para isso, implementamos métodos computacionais heurísticos como algoritmos evolutivos de primeira geração - algoritmo genético (AG) básico - e os algoritmos UMDA(Univariate Marginal Distribution Algorithm) e BOA(Bayesian Optimization Algorithm), de segunda geração. Utilizamos um algoritmo variacional para comparar com os métodos implementados e medir a qualidade de suas soluções. Desenvolvemos uma abordagem de transição de níveis de observação (ATNO), partindo de um problema de observação completa e migrando através de problemas parcialmente observados. Cada um dos métodos mencionados acima foi implementado também no contexto da ATNO. Para realizar uma análise estatística sobre o desempenho dos métodos computacionais, utilizamos um gerador de SLSMs com importantes características da teoria de controle como: estabilidade, estabilizabilidade, observabilidade, controlabilidade e detetabilidade. Por fim, apresentamos alguns resultados sobre o CMLP com controles estabilizantes e resultados parciais a respeito da unicidade de solução; In this work we are interested in the optimal control for the long run average cost (LRAC) problem for linear systems with Markov jump parameters (LSMJP)...

Genetic algorithm of chu and beasley for static and multistage transmission expansion planning

De Silva, Irênio J.; Rider, Marcos J.; Romero, Rubén; Murari, Carlos A.
Fonte: Universidade Estadual Paulista Publicador: Universidade Estadual Paulista
Tipo: Conferência ou Objeto de Conferência
Português
Relevância na Pesquisa
45.97%
In this paper the genetic algorithm of Chu and Beasley (GACB) is applied to solve the static and multistage transmission expansion planning problem. The characteristics of the GACB, and some modifications that were done, to efficiently solve the problem described above are also presented. Results using some known systems show that the GACB is very efficient. To validate the GACB, we compare the results achieved using it with the results using other meta-heuristics like tabu-search, simulated annealing, extended genetic algorithm and hibrid algorithms. © 2006 IEEE.

Otimização de parametros de projeto de sistemas mecanicos atraves de algoritmo genetico multi-objetivos; Optimization in design parameters of mechanical systems using multi-objective genetic algorithm

Robeto Luiz Escobar
Fonte: Biblioteca Digital da Unicamp Publicador: Biblioteca Digital da Unicamp
Tipo: Dissertação de Mestrado Formato: application/pdf
Publicado em 16/02/2007 Português
Relevância na Pesquisa
45.97%
Os sistemas mecânicos são projetados para desempenhar funções específicas, e por essa razão as suas funções devem ser medidas para garantir seu desempenho dentro de uma certa precisão ou tolerância. A grande complexidade em se projetar e analisar novos projetos é a inserção de novas tecnologias, que envolvem aspectos multidisciplinares. Assim, o desenvolvimento e melhoria de projetos e produtos colocam o engenheiro projetista frente às diversas fontes de variabilidade, como por exemplo, as propriedades dos materiais, condições operacionais e ambientais e incertezas nas suposições feitas sobre seu funcionamento. Em termos de modelagem matemática, as aproximações inerentes e hipóteses feitas durante a concepção do sistema, conduzem normalmente a diferentes respostas obtidas através de simulações e/ou medidas experimentais. Dessa forma, em uma fase anterior à modelagem matemática,durante a concepção do sistema ou produto, as aplicações de ferramentas estatísticas e métodos de otimização podem fornecer estimativas sobre faixas de valores ou valores ótimos para parâmetros significativos de projeto, dentro do espaço experimental estudado. Esse tipo de abordagem estatística teve sua fundamentação teórica durante as décadas de 20 e 30 por Fisher...

A retroanálise de parâmetros geomecânicos em estruturas subterrâneas : comparação de diferentes técnicas de otimização; The backanalysis of the geomechanicals parameters in underground structures : comparison of different optimization techniques

Cardoso, Marta Maria da Rocha
Fonte: Universidade do Minho Publicador: Universidade do Minho
Tipo: Trabalho de Conclusão de Curso
Publicado em //2013 Português
Relevância na Pesquisa
45.97%
Dissertação de mestrado integrado em Engenharia Civil (área de especialização em Perfil de Estruturas e Geotecnia); A quantificação dos parâmetros geomecânicos nos maciços terrosos ou rochosos onde se inserem obras subterrâneas são uma constante incerteza no âmbito na Engenharia Civil. Os ensaios normalizados utilizados para a identificação e avaliação do comportamento dos maciços por vezes tornam-se incomportáveis, quer no tempo despendido para a sua concretização quer a nível económico, tornando deste modo o seu uso insuficiente para uma completa caracterização dos maciços. Com este trabalho pretende-se estudar a aplicação de técnicas de retroanálise de parâmetros geomecânicos através de ferramentas de otimização, incorporados no âmbito na computação evolucionária. Os algoritmos utilizados são os Algoritmos Genéticos e as Estratégias Evolutivas, ambos baseados na Teoria da Evolução de Darwin. Analisaram-se dois casos de estudos que descrevem o comportamento elástico e plástico de um maciço durante as fases de execução de um túnel. O estudo foi efetuado apenas com o conhecimento das deformações/deslocamentos sofridos pela estrutura e maciço, através da monitorização da obra. O principal objetivo deste trabalho consiste em estudar a capacidade que estes algoritmos evolutivos têm quando aplicados na Geotecnia...

Cash management policies by evolutionary models: a comparison using the Miller-Orr model

Moraes,Marcelo Botelho da Costa; Nagano,Marcelo Seido
Fonte: TECSI Laboratório de Tecnologia e Sistemas de Informação - FEA/USP Publicador: TECSI Laboratório de Tecnologia e Sistemas de Informação - FEA/USP
Tipo: Artigo de Revista Científica Formato: text/html
Publicado em 01/12/2013 Português
Relevância na Pesquisa
45.97%
This work aims to apply genetic algorithms (GA) and particle swarm optimization (PSO) to managing cash balance, comparing performance results between computational models and the Miller-Orr model. Thus, the paper proposes the application of computational evolutionary models to minimize the total cost of cash balance maintenance, obtaining the parameters for a cash management policy, using assumptions presented in the literature, considering the cost of maintenance and opportunity for cost of cash. For such, we developed computational experiments from cash flows simulated to implement the algorithms. For a control purpose, an algorithm has been developed that uses the Miller-Orr model defining the lower bound parameter, which is not obtained by the original model. The results indicate that evolutionary algorithms present better results than the Miller-Orr model, with prevalence for PSO algorithm in results.

Optimization of design of water distribution systems using genetic algorithms

Simpson, A.
Fonte: Hydraulics Division, Faculty of Civil and Geodetic Engineering, University of Ljubljana Publicador: Hydraulics Division, Faculty of Civil and Geodetic Engineering, University of Ljubljana
Tipo: Artigo de Revista Científica
Publicado em //2000 Português
Relevância na Pesquisa
45.97%
This paper presents details of a relatively new approach to the design of water distribution systems. An optimization technique called genetic algorithms is used to evolve an improving population of designs. Only a very, very small proportion of the total possible search space needs to be explored to find low cost solutions that satisfy all of the specified design criteria. The genetic algorithm (GA) uses operators of selection, crossover and mutation applied to a set of strings that represent the decision variables to be selected as part of the design process. These operators enable the genetic algorithm process to quickly seek out low cost optimal solutions. Many tests of the application of the genetic algorithm optimization process to real-life network designs has shown that the GA is effective at finding low cost solutions. The technique has consistently found lower cost solutions than the trial-and-error simulation approach typically used by design engineers. In addition, the technique is more effective and easier to apply than traditional mathematical optimization techniques.; http://ksh.fgg.uni-lj.si/ksh/acta/izdane_st/izdane_od00.html

On convergence and optimality of genetic algorithms

Kosinski, W.; Kotowski, S.; Michalewicz, Z.
Fonte: IEEE; USA Publicador: IEEE; USA
Tipo: Conference paper
Publicado em //2010 Português
Relevância na Pesquisa
45.97%
An action of genetic algorithm could be represented in the search space as a random Markovian process. The question concerning its asymptotic stability properties is discussed. Conditions under which genetic algorithm is convergent, are formulated. Then the existence of an operator to which infinite long iterations of the genetic algorithms tend, is shown. This operator describes optimal genetic algorithm in probabilistic sense.; Witold Kosinski, Stefan Kotowski and Zbyszek Michalewicz

Genetic algorithms compared to other techniques for pipe optimization

Simpson, A.; Dandy, G.; Murphy, L.
Fonte: American Society of Civil Engineers Publicador: American Society of Civil Engineers
Tipo: Artigo de Revista Científica
Publicado em //1994 Português
Relevância na Pesquisa
45.97%
The genetic algorithm technique is a relatively new optimization technique. In this paper we present a methodology for optimizing pipe networks using genetic algorithms. Unknown decision variables are coded as binary strings. We investigate a three-operator genetic algorithm comprising reproduction, crossover, and mutation. Results are compared with the techniques of complete enumeration and nonlinear programming. We apply the optimization techniques to a case study pipe network. The genetic algorithm technique finds the global optimum in relatively few evaluations compared to the size of the search space.; Angus R. Simpson, Graeme C. Dandy and Laurence J. Murphy

Genetic Algorithms for multimodal optimization: a review

Casas, Noe
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 10/06/2015 Português
Relevância na Pesquisa
45.98%
In this article we provide a comprehensive review of the different evolutionary algorithm techniques used to address multimodal optimization problems, classifying them according to the nature of their approach. On the one hand there are algorithms that address the issue of the early convergence to a local optimum by differentiating the individuals of the population into groups and limiting their interaction, hence having each group evolve with a high degree of independence. On the other hand other approaches are based on directly addressing the lack of genetic diversity of the population by introducing elements into the evolutionary dynamics that promote new niches of the genotypical space to be explored. Finally, we study multi-objective optimization genetic algorithms, that handle the situations where multiple criteria have to be satisfied with no penalty for any of them. Very rich literature has arised over the years on these topics, and we aim at offering an overview of the most important techniques of each branch of the field.

The Fundamental Learning Problem that Genetic Algorithms with Uniform Crossover Solve Efficiently and Repeatedly As Evolution Proceeds

Burjorjee, Keki M.
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 15/07/2013 Português
Relevância na Pesquisa
45.98%
This paper establishes theoretical bonafides for implicit concurrent multivariate effect evaluation--implicit concurrency for short---a broad and versatile computational learning efficiency thought to underlie general-purpose, non-local, noise-tolerant optimization in genetic algorithms with uniform crossover (UGAs). We demonstrate that implicit concurrency is indeed a form of efficient learning by showing that it can be used to obtain close-to-optimal bounds on the time and queries required to approximately correctly solve a constrained version (k=7, \eta=1/5) of a recognizable computational learning problem: learning parities with noisy membership queries. We argue that a UGA that treats the noisy membership query oracle as a fitness function can be straightforwardly used to approximately correctly learn the essential attributes in O(log^1.585 n) queries and O(n log^1.585 n) time, where n is the total number of attributes. Our proof relies on an accessible symmetry argument and the use of statistical hypothesis testing to reject a global null hypothesis at the 10^-100 level of significance. It is, to the best of our knowledge, the first relatively rigorous identification of efficient computational learning in an evolutionary algorithm on a non-trivial learning problem.; Comment: For an easy introduction to implicit concurrency (with animations)...

From Darwin to Sommerfeld: Genetic algorithms and the electron gas

Stoico, Cesar O.; Renzi, Danilo G.; Vericat, Fernando
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 09/12/2004 Português
Relevância na Pesquisa
45.98%
In return for the long-standing contributions of Physics to Biology, now the inverse way is frequently traveled through in order to think about many physics phenomena. In this vein, evolutionary algorithms, particularly genetic algorithms, are being more and more used as a tool to deal with several Physics problems. Here, we show how to apply a genetic algorithm to describe the homogeneous electron gas.; Comment: 8 pages, 3 figures

Genetic Algorithms and Experimental Discrimination of SUSY Models

Allanach, B. C.; Grellscheid, D.; Quevedo, F.
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Português
Relevância na Pesquisa
45.98%
We introduce genetic algorithms as a means to estimate the accuracy required to discriminate among different models using experimental observables. We exemplify the technique in the context of the minimal supersymmetric standard model. If supersymmetric particles are discovered, models of supersymmetry breaking will be fit to the observed spectrum and it is beneficial to ask beforehand: what accuracy is required to always allow the discrimination of two particular models and which are the most important masses to observe? Each model predicts a bounded patch in the space of observables once unknown parameters are scanned over. The questions can be answered by minimising a "distance" measure between the two hypersurfaces. We construct a distance measure that scales like a constant fraction of an observable. Genetic algorithms, including concepts such as natural selection, fitness and mutations, provide a solution to the minimisation problem. We illustrate the efficiency of the method by comparing three different classes of string models for which the above questions could not be answered with previous techniques. The required accuracy is in the range accessible to the Large Hadron Collider (LHC) when combined with a future linear collider (LC) facility. The technique presented here can be applied to more general classes of models or observables.; Comment: 23 pages...

Results of Evolution Supervised by Genetic Algorithms

Jäntschi, Lorentz; Bolboac{\ba}, Sorana D.; Bălan, Mugur C.; Sestraş, Radu E.
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 05/09/2010 Português
Relevância na Pesquisa
45.98%
A series of results of evolution supervised by genetic algorithms with interest to agricultural and horticultural fields are reviewed. New obtained original results from the use of genetic algorithms on structure-activity relationships are reported.; Comment: 6 pages, 1 Table, 2 figures

Search for overlapped communities by parallel genetic algorithms

Carchiolo, Vincenza; Longheu, Alessandro; Malgeri, Michele; Mangioni, Giuseppe
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Português
Relevância na Pesquisa
45.98%
In the last decade the broad scope of complex networks has led to a rapid progress. In this area a particular interest has the study of community structures. The analysis of this type of structure requires the formalization of the intuitive concept of community and the definition of indices of goodness for the obtained results. A lot of algorithms has been presented to reach this goal. In particular, an interesting problem is the search of overlapped communities and it is field seems very interesting a solution based on the use of genetic algorithms. The approach discusses in this paper is based on a parallel implementation of a genetic algorithm and shows the performance benefits of this solution.; Comment: 6 pages IEEE format, International Journal of Computer Science and Information Security, IJCSIS November 2009, ISSN 1947 5500, http://sites.google.com/site/ijcsis/

Tuning a Multiple Classifier System for Side Effect Discovery using Genetic Algorithms

Reps, Jenna M.; Aickelin, Uwe; Garibaldi, Jonathan M.
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 03/09/2014 Português
Relevância na Pesquisa
45.98%
In previous work, a novel supervised framework implementing a binary classifier was presented that obtained excellent results for side effect discovery. Interestingly, unique side effects were identified when different binary classifiers were used within the framework, prompting the investigation of applying a multiple classifier system. In this paper we investigate tuning a side effect multiple classifying system using genetic algorithms. The results of this research show that the novel framework implementing a multiple classifying system trained using genetic algorithms can obtain a higher partial area under the receiver operating characteristic curve than implementing a single classifier. Furthermore, the framework is able to detect side effects efficiently and obtains a low false positive rate.; Comment: Proceedings of the 2014 World Congress on Computational Intelligence (WCCI 2014), pp. 910-917, IEEE, Beijing, 2014

Digenes: genetic algorithms to discover conjectures about directed and undirected graphs

Absil, Romain; Mélot, Hadrien
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 30/04/2013 Português
Relevância na Pesquisa
45.98%
We present Digenes, a new discovery system that aims to help researchers in graph theory. While its main task is to find extremal graphs for a given (function of) invariants, it also provides some basic support in proof conception. This has already been proved to be very useful to find new conjectures since the AutoGraphiX system of Caporossi and Hansen (Discrete Math. 212-2000). However, unlike existing systems, Digenes can be used both with directed or undirected graphs. In this paper, we present the principles and functionality of Digenes, describe the genetic algorithms that have been designed to achieve them, and give some computational results and open questions. This do arise some interesting questions regarding genetic algorithms design particular to this field, such as crossover definition.; Comment: 17 Pages, 2 Figures, 2 Tables

A philosophical essay on life and its connections with genetic algorithms

Lobo, Fernando G.
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 20/02/2004 Português
Relevância na Pesquisa
45.98%
This paper makes a number of connections between life and various facets of genetic and evolutionary algorithms research. Specifically, it addresses the topics of adaptation, multiobjective optimization, decision making, deception, and search operators, among others. It argues that human life, from birth to death, is an adaptive or dynamic optimization problem where people are continuously searching for happiness. More important, the paper speculates that genetic algorithms can be used as a source of inspiration for helping people make decisions in their everyday life.; Comment: 10 pages, submitted to gecco 2004

Genetic Algorithms for Digital Quantum Simulations

Heras, U. Las; Alvarez-Rodriguez, U.; Solano, E.; Sanz, M.
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 02/12/2015 Português
Relevância na Pesquisa
45.98%
We propose genetic algorithms, which are robust optimization techniques inspired by natural selection, to enhance the versatility of digital quantum simulations. In this sense, we show that genetic algorithms can be employed to increase the fidelity and optimize the resource requirements of digital quantum simulation protocols, while adapting naturally to the experimental constraints. Furthermore, this method allows us to reduce not only digital errors, but also experimental errors in quantum gates. Indeed, by adding ancillary qubits, we design a modular gate made out of imperfect gates, whose fidelity is larger than the fidelity of any of the constituent gates. Finally, we prove that the proposed modular gates are resilient against different gate errors.

Optimal design of building structures using genetic algorithms

Chan, Eduardo
Fonte: California Institute of Technology Publicador: California Institute of Technology
Tipo: Report or Paper; PeerReviewed Formato: application/pdf
Publicado em 01/01/1997 Português
Relevância na Pesquisa
45.98%
A general framework for multi-criteria optimal design is presented which is well-suited for automated design of structural systems. A systematic computer-aided optimal design decision process is developed which allows the designer to rapidly evaluate and improve a proposed design by taking into account the major factors of interest related to different aspects such as design, construction, and operation. The proposed optimal design process requires the selection of the most promising choice of design parameters taken from a large design space, based on an evaluation using specified criteria. The design parameters specify a particular design, and so they relate to member sizes, structural configuration, etc. The evaluation of the design uses performance parameters which may include structural response parameters, risks due to uncertain loads and modeling errors, construction and operating costs, etc. Preference functions are used to implement the design criteria in a "soft" form. These preference functions give a measure of the degree of satisfaction of each design criterion. The overall evaluation measure for a design is built up from the individual measures for each criterion through a preference combination rule. The goal of the optimal design process is to obtain a design that has the highest overall evaluation measure - an optimization problem. Genetic algorithms are stochastic optimization methods that are based on evolutionary theory. They provide the exploration power necessary to explore high-dimensional search spaces to seek these optimal solutions. Two special genetic algorithms...