The research presented in this thesis is concerned with optimising the structure of Artificial Neural Networks. These techniques are based on computer modelling of biological evolution or foetal development. They are known as Evolutionary, Genetic or Embryological methods. Specifically, Embryological techniques are used to grow Artificial Neural Network topologies. The Embryological Algorithm is an alternative to the popular Genetic Algorithm, which is widely used to achieve similar results. The algorithm grows in the sense that the network structure is added to incrementally and thus changes from a simple form to a more complex form. This is unlike the Genetic Algorithm, which causes the structure of the network to evolve in an unstructured or random way. The thesis outlines the following original work: The operation of the Embryological Algorithm is described and compared with the Genetic Algorithm. The results of an exhaustive literature search in the subject area are reported. The growth strategies which may be used to evolve Artificial Neural Network structure are listed. These growth strategies are integrated into an algorithm for network growth. Experimental results obtained from using such a system are described and there is a discussion of the applications of the approach. Consideration is given of the advantages and disadvantages of this technique and suggestions are made for future work in the area. A new learning algorithm based on Taguchi methods is also described. The report concludes that the method of incremental growth is a useful and powerful technique for defining neural network structures and is more efficient than its alternatives. Recommendations are also made with regard to the types of network to which this approach is best suited. Finally, the report contains a discussion of two important aspects of Genetic or Evolutionary techniques related to the above. These are Modular networks (and their synthesis) and the functionality of the network itself.

This thesis addresses one of the major outstanding problems in the study of self-assembled InAs quantum dots (QDs): their physical profile after deposition of a capping layer and post-growth processing. The optical properties of QDs depend critically on the shape, composition and strain profile, yet these parameters are inaccessible to most experimental techniques once the dots are buried. Data from various x-ray scattering experiments are presented here, along with a novel approach to simulating diffuse scattering using an atomistic model based on Keating energy minimisation. The size and position of the diffuse scattering on the low-Q side of the Bragg peak, which are strongly influenced by the shape and composition of the QDs, has been used to determine that the QDs are truncated pyramids with a diagonal base length of 28 nm, with their edges aligned along the [100] and [010] directions. The composition profile varies from pure InAs at the top to 40-60% InAs at the base. These properties all agree with recent cross-sectional scanning tunnelling microscopy (X-STM) measurements by Bruls et al. It was shown that post-growth annealing causes a reduction in the In content of the QDs, primarily by diffusion from the base of the dot into the wetting layer. Grazing incidence small angle x-ray scattering (GISAXS) measurements have been made from samples of QDs produced with varying growth interruptions (GI) before deposition of the capping layer. The QDs were found to be highly diffuse. After a GI, the dots have been shown to change shape anisotropically, with two facets becoming sharper. An investigation of the use of resonant scattering to study buried QDs has shown that the method of contrast variation is of limited use for enhancing the measurement of diffuse features away from the Bragg peak. It is unsuitable for the study of buried nanostructures.

Tapered I-section members have been employed widely for the design of long-span structures such as large clear-span buildings, stadiums, and bridges because of their structural efficiency. For optimized member design providing maximum strength and stiffness at minimum cost, general non-prismatic (tapered and/or stepped cross-sections) as well as singly-symmetric cross-sections have been commonly employed. Fabricators equipped to produce web-tapered members can create a wide range of optimized members from a minimal stock of different plates and coil. Linearly tapered web plates can be nested to minimize scrap. In many cases, the savings in material and manufacturing efficiencies lead to significant cost savings relative to the use of comparable rolled shapes. To employ Design Guide 25 (DG25) which provides guidance for the application of the provisions of the AISC Specification to the design of frames composed of general non-prismatic members, designers need a robust and general capability for determining the elastic buckling loads. Furthermore, robust tools are needed to facilitate the selection of optimum non-prismatic member designs based on minimum cost. This research addresses the calculation of the elastic buckling loads for general non-prismatic members subjected to general loadings and bracing conditions (typically involving multiple brace points along a given member). This research develops an elastic buckling analysis tool (SABRE2) that can be used to define general geometries, loadings and bracing conditions and obtain a rigorous calculation of the elastic buckling load levels. The three-dimensional finite element equations using open section thin-walled beam theory are derived and formulated using a co-rotational approach including load height effects of transverse loads, stepped flange dimensions, and bracing and support height effects. In addition, this research addresses an algorithmic means to obtain automatic optimized member and frame designs using the above types of members based on Genetic Algorithms (GA). These capabilities are implemented in the tool SABRE2D, which provides a graphical user interface for optimized member and frame design based on updated DG25 provisions and the elastic buckling load calculations from SABRE2.

Regarding the problems of resource allocation in OFDMA-based wireless communication systems, much of the research effort mainly focuses on finding efficient power control and subcarrier assignment policies. With systems employing multicast transmission, the available schemes in literature are not always applicable. Moreover, the existing approaches are particularly inaccessible in practical systems in which there are a large number of OFDM subcarriers being utilized, as the required computational burden is prohibitively high. The ultimate goal of this research is therefore to propose affordable mechanisms to flexibly and effectively share out the available resources in multicast wireless systems deploying OFDMA technology. Specifically, we study the resource distribution problems in both conventional and cognitive radio network settings, formulating the design problems as mathematical optimization programs, and then offering the solution methods. Suboptimal and optimal schemes with high performance and yet of acceptable complexity are devised through the application of various mathematical optimization tools such as genetic algorithm and Lagrangian dual optimization. The novelties of the proposed approaches are confirmed, and their performances are verified by computer simulation with the presentation of numerical examples to support the findings. / Communications

AN ABSTRACT OF THE THESIS OF SOROOSH SOHANGIR, for the MASTER OF SCIENCE degree in COMPUTER SCIENCE, presented on 9 th November 2011, at Southern Illinois University Carbondale. TITLE: OPTIMIZED FEATURE SELECTION USING NEUROEVOLUTION OF AUGMENTING TOPOLOGIES (NEAT) MAJOR PROFESSOR: Dr. Shahram Rahimi Feature selection using the NeuroEvolution of Augmenting Topologies (NEAT) is a new approach. In this thesis an investigation had been carried out for implementation based on optimization of the network topology and protecting innovation through the speciation which is similar to what happens in nature. The NEAT is implemented through the JNEAT package and Utans method for feature selection is deployed. The performance of this novel method is compared with feature selection using Multilayer Perceptron (MLP) where Belue, Tekto, and Utans feature selection methods is adopted. According to unveiled data from this thesis the number of species, the training, accuracy and number of hidden neurons are notably improved as compared with conventional networks. For instance the time is reduced by factor of three.

O Atracamento Molecular é uma importante ferramenta utilizada no descobrimento de novos fármacos. O atracamento com ligante flexível é um processo computacionalmente custoso devido ao número alto de graus de liberdade do ligante e da rugosidade do espaço de busca conformacional representando a afinidade entre o receptor e uma molécula ligante. O problema é definido como a busca pela solução de menor energia de ligação proteína-ligante. Considerando uma função suficientemente acurada, a solução ótima coincide com a melhor orientação e afinidade entre as moléculas. Assim, o método de busca e a função de energia são partes fundamentais para a resolução do problema. Muitos desafios são enfrentados para a resolução do problema, o tratamento da flexibilidade, algoritmo de amostragem, a exploração do espaço de busca, o cálculo da energia livre entre os átomos, são alguns dos focos estudados. Esta dissertação apresenta uma técnica baseada em um Algoritmo Genético de Chaves Aleatórias Viciadas, incluindo a discretização do espaço de busca e métodos de agrupamento para a multimodalidade do problema de atracamento molecular. A metodologia desenvolvida explora o espaço de busca gerando soluções diversificadas. O método proposto foi testado em uma seleção de complexos proteína-ligante e foi comparado com softwares existentes: AutodockVina e Dockthor. Os resultados foram estatisticamente analisados em termos estruturais. O método se mostrou eficiente quando comparado com outras ferramentas e uma alternativa para o problema de Atracamento Molecular. / Molecular Docking is a valuable tool for drug discovery. Receptor and flexible Ligand docking is a very computationally expensive process due to a large number of degrees of freedom of the ligand and the roughness of the molecular binding search space. A Molecular Docking simulation starts with a receptor and ligand unbounded structures and the algorithm tests hundreds of thousands of ligands conformations and orientations to find the best receptor-ligand binding affinity by assigning and optimizing an energy function. Despite the advances in the conception of methods and computational strategies for search the best protein-ligand binding affinity, the development of new strategies, the adaptation, and investigation of new approaches and the combination of existing and state-of-the-art computational methods and techniques to the Molecular Docking problem are clearly needed. We developed a Biased Random-Key Genetic Algorithm as a sampling strategy to search the protein-ligand conformational space. The proposed method has been tested on a selection of protein-ligand complexes and compared with existing tools AutodockVina and Dockthor. Compared with other traditional docking software, the proposed method has the best average Root-Mean-Square Deviation. Structural results were statistically analyzed. The proposed method proved to be efficient and a good alternative to the molecular docking problem.

Made available in DSpace on 2014-06-11T19:35:40Z (GMT). No. of bitstreams: 0 Previous issue date: 2008-12-19Bitstream added on 2014-06-13T20:46:42Z : No. of bitstreams: 1 pinho_af_dr_guara.pdf: 1635741 bytes, checksum: d8dc3d0b8a67932941a332b122ed1672 (MD5) / Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES) / Métodos de otimização combinados com a simulação computacional a eventos discretos têm sido utilizados em diversas aplicações na manufatura. Entretanto, estes métodos possuem baixo desempenho, em relação ao tempo computacional, ao manipularem mais de uma variável de decisão. Desta forma, o objetivo desta tese de doutorado é propor um método para otimização de modelos de simulação a eventos discretos com maior eficiência em relação ao tempo de processamento quando comparado a uma ferramenta comercial conhecida. Cabe ressaltar que a qualidade da variável de resposta não será alterada, ou seja, o método proposto manterá a eficácia das soluções encontradas. Será mostrado que a melhora neste desempenho é obtida através de uma melhor percepção do comportamento dos parâmetros existentes nos algoritmos genéticos, em especial o parâmetro tamanho da população. A comparação entre o método desenvolvido com a ferramenta de otimização existente no mercado se dará através de uma metodologia já consolidada disponível na literatura. As conclusões serão apresentadas comprovando a eficácia do método proposto. / Optimization methods combined with discrete events simulation have been used in many manufacturing applications. However, these methods have poor performance considering the computational time, when manipulating more than one decision variable. In this way, the aim of this thesis is to propose a method for optimizing discrete events simulation models with higher efficiency in relation to the processing time when compared to a known commercial tool. Besides, the optimization quality will not be altered, i. e., the proposed method will keep the effectiveness of the achieved solutions. It will be shown that the performance improvement is obtained by means of a better perception of the behavior of all parameters presented in the genetic algorithms, particularly the population size parameter. The comparison between the developed method and the optimization tool will be accomplished by means of a consolidated methodology available in the simulation literature. The conclusions will be presented proving the effectiveness of the developed method.

abstract: In this thesis, the author described a new genetic algorithm based on the idea: the better design could be found at the neighbor of the current best design. The details of the new genetic algorithm are described, including the rebuilding process from Micro-genetic algorithm and the different crossover and mutation formation. Some popular examples, including two variable function optimization and simple truss models are used to test this algorithm. In these study, the new genetic algorithm is proved able to find the optimized results like other algorithms. Besides, the author also tried to build one more complex truss model. After tests, the new genetic algorithm can produce a good and reasonable optimized result. Form the results, the rebuilding, crossover and mutation can the jobs as designed. At last, the author also discussed two possible points to improve this new genetic algorithm: the population size and the algorithm flexibility. The simple result of 2D finite element optimization showed that the effectiveness could be better, with the improvement of these two points. / Dissertation/Thesis / Masters Thesis Civil and Environmental Engineering 2015

Submitted by JAIME AYRES DE OLIVEIRA JUNIOR null (jaime.oliveira@hotmail.com.br) on 2016-07-22T04:35:50Z No. of bitstreams: 1 2016 07 22 Msc - Oliveria - Dissertação Final.pdf: 2108988 bytes, checksum: a6e2312b794bd367675f203f7d27a138 (MD5) / Approved for entry into archive by Ana Paula Grisoto (grisotoana@reitoria.unesp.br) on 2016-07-28T13:42:33Z (GMT) No. of bitstreams: 1 oliveirajunior_ja_me_bauru.pdf: 2108988 bytes, checksum: a6e2312b794bd367675f203f7d27a138 (MD5) / Made available in DSpace on 2016-07-28T13:42:33Z (GMT). No. of bitstreams: 1 oliveirajunior_ja_me_bauru.pdf: 2108988 bytes, checksum: a6e2312b794bd367675f203f7d27a138 (MD5) Previous issue date: 2016-06-02 / Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES) / O objetivo deste trabalho é analisar o comportamento dinâmico de um sistema de suspensão eletromecânica aplicado a veículos, aplicando um algoritmo genético para maximizar o conforto dos passageiros e maximizar a energia recuperada através do subsistema elétrico. Em sistemas de suspensão mecânica, a energia vibratória é dissipada, por exemplo, em um amortecedor viscoso. É utilizado um modelo de quarto de carro com dois graus de liberdade para expressar a dinâmica vertical do sistema. Utiliza-se a equação de Euler-Lagrange para relacionar os tipos de energia envolvidos (cinética, potencial, elétrica e magnética) para escrever as equações dinâmicas do sistema. O modelo é constituído de dois domínios, um mecânico, do qual fazem parte massa e rigidez, e um elétrico, do qual faz parte um circuito RLC. Os dois domínios são associados através de um transdutor. Neste caso, uma bobina converte o movimento do subsistema mecânico em corrente elétrica no subsistema elétrico. Devido ao grande número de parâmetros e à existência de múltiplos objetivos, opta-se por utilizar um algoritmo genético para realizar a otimização do sistema de suspensão. O desempenho do algoritmo de otimização é analisada observando-se convergência e exploração do espaço de busca. Os resultados são obtidos através de expressões analíticas e simulações numéricas. / The objective of this study is to analyze the dynamic behavior of an electromechanical suspension system applied to vehicles, applying a genetic algorithm to maximize passenger comfort and to maximize the energy recovered through the electrical subsystem. In mechanical suspension systems, vibration energy is dissipated, for example, by a viscous damper. A quarter car model with two degrees of freedom is used to express the vertical dynamics of the system. The Euler-Lagrange equations are used to relate the types of energy involved (kinetic, potential, electrical and magnetic) to write the dynamic equations of the system. The model consists of two domains, a mechanic, which comprises mass and stiffness, and an electric, a RLC circuit. The two subsystems are associated with a transducer. In this case, a moving coil converts the movement of the mechanical subsystem in electrical current in the electrical subsystem. Due to the large number of parameters and the existence of multiple objectives, it is chosen to use a genetic algorithm to perform optimization of the suspension system. The performance of the optimization algorithm is analyzed observing convergence and search space exploration. The results are obtained by analytical expressions and numeric simulations.

O Atracamento Molecular é uma importante ferramenta utilizada no descobrimento de novos fármacos. O atracamento com ligante flexível é um processo computacionalmente custoso devido ao número alto de graus de liberdade do ligante e da rugosidade do espaço de busca conformacional representando a afinidade entre o receptor e uma molécula ligante. O problema é definido como a busca pela solução de menor energia de ligação proteína-ligante. Considerando uma função suficientemente acurada, a solução ótima coincide com a melhor orientação e afinidade entre as moléculas. Assim, o método de busca e a função de energia são partes fundamentais para a resolução do problema. Muitos desafios são enfrentados para a resolução do problema, o tratamento da flexibilidade, algoritmo de amostragem, a exploração do espaço de busca, o cálculo da energia livre entre os átomos, são alguns dos focos estudados. Esta dissertação apresenta uma técnica baseada em um Algoritmo Genético de Chaves Aleatórias Viciadas, incluindo a discretização do espaço de busca e métodos de agrupamento para a multimodalidade do problema de atracamento molecular. A metodologia desenvolvida explora o espaço de busca gerando soluções diversificadas. O método proposto foi testado em uma seleção de complexos proteína-ligante e foi comparado com softwares existentes: AutodockVina e Dockthor. Os resultados foram estatisticamente analisados em termos estruturais. O método se mostrou eficiente quando comparado com outras ferramentas e uma alternativa para o problema de Atracamento Molecular. / Molecular Docking is a valuable tool for drug discovery. Receptor and flexible Ligand docking is a very computationally expensive process due to a large number of degrees of freedom of the ligand and the roughness of the molecular binding search space. A Molecular Docking simulation starts with a receptor and ligand unbounded structures and the algorithm tests hundreds of thousands of ligands conformations and orientations to find the best receptor-ligand binding affinity by assigning and optimizing an energy function. Despite the advances in the conception of methods and computational strategies for search the best protein-ligand binding affinity, the development of new strategies, the adaptation, and investigation of new approaches and the combination of existing and state-of-the-art computational methods and techniques to the Molecular Docking problem are clearly needed. We developed a Biased Random-Key Genetic Algorithm as a sampling strategy to search the protein-ligand conformational space. The proposed method has been tested on a selection of protein-ligand complexes and compared with existing tools AutodockVina and Dockthor. Compared with other traditional docking software, the proposed method has the best average Root-Mean-Square Deviation. Structural results were statistically analyzed. The proposed method proved to be efficient and a good alternative to the molecular docking problem.