Evolutionary algorithms are optimization techniques inspired by the actual evolution of biological species. They use conceptually simple process of two repeating phases of reproduction and fitness-based selection, that iteratively evolves each time better solutions. Evolutionary algorithms receive a lot of attention for being able to solve very hard optimization problems, where other optimization techniques might fail due to existence of many local optima. Wide range of different variants of evolutionary algorithms have been proposed. In this thesis, we will focus on the area of Estimation of Distribution Algorithms (EDA). When creating the next generation, EDAs transform the selected high-fitness population into a probability distribution. New generation is obtained by sampling the estimated distribution. We will design and and implement combinations of existing EDAs that will operate in business-specific environment, that can be characterized as tree-like structure of both discrete and continuous variables. Also, additional linear inequality constraints are specified to applicable solutions. Implemented application communicates with provided interfaces, retrieving the problem model specification and storing populations into database. Database is used to assign externally computed fitness values from...

This thesis deals with agent behavior evolution for the environment of a real computer game using evolutionary algorithms. The game Unreal Tournament 2004 was chosen, due to its ease of use for creating agents manually with the Pogamut suite of tools. As a decision making structure for the agents yaPOSH reactive plans were used. Due to the demanding needs on the hardware and time a real computer game is not considered to be very suitable for artificial evolution. To overcome this fact a light-weighted environment LightEnv, that simulates only those aspects that are important for agent evolution, was created. The evolution was based on genetic programming modified for use with yaPOSH reactive plans. The evolved agent behavior for death match and team death match game scenarios exceeded the preprogrammed ones and was successfully transferred to Unreal Tournament 2004 environment. In the team death match scenario an interesting behavior that utilizes agent communication was evolved.

Tree-based genetic programming (GP) has several known shortcomings: difficult adaptability to specific programming languages and environments, the problem of closure and multiple types, and the problem of declarative representation of knowledge. Most of the methods that try to solve these problems are based on formal grammars. The precise effect of their distinctive features is often difficult to analyse and a good comparison of performance in specific problems is missing. This thesis reviews three grammar-based methods: context-free grammar genetic programming (CFG-GP), including its variant GPHH recently applied to exam timetabling, grammatical evolution (GE), and LOGENPRO, it discusses how they solve the problems encountered by GP, and compares them in a series of experiments in six applications using success rates and derivation tree characteristics. The thesis demonstrates that neither GE nor LOGENPRO provide a substantial advantage over CFG-GP in any of the experiments, and analyses the differences between the effects of operators used in CFG-GP and GE. It also presents results from a highly efficient implementation of CFG-GP and GE.

Neural connections in the human brain are known to be modified by experiences. Yet, little is known about the mechanism of the modification and its implications on the brain function. The aim of this thesis is to investigate what impact the spatial properties of brain tissue can have on learning and memory. In particular, we focus on the dendritic plasticity. We present a model where the tissue is represented by a two-dimensional grid and its structure is characterized by various connections between the grid cells. We provide a formal definition of the model and we prove it to be computational as strong as the Turing machine. An adaptation algorithm proposed enables the model to reflect the environmental feedback, while evolutionary algorithms are employed to search for a satisfactory architecture of the model. Implementation is provided and several experiments are driven to demonstrate the key properties of the model. Powered by TCPDF (www.tcpdf.org)

Evolutionary algorithms have proved to be useful for tackling many practical black-box optimization problems. In this thesis, we describe one of the most powerful evolutionary algorithms of today, CMA- ES, and apply it in novel way to solve the problem of tuning multiple coupled PID controllers in combustion engine models. Powered by TCPDF (www.tcpdf.org)

With maritime industry carrying out nearly 90% of the volume of global trade, the algorithms and solutions to provide quality of services in maritime transportation are of great importance to both academia and the industry. This research investigates an optimization problem using evolutionary algorithms and big data analytics to address an important challenge in maritime disruption management, and illustrates how it can be engaged with information technologies and Internet of Things. Accordingly, in this thesis, we design, develop and evaluate methods to improve decision support systems (DSSs) in maritime supply chain management. We pursue three research goals in this thesis. First, the Vessel Schedule recovery Problem (VSRP) is reformulated and a bi-objective optimization approach is proposed. We employ bi-objective evolutionary algorithms (MOEAs) to solve optimization problems. An optimal Pareto front provides a valuable trade-off between two objectives (minimizing delay and minimizing financial loss) for a stakeholder in the freight ship company. We evaluate the problem in three domains, namely scalability analysis, vessel steaming policies, and voyage distance analysis, and statistically validate their performance significance. According to the experiments, the problem complexity varies in different scenarios, while NSGAII performs better than other MOEAs in all scenarios. In the second work, a new data-driven VSRP is proposed, which benefits from the available Automatic Identification System (AIS) data. In the new formulation, the trajectory between the port calls is divided and encoded into adjacent geohashed regions. In each geohash, the historical speed profiles are extracted from AIS data. This results in a large-scale optimization problem called G-S-VSRP with three objectives (i.e., minimizing loss, delay, and maximizing compliance) where the compliance objective maximizes the compliance of optimized speeds with the historical data. Assuming that the historical speed profiles are reliable to trust for actual operational speeds based on other ships' experience, maximizing the compliance of optimized speeds with these historical data offers some degree of avoiding risks. Three MOEAs tackled the problem and provided the stakeholder with a Pareto front which reflects the trade-off among the three objectives. Geohash granularity and dimensionality reduction techniques were evaluated and discussed for the model. G-S-VSRPis a large-scale optimization problem and suffers from the curse of dimensionality (i.e. problems are difficult to solve due to exponential growth in the size of the multi-dimensional solution space), however, due to a special characteristic of the problem instance, a large number of function evaluations in MOEAs can still find a good set of solutions. Finally, when the compliance objective in G-S-VSRP is changed to minimization, the regular MOEAs perform poorly due to the curse of dimensionality. We focus on improving the performance of the large-scale G-S-VSRP through a novel distributed multiobjective cooperative coevolution algorithm (DMOCCA). The proposed DMOCCA improves the quality of performance metrics compared to the regular MOEAs (i.e. NSGAII, NSGAIII, and GDE3). Additionally, the DMOCCA results in speedup when running on a cluster.

Nesta tese, são estudados algoritmos para agrupamento de dados, com particular ênfase em Agrupamento de Dados com Restrições, no qual, além dos objetos a serem agrupados, são fornecidos pelo usuário algumas informações sobre o agrupamento desejado. Como fundamentação para o agrupamento, são considerados os modelos de mistura finitos, em especial, com componentes gaussianos, usualmente chamados de modelos de mistura de gaussianas. Dentre os principais problemas que os algoritmos desenvolvidos nesta tese de doutorado buscam tratar destacam-se: (i) estimar parâmetros de modelo de mistura de gaussianas; (ii) como incorporar, de forma eficiente, restrições no processo de aprendizado de forma que tanto os dados quanto as restrições possam ser adicionadas de forma online; (iii) estimar, via restrições derivadas de conceitos pré-determinados sobre os objetos (usualmente chamados de classes), o número de grupos destes conceitos. Como ferramenta para auxiliar no desenvolvimento de soluções para tais problemas, foram utilizados algoritmos evolutivos que operam com mais de uma solução simultaneamente, além de utilizarem informações de soluções anteriores para guiar o processo de busca. Especificamente, foi desenvolvido um algoritmo evolutivo baseado na divisão e união de componentes para a estimação dos parâmetros de um modelo de mistura de gaussianas. Este algoritmo foi comparado com o algoritmo do mesmo gênero considerado estado-da-arte na literatura, apresentando resultados competitivos e necessitando de menos parâmetros e um menor custo computacional. Nesta tese, foram desenvolvidos dois algoritmos que incorporam as restrições no processo de agrupamento de forma online. Ambos os algoritmos são baseados em algoritmos bem-conhecidos na literatura e apresentaram, em comparações empíricas, resultados melhores que seus antecessores. Finalmente, foram propostos dois algoritmos para se estimar o número de grupos por classe. Ambos os algoritmos foram comparados com algoritmos reconhecidos na literatura de agrupamento de dados com restrições, e apresentaram resultados competitivos ou melhores que estes. A estimação bem sucedida do número de grupos por classe pode auxiliar em diversas tarefas de mineração de dados, desde a sumarização dos dados até a decomposição de problemas de classificação em sub-problemas potencialmente mais simples. / In the last decade, researchers have been giving considerable attention to the field of Constrained Clustering. Algorithms in this field assume that along with the objects to be clustered, the user also provides some constraints about which kind of clustering (s)he prefers. In this thesis, two scenarios are studied: clustering with and without constraints. The developments are based on finite mixture models, namely, models with Gaussian components, which are usually called Gaussian Mixture Models (GMMs). In this context the main problems addressed are: (i) parameter estimation of GMMs; (ii) efficiently integrating constraints in the learning process allowing both constraints and the data to be added in the modeling in an online fashion; (iii) estimating, by using constraints derived from pre-determined concepts (usually named classes), the number of clusters per concept. Evolutionary algorithms were adopted to develop solutions for such problems. These algorithms analyze more than one solution simultaneously and use information provided by previous solutions to guide the search process. Specifically, an evolutionary algorithm based on procedures that perform splitting and merging of components to estimate the parameters of a GMM was developed. This algorithm was compared to an algorithm considered as the state-of-the-art in the literature, obtaining competitive results while requiring less parameters and being more computationally efficient. Besides the aforementioned contributions, two algorithms for online constrained clustering were developed. Both algorithms are based on well known algorithms from the literature and get better results than their predecessors. Finally, two algorithms to estimate the number of clusters per class were also developed. Both algorithms were compared to well established algorithms from the literature of constrained clustering, and obtained equal or better results than the ones obtained by the contenders. The successful estimation of the number of clusters per class is helpful to a variety of data mining tasks, such as data summarization and problem decomposition of challenging classification problems.

Problemas de projeto de redes (PPRs) são muito importantes uma vez que envolvem uma série de aplicações em áreas da engenharia e ciências. Para solucionar as limitações de algoritmos convencionais para PPRs que envolvem redes complexas do mundo real (em geral modeladas por grafos completos ou mesmo esparsos de larga-escala), heurísticas, como os algoritmos evolutivos (EAs), têm sido investigadas. Trabalhos recentes têm mostrado que estruturas de dados adequadas podem melhorar significativamente o desempenho de EAs para PPRs. Uma dessas estruturas de dados é a representação nó-profundidade (NDE, do inglês Node-depth Encoding). Em geral, a aplicação de EAs com a NDE tem apresentado resultados relevantes para PPRs de larga-escala. Este trabalho investiga o desenvolvimento de uma nova representação, baseada na NDE, chamada representação nó-profundidade-grau (NDDE, do inglês Node-depth-degree Encoding). A NDDE é composta por melhorias nos operadores existentes da NDE e pelo desenvolvimento de novos operadores de reprodução possibilitando a recombinação de soluções. Nesse sentido, desenvolveu-se um operador de recombinação capaz de lidar com grafos não-completos e completos, chamado EHR (do inglês, Evolutionary History Recombination Operator). Foram também desenvolvidos operadores de recombinação que lidam somente com grafos completos, chamados de NOX e NPBX. Tais melhorias tem como objetivo manter relativamente baixa a complexidade computacional dos operadores para aumentar o desempenho de EAs para PPRs de larga-escala. A análise de propriedades de representações mostrou que a NDDE possui redundância, assim, foram propostos mecanismos para evitá-la. Essa análise mostrou também que o EHR possui baixa complexidade de tempo e não possui tendência, além de revelar que o NOX e o NPBX possuem uma tendência para árvores com topologia de estrela. A aplicação de EAs usando a NDDE para PPRs clássicos envolvendo grafos completos, tais como árvore geradora de comunicação ótima, árvore geradora mínima com restrição de grau e uma árvore máxima, mostrou que, quanto maior o tamanho das instâncias do PPR, melhor é o desempenho relativo da técnica em comparação com os resultados obtidos com outros EAs para PPRs da literatura. Além desses problemas, um EA utilizando a NDE com o operador EHR foi aplicado ao PPR do mundo real de reconfiguração de sistemas de distribuição de energia elétrica (envolvendo grafos esparsos). Os resultados mostram que o EHR possibilita reduzir significativamente o tempo de convergência do EA / Network design problems (NDPs) are very important since they involve several applications from areas of Engineering and Sciences. In order to solve the limitations of traditional algorithms for NDPs that involve real world complex networks (in general, modeled by large-scale complete or sparse graphs), heuristics, such as evolutionary algorithms (EAs), have been investigated. Recent researches have shown that appropriate data structures can improve EA performance when applied to NDPs. One of these data structures is the Node-depth Encoding (NDE). In general, the performance of EAs with NDE has presented relevant results for large-scale NDPs. This thesis investigates the development of a new representation, based on NDE, called Node-depth-degree Encoding (NDDE). The NDDE is composed for improvements of the NDE operators and the development of new reproduction operators that enable the recombination of solutions. In this way, we developed a recombination operator to work with both non-complete and complete graphs, called EHR (Evolutionary History Recombination Operator). We also developed two other operators to work only with complete graphs, named NOX and NPBX. These improvements have the advantage of retaining the computational complexity of the operators relatively low in order to improve the EA performance. The analysis of representation properties have shown that NDDE is a redundant representation and, for this reason, we proposed some strategies to avoid it. This analysis also showed that EHR has low running time and it does not have bias, moreover, it revealed that NOX and NPBX have bias to trees like stars. The application of an EA using the NDDE to classic NDPs, such as, optimal communication spanning tree, degree-constraint minimum spanning tree and one-max tree, showed that the larger the instance is, the better the performance will be in comparison whit other EAs applied to NDPs in the literatura. An EA using the NDE with EHR was applied to a real-world NDP of reconfiguration of energy distribution systems. The results showed that EHR significantly decrease the convergence time of the EA

In many real classification problems, the data set used for model induction is significantly imbalanced. This occurs when the number of examples of some classes is much lower than the other classes. Imbalanced datasets can compromise the performance of most classical classification algorithms. The classification models induced by such datasets usually present a strong bias towards the majority classes, tending to classify new instances as belonging to these classes. A commonly adopted strategy for dealing with this problem is to train the classifier on a balanced sample from the original dataset. However, this procedure can discard examples that could be important for a better class discrimination, reducing classifier efficiency. On the other hand, in recent years several studies have shown that in different scenarios the strategy of combining several classifiers into structures known as ensembles has proved to be quite effective. This strategy has led to a stable predictive accuracy and, in particular, to a greater generalization ability than the classifiers that make up the ensemble. This generalization power of classifier ensembles has been the focus of research in the imbalanced learning field in order to reduce the bias toward the majority classes, despite the complexity involved in generating efficient ensembles. Optimization meta-heuristics, such as evolutionary algorithms, have many applications for ensemble learning, although they are little used for this purpose. For example, evolutionary algorithms maintain a set of possible solutions and diversify these solutions, which helps to escape out of the local optimal. In this context, this thesis investigates and develops approaches to deal with imbalanced datasets, using ensemble of classifiers induced by samples taken from the original dataset. More specifically, this theses propose three solutions based on evolutionary ensemble learning and a fourth proposal that uses a pruning mechanism based on dominance ranking, a common concept in multiobjective evolutionary algorithms. Experiments showed the potential of the developed solutions. / Em muitos problemas reais de classificação, o conjunto de dados usado para a indução do modelo é significativamente desbalanceado. Isso ocorre quando a quantidade de exemplos de algumas classes é muito inferior às das outras classes. Conjuntos de dados desbalanceados podem comprometer o desempenho da maioria dos algoritmos clássicos de classificação. Os modelos de classificação induzidos por tais conjuntos de dados geralmente apresentam um forte viés para as classes majoritárias, tendendo classificar novas instâncias como pertencentes a essas classes. Uma estratégia comumente adotada para lidar com esse problema, é treinar o classificador sobre uma amostra balanceada do conjunto de dados original. Entretanto, esse procedimento pode descartar exemplos que poderiam ser importantes para uma melhor discriminação das classes, diminuindo a eficiência do classificador. Por outro lado, nos últimos anos, vários estudos têm mostrado que em diferentes cenários a estratégia de combinar vários classificadores em estruturas conhecidas como comitês tem se mostrado bastante eficaz. Tal estratégia tem levado a uma acurácia preditiva estável e principalmente a apresentar maior habilidade de generalização que os classificadores que compõe o comitê. Esse poder de generalização dos comitês de classificadores tem sido foco de pesquisas no campo de aprendizado desbalanceado, com o objetivo de diminuir o viés em direção as classes majoritárias, apesar da complexidade que envolve gerar comitês de classificadores eficientes. Meta-heurísticas de otimização, como os algoritmos evolutivos, têm muitas aplicações para o aprendizado de comitês, apesar de serem pouco usadas para este fim. Por exemplo, algoritmos evolutivos mantêm um conjunto de soluções possíveis e diversificam essas soluções, o que auxilia na fuga dos ótimos locais. Nesse contexto, esta tese investiga e desenvolve abordagens para lidar com conjuntos de dados desbalanceados, utilizando comitês de classificadores induzidos a partir de amostras do conjunto de dados original por meio de metaheurísticas. Mais especificamente, são propostas três soluções baseadas em aprendizado evolucionário de comitês e uma quarta proposta que utiliza um mecanismo de poda baseado em ranking de dominância, conceito comum em algoritmos evolutivos multiobjetivos. Experimentos realizados mostraram o potencial das soluções desenvolvidas.

O presente trabalho investiga metodologias para se obter automaticamente planos de restabelecimento de energia em sistemas de distribuição de energia elétrica, contemplando-se múltiplos objetivos, sendo alguns conflitantes. A redução nos índices de interrupção de energia elétrica deve ser um alvo permanente das empresas de distribuição buscando a melhoria da qualidade de fornecimento. Por outro lado, as interrupções são inevitáveis, quer para a execução de obras de manutenção preventiva, quer para obras de manutenção corretiva em virtude da ocorrência de um defeito no sistema. Depois de uma falta ter sido identificada e isolada, um plano de restabelecimento deve ser encontrado em um curto período de tempo. Devido ao problema de explosão combinatorial, técnicas de programação matemática se tornam proibitivas para esse tipo de aplicação, principalmente em sistemas de tamanho real. Por outro lado, a proposta desenvolvida de algoritmos evolucionários utilizando cadeias de grafos, têm se mostrado capaz de obter planos de restabelecimento de energia em um sistema de tamanho real no menor tempo possível. Este trabalho investiga a utilização desta metodologia para redes de grande porte sem simplificações, isto é, incluindo todas as linhas, barras e chaves do sistema. Testes são realizados em três redes de tamanhos diferentes, considerando diversos objetivos a fim de avaliar a técnica proposta. / This work investigates methodologies to automatically obtain energy restoration plans in distribution systems, involving multiple objectives that are conflicting. The reduction energy interruption indices is a permanent objective of the distribution companies in order to improve power supply. Interruptions may be carried out for maintenance or may occur due to system faults. After a fault have been identified and isolated, a restoration plan is required in a short interval of time. Due to the combinatorial explosion problem it is not possible to apply mathematical programming techniques to produce restoration plans for large networks. On the other hand, an evolutionary algorithm utilizing graph, chain has shown to be able to obtain restoration plans for real-size networks in a short interval of time. Tests are performed for three different size networks, considering several objectives to evaluate the proposed technique.