The Learning Classifier System (LCS) and its descendant, XCS, are promising paradigms for machine learning design and implementation. Whereas LCS allows classifier payoff predictions to guide system performance, XCS focuses on payoff-prediction accuracy instead, allowing it to evolve "optimal" classifier sets in particular applications requiring rational thought. This research examines LCS and XCS performance in artificial situations with broad social/commercial parallels, created using the non-Markov Iterated Prisoner's Dilemma (IPD) game-playing scenario, where the setting is sometimes asymmetric and where irrationality sometimes pays. This research systematically perturbs a "conventional" IPD-playing LCS-based agent until it results in a full-fledged XCS-based agent, contrasting the simulated behavior of each LCS variant in terms of a number of performance measures. The intent is to examine the XCS paradigm to understand how it better copes with a given situation (if it does) than the LCS perturbations studied.Experiment results indicate that the majority of the architectural differences do have a significant effect on the agents' performance with respect to the performance measures used in this research. The results of these competitions indicate that while each architectural difference significantly affected its agent's performance, no single architectural difference could be credited as causing XCS's demonstrated superiority in evolving optimal populations. Instead, the data suggests that XCS's ability to evolve optimal populations in the multiplexer and IPD problem domains result from the combined and synergistic effects of multiple architectural differences.In addition, it is demonstrated that XCS is able to reliably evolve the Optimal Population [O] against the TFT opponent. This result supports Kovacs' Optimality Hypothesis in the IPD environment and is significant because it is the first demonstrated occurrence of this ability in an environment other than the multiplexer and Woods problem domains.It is therefore apparent that while XCS performs better than its LCS-based counterparts, its demonstrated superiority may not be attributed to a single architectural characteristic. Instead, XCS's ability to evolve optimal classifier populations in the multiplexer problem domain and in the IPD problem domain studied in this research results from the combined and synergistic effects of multiple architectural differences.

Classificação é, provavelmente, a tarefa mais estudada na área de Aprendizado de Máquina, possuindo aplicação em uma grande quantidade de problemas reais, como categorização de textos, diagnóstico médico, problemas de bioinformática, além de aplicações comerciais e industriais. De um modo geral, os problemas de classificação podem ser categorizados quanto ao número de rótulos de classe que podem ser associados à cada exemplo de entrada. A abordagem mais investigada pela comunidade de Aprendizado de Máquina é a de classes mutuamente exclusivas. Entretanto, existe uma grande variedade de problemas importantes em que cada exemplo de entrada pode ser associado a mais de um rótulo ou classe. Esses problemas são denominados problemas de classificação multirrótulo. Os Learning Classifier Systems(LCS) constituem uma técnica de Indução de Regras de Classificação que tem como principal mecanismo de busca um Algoritmo Genético. Essa técnica busca encontrar um conjunto de regras que tenha alta precisão de classificação, que seja compreensível e que possua regras consideradas interessantes sob o ponto de vista de classificação. Apesar de existirem na literatura diversos trabalhos sobre os LCS para problemas de classificação com classes mutuamente exclusivas, pouco se tem conhecimento sobre um LCS que seja capaz de lidar com problemas multirrótulo. Dessa maneira, o objetivo desta monografia é apresentar uma proposta de LCS para problemas multirrótulo, que pretende induzir um conjunto de regras de classificação que produza um resultado eficaz e comparável com outras técnicas de classificação. De acordo com esse objetivo, apresenta-se também uma revisão bibliográfica dos temas envolvidos na proposta, que são: Sistemas Classificadores Evolutivos e Classificação Multirrótulo / Classification is probably the most studied task in the Machine Learning area, with applications in a broad number of real problems like text categorization, medical diagnosis, bioinformatics and even comercial and industrial applications. Generally, classification problems can be categorized considering the number of class labels associated to each input instance. The most studied approach by the community of Machine Learning is the one that considers mutually exclusive classes. However, there is a large variety of important problems in which each instance can be associated to more than one class label. This problems are called multi-label classification problems. Learning Classifier Systems (LCS) are a technique for rule induction which uses a Genetic Algorithm as the primary search mechanism. This technique searchs for sets of rules that have high classification accuracy and that are also understandable and interesting on the classification point of view. Although there are several works on LCS for classification problems with mutually exclusive classes, there is no record of an LCS that can deal with the multi-label classification problem. The objective of this work is to propose an LCS for multi-label classification that builds a set of classification rules which achieves results that are efficient and comparable to other multi-label methods. In accordance with this objective this work also presents a review of the themes involved: Learning Classifier Systems and Multi-label Classification

A distributed reinforcement-learning system is designed and implemented on a mobile robot for the study of complex task decomposition in real robot learning environments. The Distributed Q-learning Classifier System (DQLCS) is evolved from the standard Learning Classifier System (LCS) proposed by J.H. Holland. Two of the limitations of the standard LCS are its monolithic nature and its complex apportionment of credit scheme, the bucket brigade algorithm (BBA). The DQLCS addresses both of these problems as well as the inherent difficulties faced by learning systems operating in real environments. We introduce Q-learning as the apportionment of credit component of the DQLCS, and we develop a distributed learning architecture to facilitate complex task decomposition. Based upon dynamic programming, the Q-learning update equation is derived and its advantages over the complex BBA are discussed. The distributed architecture is implemented to provide for faster learning by allowing the system to effectively decrease the size of the problem space it must explore. Holistic and monolithic shaping approaches are used to distribute reward among the learning modules of the DQLCS in a variety of real robot learning experiments. The results of these experiments support the DQLCS as a useful reinforcement learning paradigm and suggest future areas of study in distributed learning systems. / Master of Science

Neste trabalho, investigou-se a utilização de algoritmos evolutivos para identificação de procedimentos de raciocínio utilizados por humanos na construção de soluções para uma classe de problemas cuja principal característica é a utilização de raciocínio dedutivo. Para isso, utilizou-se uma abordagem que explora os diferentes níveis de complexidade do problema, partindo da análise das estratégias apresentadas por jogadores humanos. Foram realizados diversos ensaios que evoluíram primeiramente, para um modelo de solução puramente combinatória guiada por um algoritmo genético e independente do jogador humano, até atingir um modelo que procura identificar um procedimento de solução que guarde semelhanças com os procedimentos apresentados pelos jogadores humanos. Como resultado, apresentou-se um algoritmo denominado Classificador Genético um sistema de operadores guiado por um algoritmo genético capaz de identificar procedimentos de raciocínio para solução de combinações específicas do problema proposto. Os ensaios permitiram ainda identificar conjuntos de operadores que se combinados corretamente, através de um mecanismo que simule a tomada de decisão do jogador humano, são capazes de aumentar o potencial de identificação de soluções do algoritmo proposto. O estudo também revelou a importância dos mecanismos de memória no processo de solução do problema e as dificuldades em manipular operadores gerais com métodos puramente evolutivos. Foi possível ainda identificar de que modo jogadores humanos tratam os fatores relacionados à diversidade de possíveis encaminhamentos no processo decisório, que afetam a solução do problema proposto. / In this work we investigated the use of evolutionary algorithms to identify logic procedures used by humans in the construction of solutions of a class of problems in which the main characteristic is the use of deductive reasoning. In order to do that it was used an approach that explores the problems different levels of complexity, starting from the strategies analysis presented by human players. Several experiments were carried out where at first moment used a model of solution that is strictly combinatorial guided by a genetic algorithm and independent of the human player that evolved to a model that tries to identify a solution procedure that maintains the similarities with the procedures presented by human players. As a result, we presented an algorithm denominated Genetic Classifier - a system of rules guided by a genetic algorithm - able to identify reasoning procedures for solution of specific combinations of the proposed problem. Moreover, the experiments allowed identifying clusters of rules that if combined correctly, through a mechanism that simulates the decision making performed by a human player, are capable of increasing the potential to identify the solutions of the proposed algorithm. The study also revealed the importance of the memorys mechanism in the process of solving the proposed problem and the difficulties to manipulate general rules with regular evolutionary methodologies. It was also possible to identify the way human players deal with the factors related to the diversity of possible directions in the decision process.

Neste trabalho, investigou-se a utilização de algoritmos evolutivos para identificação de procedimentos de raciocínio utilizados por humanos na construção de soluções para uma classe de problemas cuja principal característica é a utilização de raciocínio dedutivo. Para isso, utilizou-se uma abordagem que explora os diferentes níveis de complexidade do problema, partindo da análise das estratégias apresentadas por jogadores humanos. Foram realizados diversos ensaios que evoluíram primeiramente, para um modelo de solução puramente combinatória guiada por um algoritmo genético e independente do jogador humano, até atingir um modelo que procura identificar um procedimento de solução que guarde semelhanças com os procedimentos apresentados pelos jogadores humanos. Como resultado, apresentou-se um algoritmo denominado Classificador Genético um sistema de operadores guiado por um algoritmo genético capaz de identificar procedimentos de raciocínio para solução de combinações específicas do problema proposto. Os ensaios permitiram ainda identificar conjuntos de operadores que se combinados corretamente, através de um mecanismo que simule a tomada de decisão do jogador humano, são capazes de aumentar o potencial de identificação de soluções do algoritmo proposto. O estudo também revelou a importância dos mecanismos de memória no processo de solução do problema e as dificuldades em manipular operadores gerais com métodos puramente evolutivos. Foi possível ainda identificar de que modo jogadores humanos tratam os fatores relacionados à diversidade de possíveis encaminhamentos no processo decisório, que afetam a solução do problema proposto. / In this work we investigated the use of evolutionary algorithms to identify logic procedures used by humans in the construction of solutions of a class of problems in which the main characteristic is the use of deductive reasoning. In order to do that it was used an approach that explores the problems different levels of complexity, starting from the strategies analysis presented by human players. Several experiments were carried out where at first moment used a model of solution that is strictly combinatorial guided by a genetic algorithm and independent of the human player that evolved to a model that tries to identify a solution procedure that maintains the similarities with the procedures presented by human players. As a result, we presented an algorithm denominated Genetic Classifier - a system of rules guided by a genetic algorithm - able to identify reasoning procedures for solution of specific combinations of the proposed problem. Moreover, the experiments allowed identifying clusters of rules that if combined correctly, through a mechanism that simulates the decision making performed by a human player, are capable of increasing the potential to identify the solutions of the proposed algorithm. The study also revealed the importance of the memorys mechanism in the process of solving the proposed problem and the difficulties to manipulate general rules with regular evolutionary methodologies. It was also possible to identify the way human players deal with the factors related to the diversity of possible directions in the decision process.

Present day air traffc control is reaching its operational limits and accommodating future traffic growth will be a challenging task for air traffic service providers and airline operators. Free Flight is a proposed transition from a highly-structured and centrally-controlled air traffic system to a self-optimized and highly-distributed system. In Free Flight, pilots will have the flexibility of real-time trajectory planning and dynamic route optimization given airspace constraints (traffic, weather etc.). A variety of advanced air traffc management (ATM) concepts are proposed as enabling technologies for the realization of Free Flight. Since these concepts can be exposed to unforeseen and challenging scenarios in Free Flight, they need to be validated and evaluated in order to implement the most effective systems in the field. Evaluation of advanced ATM concepts is a challenging task due to the limitations in the existing scenario generation methodologies and limited availability of a common platform (air traffic simulator) where diverse ATM concepts can be modeled and evaluated. Their rigorous evaluation on safety metrics, in a variety of complex scenarios, can provide an insight into their performance, which can help improve upon them while developing new ones. In this thesis, I propose a non-propriety, non-commercial air traffic simulation system, with a novel representation of airspace, which can prototype advanced ATM concepts such as conflict detection and resolution, airborne weather avoidance and cockpit display of traffic information. I then propose a novel evolutionary computation methodology to algorithmically generate a massive number of conflict scenarios of increasing complexity in order to evaluate conflict detection algorithms. I illustrate the methodology in detail by quantitative evaluation of three conflict detection algorithms, from the literature, on safety metrics. I then propose the use of data mining techniques for the discovery of interesting relationships, that may exist implicitly, in the algorithm's performance data. The data mining techniques formulate the conflict characteristics, which may lead to algorithm failure, using if-then rules. Using the rule sets for each algorithm, I propose an ensemble of conflict detection algorithms which uses a switch mechanism to direct the subsequent conflict probes to an algorithm which is less vulnerable to failure in a given conflict scenario. The objective is to form a predictive model for algorithm's vulnerability which can then be included in an ensemble that can minimize the overall vulnerability of the system. In summary, the contributions of this thesis are: 1. A non-propriety, non-commercial air traffic simulation system with a novel representation of airspace for efficient modeling of advanced ATM concepts. 2. An Ant-based dynamic weather avoidance algorithm for traffic-constrained enroute airspace. 3. A novel representation of 4D air traffic scenario that allows the use of an evolutionary computation methodology to evolve complex conflict scenarios for the evaluation of conflict detection algorithms. 4. An evaluation framework where scenario generation, scenario evaluation and scenario evolution processes can be carried out in an integrated manner for rigorous evaluation of advanced ATM concepts. 5. A methodology for forming an intelligent ensemble of conflict detection algorithms by data mining the scenario space.

This thesis is focused on the analysis and development of Ensembles of Neural Networks. An ensemble is a system in which a set of heterogeneous Artificial Neural Networks are generated in order to outperform the Single network based classifiers. However, this proposed thesis differs from others related to ensembles of neural networks [1, 2, 3, 4, 5, 6, 7] since it is organized as follows. In this thesis, firstly, an ensemble methods comparison has been introduced in order to provide a rank-based list of the best ensemble methods existing in the bibliography. This comparison has been split into two researches which represents two chapters of the thesis. Moreover, there is another important step related to the ensembles of neural networks which is how to combine the information provided by the neural networks in the ensemble. In the bibliography, there are some alternatives to apply in order to get an accurate combination of the information provided by the heterogeneous set of networks. For this reason, a combiner comparison has also been introduced in this thesis. Furthermore, Ensembles of Neural Networks is only a kind of Multiple Classifier System based on neural networks. However, there are other alternatives to generate MCS based on neural networks which are quite different to Ensembles. The most important systems are Stacked Generalization and Mixture of Experts. These two systems will be also analysed in this thesis and new alternatives are proposed. One of the results of the comparative research developed is a deep understanding of the field of ensembles. So new ensemble methods and combiners can be designed after analyzing the results provided by the research performed. Concretely, two new ensemble methods, a new ensemble methodology called Cross-Validated Boosting and two reordering algorithms are proposed in this thesis. The best overall results are obtained by the ensemble methods proposed. Finally, all the experiments done have been carried out on a common experimental setup. The experiments have been repeated ten times on nineteen different datasets from the UCI repository in order to validate the results. Moreover, the procedure applied to set up specific parameters is quite similar in all the experiments performed. It is important to conclude by remarking that the main contributions are: 1) An experimental setup to prepare the experiments which can be applied for further comparisons. 2) A guide to select the most appropriate methods to build and combine ensembles and multiple classifiers systems. 3) New methods proposed to build ensembles and other multiple classifier systems.

The growth in the use of machine learning in different areas has revealed challenging classification problems that require robust systems. Multiple Classier Systems (MCSs) have attracted interest from researchers as a method that could address such problems. Optimizing the fitness of an MCS improves its, robustness. The lack of an analysis for MCSs from a fitness perspective is identified. To fill this gap, an analytic model from this perspective is derived mathematically by extending the error analysis introduced by Brown and Kuncheva in 2010. The model relates the fitness of an MCS to the average accuracy, positive-diversity, and negative-diversity of the classifiers that constitute the MCS. The model is verified using a statistical analysis of a Monte-Carlo based simulation. This shows the significance of the indicated relationships by the model. This model provides guidelines for developing robust MCSs. It enables the selection of classifiers which compose an MCS with an improved fitness while improving computational cost by avoiding local calculations. The usefulness of the model for designing classification systems is investigated. A new measure consisting of the accuracy and positive-diversity is developed. This measure evaluates fitness while avoiding many calculations compared to the regular measures. A new system (Gadapt) is developed. Gadapt combines machine learning and genetic algorithms to define subsets of the feature space that closely match true class regions. It uses the new measure as a multi-objective criterion for a multi-objective genetic algorithm to identify the MCSs those create the subsets. The design of Gadapt is validated experimentally. The usefulness of the measure and the method of determining the subsets for the performance of Gadapt are examined based on five generated data sets that represent a wide range of problems. The robustness of Gadapt to small amounts of training data is evaluated in comparison with five existing systems on four benchmark data sets. The performance of Gadapt is evaluated in comparison with eleven existing systems on nine benchmark data sets. The analysis of the experiment results supports the validity of the Gadapt design and the outperforming of Gadapt on the existing systems in terms of robustness and performance.

In this thesis, we introduce a radial basis function network approach to solve a color image classification problem in a real time industrial application. Radial basis function networks are employed to classify the images of finished wooden parts in terms of their color and species. Other classification methods are also examined in this work. The minimum distance classifiers are presented since they have been employed by the previous research. We give brief definitions about color space, color texture, color quantization, color classification methods. We also give an intensive review of radial basis functions, regularization theory, regularized radial basis function networks, and generalized radial basis function networks. The centers of the radial basis functions are calculated by the k-means clustering algorithm. We examine the k-means algorithm in terms of starting criteria, the movement rule, and the updating rule. The dilations of the radial basis functions are calculated using a statistical method. Learning classifier systems are also employed to solve the same classification problem. Learning classifier systems learn the training samples completely whereas they are not successful to classify the test samples. Finally, we present some simulation results for both radial basis function network method and learning classifier systems method. A comparison is given between the results of each method. The results show that the best classification method examined in this work is the radial basis function network method. / Master of Science

Ferramentas de geoinformação possuem grande aplicabilidade na compreensão e no mapeamento de deslizamentos. Considerando-se a importância dos componentes do relevo e da cobertura do solo neste processo, torna-se essencial o estabelecimento de metodologias para a síntese de informações do relevo e para a identificação de cicatrizes de deslizamento, de maneira a facilitar o monitoramento de áreas de risco. O objetivo desta Tese é propor metodologias de processamento digital de imagens para o mapeamento e identificação de cicatrizes de deslizamento próximo a rodovias. Um deslizamento de grande porte com várias consequências econômicas, ocorrido no ano de 1999, às margens da Rodovia Anchieta, na bacia hidrográfica do Rio Pilões foi utilizado como área de estudo deste trabalho. Utilizando dados gratuitos, mapas de cobertura do solo e de compartimentação do relevo foram gerados e analisados conjuntamente para a identificação das áreas de potenciais cicatrizes na região das Rodovias Anchieta e Imigrantes. A análise do relevo foi realizada utilizando técnicas de classificação baseada em objeto. A identificação de áreas de cicatrizes de deslizamento foi realizada através da avaliação de duas estratégias metodológicas: uma utilizando o algoritmo de classificação supervisionada SVM (Support Vector Machine) aplicado ao índice de vegetação NDVI (Normalized Difference Vegetation Index) e outra que utilizando combinação entre diferentes classificadores para a composição de uma classificação final. Os resultados obtidos para o mapeamento do relevo mostraram que a metodologia proposta possui grande potencial para a descrição de feições do relevo, com maior nível de detalhamento, facilitando a identificação de áreas com grande potencial de ocorrência de deslizamentos. Ambas as metodologias de identificação de cicatrizes de deslizamento apresentaram bons resultados, sendo que a combinação entre os algoritmos SVM, Redes Neurais e Máxima Verossimilhança apresentou o resultado mais adequado com os objetivos do trabalho, atingindo erro de omissão inferior a 10% para a classe de deslizamento. A combinação dos dois produtos permitiu a análise e identificação de diversas áreas de potenciais cicatrizes de deslizamento associadas à rodovias na região de estudo. A metodologia proposta possui ampla replicabilidade, podendo ser utilizada para análises de risco associadas a assentamentos urbanos, empreendimentos lineares e para o planejamento territorial e ambiental. / Geoinformation tools have great applicability in understanding and mapping landslides. Considering the significance of releif components and land cover in this process, it is essential the establishment of methods for the synthesis of the relief information and identification landslides, aiming to facilitate areas risk monitoring. The objective of this Dissertation is to propose digital image processing methodologies for map and identify landslide near to highways. A large landslide with several economic consequences was used as a study area of this work, occurred in 1999, near the Highway Anchieta, in Piloes river basin. Using free data, land cover and relief subdivsion maps were generated and intersected to identify areas of potential landslides in the region of Highways Anchieta and Imigrantes. The relief analysis was performed using based on object classification techniques. The identification of the landslide was performed by evaluating two methodological strategies: one using the supervised classification algorithm SVM (Support Vector Machine) applied to the NDVI vegetation index (Normalized Difference Vegetation Index) and another using combination of different classifiers for the composition of a final classification. The results obtained for relief mapping showed that the proposed method has great potential for the description of the relief features, with greater detail, facilitating the identification of areas with high potential for occurrence of landslides. Both landslides identification methodologies showed good results, and the combination of SVM, Neural Network and Maximum Likelihood algorithms presented the most appropriate result, reaching omission error of less than 10% for the landslide class. The combination of the two products allowed the analysis and identification of several areas of potential landslide scars associated with roads in the study area. The proposed methodology has extensive replication and can be used for risk analysis associated with urban settlements, linear infrastructures and the territorial and environmental planning.