Els sistemes de conversió de text en parla (CTP-SU) s'encarreguen de produir veu sintètica a partir d'un text d'entrada. Els CTP basats en selecció d'unitats (CTP-SU) recuperen la millor seqüència d'unitats de veu enregistrades prèviament en una base de dades (corpus). La recuperació es realitza mitjançant algorismes de programació dinàmica i una funció de cost ponderada. La ponderació de la funció de cost es realitza típicament de forma manual per part d'un expert. No obstant, l'ajust manual resulta costós des d'un punt de vista de coneixement prèvi, i imprecís en la seva execució. Per tal d'ajustar els pesos de la funció de cost, aquesta tesi parteix de la prova de viabilitat d'ajust perceptiu presentada per Alías (2006) que empra algorismes genètics interactius actius (active interactive Genetic Algorithm - aiGA). Aquesta tesi doctoral investiga les diferents problemàtiques que es presenten en aplicar els aiGAs en l'ajust de pesos d'un CTP-SU en un context real de selecció d'unitats. Primerament la tesi realitza un estudi de l'estat de l'art en l'ajust de pesos. Tot seguit, repassa la idoneïtat de la computació evolutiva interactiva per realitzar l'ajust revisant amb profunditat el treball previ. Llavors es presenten i es validen les propostes de millora. Les quatre línies mestres que guien les contribucions d'aquesta tesi són: la precisió en l'ajust dels pesos, la robustesa dels pesos obtinguts, l'aplicabilitat de la metodologia per qualsevol funció de cost i el consens dels pesos obtinguts incorporant el criteri de diferents usuaris. En termes de precisió la tesi proposa realitzar l'ajust perceptiu per diferents tipus (clústers) d'unitats respectant les seves peculiaritats fonètiques i contextuals. En termes de robustesa la tesi incorpora diferents mètriques evolutives (indicadors) que avaluen aspectes com l'ambigüitat en la cerca, la convergència d'un usuari o el nivell de consens entre diferents usuaris. Posteriorment, per estudiar l'aplicabilitat de la metodologia proposada s'ajusten perceptivament diferents pesos que combinen informació lingüística i simbòlica. La última contribució d'aquesta tesi estudia l'idoneïtat dels models latents per modelar les preferències dels diferents usuaris i obtenir una solució de consens. Paral•lelament, per fer el pas d'una prova de viabilitat a un entorn real de selecció d'unitats es treballa amb un corpus d'extensió mitjana (1.9h) etiquetat automàticament. La tesi permet concloure que l'aiGA a nivell de clúster és una metodologia altament competitiva respecte les altres tècniques d'ajust presents en l'estat de l'art. / Los sistemas de conversión texto-habla (CTH-SU) se encargan de producir voz sintética a partir de un texto de entrada. Los CTH basados en selección de unidades (CTH-SU) recuperan la mejor secuencia de unidades de voz grabadas previamente en una base de datos (corpus). La recuperación se realitza mediante algoritmos de programación dinámica y una función de coste ponderada. La ponderación de la función de coste se realiza típicamente de forma manual por parte de un experto. Sin embargo, el ajuste manual resulta costoso desde un punto de vista de conocimiento previo e impreciso en su ejecución. Para ajustar los pesos de la función de coste, esta tesis parte de la prueba de viabilidad de ajuste perceptivo presentada por Alías (2006) que emplea algoritmos genéticos interactivos activos (active interactive Genetic Algorithm - aiGA). Esta tesis doctoral investiga las diferentes problemáticas que se presentan al aplicar los aiGAs en el ajuste de pesos de un CTH-SU en un contexto real de selección de unidades. Primeramente la tesis realiza un estudio del estado del arte en el ajuste de pesos, posteriormente repasa la idoneidad de la computación evolutiva interactiva para realizar el ajuste revisando en profundidad el trabajo previo. Entonces se presentan y se validan las propuestas de mejora. Las cuatro líneas maestras que guían las contribuciones de esta tesis son: la precisión en el ajuste de los pesos, la robustez de los pesos obtenidos, la aplicabilidad de la metodología para cualquier función de coste y el consenso de los pesos obtenidos incorporando el criterio de diferentes usuarios. En términos de precisión la tesis propone realizar el ajuste perceptivo por diferentes tipos (clusters) de unidades respetando sus peculiaridades fonéticas y contextuales. En términos de robustez la tesis incorpora diferentes métricas evolutivas (indicadores) que evalúan aspectos como la ambigüedad en la búsqueda, la convergencia de un usuario o el nivel de consenso entre diferentes usuarios. Posteriormente, para estudiar la aplicabilidad de la metodología propuesta se ajustan perceptivamente diferentes pesos que combinan información lingüística y simbólica. La última contribución de esta tesis estudia la idoneidad de los modelos latentes para modelar las preferencias de los diferentes usuarios y obtener una solución de consenso. Paralelamente, para dar el paso de una prueba de viabilidad a un entorno real de selección de unidades se trabaja con un corpus de extensión media (1.9h) etiquetado automáticamente. La tesis permite concluir que el aiGA a nivel de cluster es una metodología altamente competitiva respecto a las otras técnicas de ajuste presentes en el estado del arte. / Text-to-Speech Systems (TTS) produce synthetic speech from an input text. Unit Selection TTS (US-TTS) systems are based on the retrieval of the best sequence of recorded speech units previously recorded into a database (corpus). The retrieval is done by means of dynamic programming algorithm and a weighted cost function. An expert typically performs the weighting of the cost function by hand. However, hand tuning is costly from a standpoint of previous training and inaccurate in terms of methodology. In order to properly tune the weights of the cost function, this thesis continues the perceptual tuning proposal submitted by Alías(2006) which uses active interactive Genetic Algorithms (aiGAs). This thesis conducts an investigation to the various problems that arise in applying aiGAs to the weight tuning of the cost function. Firstly, the thesis makes a deep revision to the state-of-the-art in weight tuning. Afterwards, the thesis outlines the suitability of Interactive Evolutionary Computation (IEC) to perform the weight tuning making a thorough review of previous work. Then, the proposals of improvement are presented. The four major guidelines pursued by this thesis are: accuracy in adjusting the weights, robustness of the weights obtained, the applicability of the methodology to any subcost distance and the consensus of weights obtained by different users. In terms of precision cluster-level perceptual tuning is proposed in order to obtain weights for different types (clusters) of units considering their phonetic and contextual properties. In terms of robustness of the evolutionary process, the thesis presents different metrics (indicators) to assess aspects such as the ambiguity within the evolutionary search, the convergence of one user or the level of consensus among different users. Subsequently, to study the applicability of the proposed methodology different weights are perceptually tuned combining linguistic and symbolic information. The last contribution of this thesis examines the suitability of latent models for modeling the preferences of different users and obtains a consensus solution. In addition, the experimentation is carried out through a medium size corpus (1.9h) automatically labelled in order fill the gap between the proof-of-principle and a real unit selection scenario. The thesis concludes that aiGAs are highly competitive in comparison to other weight tuning techniques from the state-of-the-art.

The primary goal of artificial intelligence research is to develop a machine capable of learning to solve disparate real-world tasks autonomously, without relying on specialized problem-specific inputs. This dissertation suggests that such machines are realistic: If No Free Lunch theorems were to apply to all real-world problems, then the world would be utterly unpredictable. In response, the dissertation proposes the information-maximization principle, which claims that the optimal optimization methods make the best use of the information available to them. This principle results in a new algorithm, evolutionary annealing, which is shown to perform well especially in challenging problems with irregular structure. / text

Made available in DSpace on 2014-12-17T15:46:59Z (GMT). No. of bitstreams: 1 PauloHAS_TESE.pdf: 9268945 bytes, checksum: 08c0c5f93ed7b964b99c6df2ee26ab1b (MD5) Previous issue date: 2011-12-19 / Coordena??o de Aperfei?oamento de Pessoal de N?vel Superior / The Car Rental Salesman Problem (CaRS) is a variant of the classical Traveling Salesman Problem which was not described in the literature where a tour of visits can be decomposed into contiguous paths that may be performed in different rental cars. The aim is to determine the Hamiltonian cycle that results in a final minimum cost, considering the cost of the route added to the cost of an expected penalty paid for each exchange of vehicles on the route. This penalty is due to the return of the car dropped to the base. This paper introduces the general problem and illustrates some examples, also featuring some of its associated variants. An overview of the complexity of this combinatorial problem is also outlined, to justify their classification in the NPhard class. A database of instances for the problem is presented, describing the methodology of its constitution. The presented problem is also the subject of a study based on experimental algorithmic implementation of six metaheuristic solutions, representing adaptations of the best of state-of-the-art heuristic programming. New neighborhoods, construction procedures, search operators, evolutionary agents, cooperation by multi-pheromone are created for this problem. Furtermore, computational experiments and comparative performance tests are conducted on a sample of 60 instances of the created database, aiming to offer a algorithm with an efficient solution for this problem. These results will illustrate the best performance reached by the transgenetic algorithm in all instances of the dataset / O Problema do Caixeiro Alugador (CaRS) ? uma variante ainda n?o descrita na literatura do cl?ssico Problema do Caixeiro Viajante onde o tradicional tour de visitas do caixeiro pode ser decomposto em caminhos cont?guos e que podem ser realizados em diferentes carros alugados. O problema consiste em determinar o ciclo hamiltoniano que resulte em um custo final m?nimo, considerando o custo da rota adicionado ao custo de uma prov?vel penaliza??o paga em cada troca de ve?culos na rota, penaliza??o devida ao retorno do carro descartado at? a sua cidade base. Sem perda para a generalidade do caso, os custos do aluguel do carro podem ser considerados embutidos nos custos da rota do carro. O presente trabalho introduz o problema geral e o exemplifica, caracterizando igualmente algumas variantes associadas. Uma an?lise geral da complexidade desse problema combinat?rio ? descrita, visando justificar sua classifica??o na classe NP-dif?cil. Um banco de inst?ncias para o problema ? apresentado, descrevendo-se a metodologia de sua constitui??o. O problema proposto tamb?m ? objeto de um estudo algor?tmico experimental baseado na aplica??o de seis metaheur?sticas de solu??o, representando adapta??es do melhor do estado da arte em programa??o heur?stica. Novas vizinhan?as, procedimentos construtivos, operadores de busca, agentes evolucion?rios, coopera??o por multiferom?nios, s?o criados para o caso. Experimentos computacionais comparativos e testes de desempenho s?o realizados sobre uma amostra de 60 inst?ncias, visando oferecer um algoritmo de solu??o competitivo para o problema. Conclui-se pela vantagem do algoritmo transgen?tico em todos os conjuntos de inst?ncias

Made available in DSpace on 2014-12-17T15:47:52Z (GMT). No. of bitstreams: 1 ThatianaCNS_DISSERT.pdf: 1637234 bytes, checksum: 8b38ce4a7a358efe654d9bb1c23c15bc (MD5) Previous issue date: 2010-03-02 / The distribution of petroleum products through pipeline networks is an important problem that arises in production planning of refineries. It consists in determining what will be done in each production stage given a time horizon, concerning the distribution of products from source nodes to demand nodes, passing through intermediate nodes. Constraints concerning storage limits, delivering time, sources availability, limits on sending or receiving, among others, have to be satisfied. This problem can be viewed as a biobjective problem that aims at minimizing the time needed to for transporting the set of packages through the network and the successive transmission of different products in the same pipe is called fragmentation. This work are developed three algorithms that are applied to this problem: the first algorithm is discrete and is based on Particle Swarm Optimization (PSO), with local search procedures and path-relinking proposed as velocity operators, the second and the third algorithms deal of two versions based on the Non-dominated Sorting Genetic Algorithm II (NSGA-II). The proposed algorithms are compared to other approaches for the same problem, in terms of the solution quality and computational time spent, so that the efficiency of the developed methods can be evaluated / A distribui??o de produtos de petr?leo atrav?s de redes de polidutos ? um importante problema que se coloca no planejamento de produ??o das refinarias. Consiste em determinar o que ser? feito em cada est?gio de produ??o dado um determinado horizonte de tempo, no que respeita ? distribui??o de produtos de n?s fonte ? procura de n?s, passando por n?s intermedi?rios. Restri??es relativas a limites de armazenamento, tempo de entrega, disponibilidade de fontes, limites de envio ou recebimento, entre outros, t?m de ser satisfeitas. Este problema pode ser visto como um problema biobjetivo, que visa minimizar o tempo necess?rio para transportar o conjunto de pacotes atrav?s da rede e o envio sucessivo de produtos diferentes no mesmo duto que ? chamado de fragmenta??o. Neste trabalho, s?o desenvolvidos tr?s algoritmos que s?o aplicados a esse problema: o primeiro algoritmo ? discreto e baseia-se na Otimiza??o por Nuvem de Part?culas (PSO), com procedimentos de busca local e path-relinking propostos como operadores de velocidade, o segundo e o terceiro algoritmos tratam de duas vers?es baseadas no Non-dominated Sorting Genetic Algorithm II (NSGA-II). Os algoritmos propostos s?o comparados a outras abordagens para o mesmo problema, em termos de qualidade de solu??o e tempo computacional despendido, a fim de se avaliar a efici?ncia dos m?todos desenvolvidos

Made available in DSpace on 2015-03-03T15:48:41Z (GMT). No. of bitstreams: 1 MatheusSM_TESE.pdf: 3657538 bytes, checksum: 05bf71663b044728a1e70b6db57b834e (MD5) Previous issue date: 2014-03-21 / This paper introduces a new variant of the Traveling Car Renter Problem, named Prizecollecting Traveling Car Renter Problem. In this problem, a set of vertices, each associated with a bonus, and a set of vehicles are given. The objective is to determine a cycle that visits some vertices collecting, at least, a pre-defined bonus, and minimizing the cost of the tour that can be traveled with different vehicles. A mathematical formulation is presented and implemented in a solver to produce results for sixty-two instances. The proposed problem is also subject of an experimental study based on the algorithmic application of four metaheuristics representing the best adaptations of the state of the art of the heuristic programming.We also provide new local search operators which exploit the neighborhoods of the problem, construction procedures and adjustments, created specifically for the addressed problem. Comparative computational experiments and performance tests are performed on a sample of 80 instances, aiming to offer a competitive algorithm to the problem. We conclude that memetic algorithms, computational transgenetic and a hybrid evolutive algorithm are competitive in tests performed / Este trabalho apresenta uma nova variante do problema do Caixeiro Alugador ainda n?o descrita na literatura, denominada de Caixeiro Alugador com Coleta de Pr?mios. Neste problema s?o disponibilizados um conjunto de v?rtices, cada um com um b?nus associado e um conjunto de ve?culos. O objetivo do problema ? determinar um ciclo que visite alguns v?rtices coletando, pelo menos, um b?nus pr?-de nido e minimizando os custos de viagem atrav?s da rota, que pode ser feita com ve?culos de diferentes tipos. ? apresentada uma formula??o matem?tica e implementada em um solver produzindo resultados em sessenta e duas inst?ncias. O problema proposto tamb?m ? objeto de um estudo algor?tmico experimental baseado na aplica??o de quatro metaheur?sticas de solu??o, representando adapta??es do melhor do estado da arte em programa??o heur?stica. Nesse trabalho tamb?m apresentamos a constitui??o de novos operadores que exploram as vizinhan?as do problema, procedimentos construtivos e adapta??es, criados especifi camente para o problema abordado. Experimentos computacionais comparativos e testes de desempenho s?o realizados sobre uma amostra de 80 inst?ncias, visando oferecer um algoritmo de solu??o competitivo para o problema. Conclui-se que algoritmos com abordagem mem?tica, transgen ?tica e evolucion?ria h?brida obtiveram resultados competitivos nos testes efetuados. Palavras-chave: Caixeiro Alugador com Coleta de Pr?mios. Metaheur?sticas. GRASP/VNS. Algoritmo Mem?tico. Transgen?tica Computacional. Computa??o Evolucion?ria

Made available in DSpace on 2016-08-17T14:53:21Z (GMT). No. of bitstreams: 1 Sergio Augusto.pdf: 2350058 bytes, checksum: 7c3c67925b0b27a77105c3cb0799c4e6 (MD5) Previous issue date: 2012-05-04 / Conselho Nacional de Desenvolvimento Científico e Tecnológico / This work provides a framework to obtain the optimal bidding strategy for a GENCO in long-term electricity auction. The tool is based on intelligent techniques for optimizing the proposed Utility Function. The goal is to find the optimal strategy that maximizes the expected payoff of GENCO and simultaneously minimize the risks. The risks are modeled by two classical metrics: the Variance (Portfolio Theory) and Value at Risk (VaR). The proposed methodology is applied to auctions for long-term forward contracts, such that used in the Brazilian power system for buying and selling energy in the regulated market. The Bidding Strategy is formed through a Supply Curve which relates the optimal amount of energy to different offer prices. Thus, it allows the GENCO define the best bid (offer) for a given offer price. The proposed approach is validated for three test cases: First, concerning the variation of generation and price of energy scenarios for evaluation of the bidding strategy and the GENCOS risk perception; The second, consider a cascade hydro-term system for evaluation of MRE; and The third, considers the northeastern Brazilian subsystem where the supply curve is formed for the CHESF company's power plants portfolio. The results show how the offer may be changed according the variation of the spot prices and physical generation and demonstrate the efficacy of meta-heuristics proposed to optimize the supply model. / Este trabalho apresenta uma ferramenta de auxílio e suporte à tomada de decisões na formação de estratégias de oferta para agentes geradores (GENCOS) participantes de leilões de eletricidade de longo-prazo. A ferramenta é baseada em técnicas inteligentes para a otimização da Função de Utilidade proposta média-risco . O objetivo é encontrar a Estratégia Ótima que maximize o retorno esperado da GENCO e, simultaneamente, minimize os riscos relacionados às incertezas no montante de energia produzida e no preço spot, modelados por duas métricas clássicas de risco: a Variância (teoria dos portfólios) e o Valor em Risco (VaR). A abordagem proposta é aplicada ao mercado brasileiro de eletricidade, especificamente, ao ambiente de Leilões de Energia Existente na categoria Quantidade de Energia, tais quais os leilões aplicados pelo órgão regulador brasileiro para compra e venda de energia no mercado regulado. Sugere-se aqui a formação de uma Curva de Oferta que relacione a quantidade de energia ótima para diferentes preços de oferta. E, deste modo, permita a GENCO definir qual o melhor lance (oferta) para dado preço de oferta durante o processo do leilão. Para a avaliação da abordagem foram utilizados três casos testes: O primeiro considera cenários de geração física e preço de energia a fim de avaliar a estratégia de oferta e a percepção ao risco de contratação da GENCO quanto à variação de tais cenários; o segundo, considera um sistema em cascata onde é possível observar o efeito do Mecanismo de Realocação de Energia (MRE) sobre a oferta das GENCOS; e o terceiro considera o subsistema nordeste brasileiro onde a curva de oferta é formada para o portfólio de usinas pertencentes à empresa CHESF. Os resultados demonstram como a oferta de energia pode ser alterada de acordo com cenários de oferta gerados e comprovam a eficiência da meta-heurística proposta para otimização do modelo de oferta.

Indiana University-Purdue University Indianapolis (IUPUI) / Evolutionary testing (ET) techniques (e.g., mutation, crossover, and natural selection) have been applied successfully to many areas of software engineering, such as error/fault identification, data mining, and software cost estimation. Previous research has also applied ET techniques to performance testing. Its application to performance testing, however, only goes as far as finding the best and worst case, execution times. Although such performance testing is beneficial, it provides little insight into performance characteristics of complex functions with multiple branches. This thesis therefore provides two contributions towards performance testing of software systems. First, this thesis demonstrates how ET and genetic algorithms (GAs), which are search heuristic mechanisms for solving optimization problems using mutation, crossover, and natural selection, can be combined with a constraint solver to target specific paths in the software. Secondly, this thesis demonstrates how such an approach can identify local minima and maxima execution times, which can provide a more detailed characterization of software performance. The results from applying our approach to example software applications show that it is able to characterize different execution paths in relatively short amounts of time. This thesis also examines a modified exhaustive approach which can be plugged in when the constraint solver cannot properly provide the information needed to target specific paths.

Indiana University-Purdue University Indianapolis (IUPUI) / Heating, ventilation, and air conditioning (HVAC) is the technology responsible to maintain temperature levels and air quality in buildings to certain standards. In a commercial setting, HVAC systems accounted for more than 50% of the total energy cost of the building in 2013 [13]. New control methods are always being worked on to improve the effectiveness and efficiency of the system. These control systems include model predictive control (MPC), evolutionary algorithm (EA), evolutionary programming (EP), and proportional-integral-derivative (PID) controllers. Such control tools are used on new HVAC system to ensure the ultimate efficiency and ensure the comfort of occupants. However, there is a need for a system that can monitor the energy performance of the HVAC system and ensure that it is operating in its optimal operation and controlled as expected. In this thesis, an air handling unit (AHU) of an HVAC system was modeled to analyze its performance using real data collected from an operating AHU using a wireless monitoring system. The purpose was to monitor the AHU's performance, analyze its key parameters to identify flaws, and evaluate the energy waste. This system will provide the maintenance personnel to key information to them to act for increasing energy efficiency. The mechanical model was experimentally validated first. Them a baseline operating condition was established. Finally, the system under extreme weather conditions was evaluated. The AHU's subsystem performance, the energy consumption and the potential wastes were monitored and quantified. The developed system was able to constantly monitor the system and report to the maintenance personnel the information they need. I can be used to identify energy savings opportunities due to controls malfunction. Implementation of this system will provide the system's key performance indicators, offer feedback for adjustment of control strategies, and identify the potential savings. To further verify the capabilities of the model, a case study was performed on an air handling unit on campus for a three month monitoring period. According to the mechanical model, a total of 63,455 kWh can be potentially saved on the unit by adjusting controls. In addition the mechanical model was able to identify other energy savings opportunities due to set point changes that may result in a total of 77,141 kWh.

Fundação de Amparo a Pesquisa do Estado de Minas Gerais / Agentes que operam em ambientes onde as tomadas de decisão precisam levar em conta, além do ambiente, a atuação minimizadora de um oponente (tal como nos jogos), é fundamental que o agente seja dotado da habilidade de, progressivamente, traçar um perĄl de seu adversário que o auxilie em seu processo de seleção de ações apropriadas. Entretanto, seria improdutivo construir um agente com um sistema de tomada de decisão baseado apenas na elaboração desse perĄl, pois isso impediria o agente de ter uma Şidentidade própriaŤ, o que o deixaria a mercê de seu adversário. Nesta direção, este trabalho propõe um sistema automático jogador de Damas híbrido, chamado ACE-RL-Checkers, dotado de um mecanismo dinâmico de tomada de decisões que se adapta ao perĄl de seu oponente no decorrer de um jogo. Em tal sistema, o processo de seleção de ações (movimentos) é conduzido por uma composição de Rede Neural de Perceptron Multicamadas e biblioteca de casos. No caso, a Rede Neural representa a ŞidentidadeŤ do agente, ou seja, é um módulo tomador de decisões estático já treinado e que faz uso da técnica de Aprendizagem por Reforço TD( ). Por outro lado, a biblioteca de casos representa o módulo tomador de decisões dinâmico do agente que é gerada pela técnica de Elicitação Automática de Casos (um tipo particular de Raciocínio Baseado em Casos). Essa técnica possui um comportamento exploratório pseudo-aleatório que faz com que a tomada de decisão dinâmica do agente seja guiada, ora pelo perĄl de jogo do adversário, ora aleatoriamente. Contudo, ao conceber tal arquitetura, é necessário evitar o seguinte problema: devido às características inerentes à técnica de Elicitação Automática de Casos, nas fases iniciais do jogo Ű em que a quantidade de casos disponíveis na biblioteca é extremamente baixa em função do exíguo conhecimento do perĄl do adversário Ű a frequência de tomadas de decisão aleatórias seria muito elevada, o que comprometeria o desempenho do agente. Para atacar tal problema, este trabalho também propõe incorporar à arquitetura do ACE-RLCheckers um terceiro módulo, composto por uma base de regras de experiência extraída a partir de jogos de especialistas humanos, utilizando uma técnica de Mineração de Padrões Sequenciais. O objetivo de utilizar tal base é reĄnar e acelerar a adaptação do agente ao perĄl de seu adversário nas fases iniciais dos confrontos entre eles. Resultados experimentais conduzidos em torneio envolvendo ACE-RL-Checkers e outros agentes correlacionados com este trabalho, conĄrmam a superioridade da arquitetura dinâmica aqui proposta. / ake into account, in addition to the environment, the minimizing action of an opponent (such as in games), it is fundamental that the agent has the ability to progressively trace a proĄle of its adversary that aids it in the process of selecting appropriate actions. However, it would be unsuitable to construct an agent with a decision-making system based on only the elaboration of this proĄle, as this would prevent the agent from having its Şown identityŤ, which would leave it at the mercy of its opponent. Following this direction, this work proposes an automatic hybrid Checkers player, called ACE-RL-Checkers, equipped with a dynamic decision-making mechanism, which adapts to the proĄle of its opponent over the course of the game. In such a system, the action selection process (moves) is conducted through a composition of Multi-Layer Perceptron Neural Network and case library. In the case, Neural Network represents the ŞidentityŤ of the agent, i.e., it is an already trained static decision-making module and makes use of the Reinforcement Learning TD( ) techniques. On the other hand, the case library represents the dynamic decision-making module of the agent, which is generated by the Automatic Case Elicitation technique (a particular type of Case-Based Reasoning). This technique has a pseudo-random exploratory behavior, which makes the dynamic decision-making on the part of the agent to be directed, either by the game proĄle of the opponent or randomly. However, when devising such an architecture, it is necessary to avoid the following problem: due to the inherent characteristics of the Automatic Case Elicitation technique, in the game initial phases, in which the quantity of available cases in the library is extremely low due to low knowledge content concerning the proĄle of the adversary, the decisionmaking frequency for random decisions is extremely high, which would be detrimental to the performance of the agent. In order to attack this problem, this work also proposes to incorporate onto the ACE-RL-Checkers architecture a third module composed of a base of experience rules, extracted from games played by human experts, using a Sequential Pattern Mining technique. The objective behind using such a base is to reĄne and accelerate the adaptation of the agent to the proĄle of its opponent in the initial phases of their confrontations. Experimental results conducted in tournaments involving ACE-RL-Checkers and other agents correlated with this work, conĄrm the superiority of the dynamic architecture proposed herein. / Tese (Doutorado)

<p><strong>Graph Neural Networks</strong> (GNNs) have become excessively popular and prominent deep learning techniques to analyze structural graph data for their ability to solve complex real-world problems. Because graphs provide an efficient approach to contriving abstract hypothetical concepts, modern research overcomes the limitations of classical graph theory, requiring prior knowledge of the graph structure before employing traditional algorithms. GNNs, an impressive framework for representation learning of graphs, have already produced many state-of-the-art techniques to solve node classification, link prediction, and graph classification tasks. GNNs can learn meaningful representations of graphs incorporating topological structure, node attributes, and neighborhood aggregation to solve supervised, semi-supervised, and unsupervised graph-based problems. In this study, the usefulness of GNNs has been analyzed primarily from two aspects - <strong>clustering and classification</strong>. We focus on these two techniques, as they are the most popular strategies in data mining to discern collected data and employ predictive analysis.</p>