Uma contribuição à solução do problema dos k-servos usando aprendizagem por reforço

Neste trabalho é proposto um novo algoritmo online para o resolver o Problema dos k-Servos (PKS). O desempenho desta solução é comparado com o de outros algoritmos existentes na literatura, a saber, os algoritmos Harmonic e Work Function, que mostraram ser competitivos, tornando-os parâmetros de comparação significativos. Um algoritmo que apresente desempenho eficiente em relação aos mesmos tende a ser competitivo também, devendo, obviamente, se provar o referido fato. Tal prova, entretanto, foge aos objetivos do presente trabalho. O algoritmo apresentado para a solução do PKS é baseado em técnicas de aprendizagem por reforço. Para tanto, o problema foi modelado como um processo de decisão em múltiplas etapas, ao qual é aplicado o algoritmo Q-Learning, um dos métodos de solução mais populares para o estabelecimento de políticas ótimas neste tipo de problema de decisão. Entretanto, deve-se observar que a dimensão da estrutura de armazenamento utilizada pela aprendizagem por reforço para se obter a política ótima cresce em função do número de estados e de ações, que por sua vez é proporcional ao número n de nós e k de servos. Ao se analisar esse crescimento (matematicamente, ) percebe-se que o mesmo ocorre de maneira exponencial, limitando a aplicação do método a problemas de menor porte, onde o número de nós e de servos é reduzido. Este problema, denominado maldição da dimensionalidade, foi introduzido por Belmann e implica na impossibilidade de execução de um algoritmo para certas instâncias de um problema pelo esgotamento de recursos computacionais para obtenção de sua saída. De modo a evitar que a solução proposta, baseada exclusivamente na aprendizagem por reforço, seja restrita a aplicações de menor porte, propõe-se uma solução alternativa para problemas mais realistas, que envolvam um número maior de nós e de servos. Esta solução alternativa é hierarquizada e utiliza dois métodos de solução do PKS: a aprendizagem por reforço, aplicada a um número reduzido de nós obtidos a partir de um processo de agregação, e um método guloso, aplicado aos subconjuntos de nós resultantes do processo de agregação, onde o critério de escolha do agendamento dos servos é baseado na menor distância ao local de demanda

ISE-SPL: Uma abordagem baseada em linha de produtos de software aplicada à geração automática de sistemas para educação médica na plataforma E-learning

E-learning, which refers to the use of Internet-related technologies to improve knowledge and learning, has emerged as a complementary form of education, bringing advantages such as increased accessibility to information, personalized learning, democratization of education and ease of update, distribution and standardization of the content. In this sense, this paper aims to develop a tool, named ISE-SPL, whose purpose is the automatic generation of E-learning systems for medical education, making use of concepts of Software Product Lines. It consists of an innovative methodology for medical education that aims to assist professors of healthcare in their teaching through the use of educational technologies, all based on computing applied to healthcare (Informatics in Health). The tests performed to validate the ISE-SPL were divided into two stages: the first was made by using a software analysis tool similar to ISE-SPL, called SPLOT and the second was performed through usability questionnaires to healthcare professors who used ISESPL. Both tests showed positive results, proving it to be an efficient tool for generation of E-learning software and useful for professors in healthcare

Classificação de padrões através de um comitê de máquinas aprimorado por aprendizagem por reforço

Reinforcement learning is a machine learning technique that, although finding a large number of applications, maybe is yet to reach its full potential. One of the inadequately tested possibilities is the use of reinforcement learning in combination with other methods for the solution of pattern classification problems. It is well documented in the literature the problems that support vector machine ensembles face in terms of generalization capacity. Algorithms such as Adaboost do not deal appropriately with the imbalances that arise in those situations. Several alternatives have been proposed, with varying degrees of success. This dissertation presents a new approach to building committees of support vector machines. The presented algorithm combines Adaboost algorithm with a layer of reinforcement learning to adjust committee parameters in order to avoid that imbalances on the committee components affect the generalization performance of the final hypothesis. Comparisons were made with ensembles using and not using the reinforcement learning layer, testing benchmark data sets widely known in area of pattern classification

Roteamento em Redes de Sensores Sem Fios Com Base Em Aprendizagem Por Reforço

The use of wireless sensor and actuator networks in industry has been increasing past few years, bringing multiple benefits compared to wired systems, like network flexibility and manageability. Such networks consists of a possibly large number of small and autonomous sensor and actuator devices with wireless communication capabilities. The data collected by sensors are sent directly or through intermediary nodes along the network to a base station called sink node. The data routing in this environment is an essential matter since it is strictly bounded to the energy efficiency, thus the network lifetime. This work investigates the application of a routing technique based on Reinforcement Learning s Q-Learning algorithm to a wireless sensor network by using an NS-2 simulated environment. Several metrics like energy consumption, data packet delivery rates and delays are used to validate de proposal comparing it with another solutions existing in the literature

Estudo Comparativo de Métricas de Pontuação para Aprendizagem Estrutural de Redes Bayesianas

Bayesian networks are powerful tools as they represent probability distributions as graphs. They work with uncertainties of real systems. Since last decade there is a special interest in learning network structures from data. However learning the best network structure is a NP-Hard problem, so many heuristics algorithms to generate network structures from data were created. Many of these algorithms use score metrics to generate the network model. This thesis compare three of most used score metrics. The K-2 algorithm and two pattern benchmarks, ASIA and ALARM, were used to carry out the comparison. Results show that score metrics with hyperparameters that strength the tendency to select simpler network structures are better than score metrics with weaker tendency to select simpler network structures for both metrics (Heckerman-Geiger and modified MDL). Heckerman-Geiger Bayesian score metric works better than MDL with large datasets and MDL works better than Heckerman-Geiger with small datasets. The modified MDL gives similar results to Heckerman-Geiger for large datasets and close results to MDL for small datasets with stronger tendency to select simpler network structures

Abordagem de construção de arquitetura homogênea para comitês via meta-aprendizagem

In the world we are constantly performing everyday actions. Two of these actions are frequent and of great importance: classify (sort by classes) and take decision. When we encounter problems with a relatively high degree of complexity, we tend to seek other opinions, usually from people who have some knowledge or even to the extent possible, are experts in the problem domain in question in order to help us in the decision-making process. Both the classification process as the process of decision making, we are guided by consideration of the characteristics involved in the specific problem. The characterization of a set of objects is part of the decision making process in general. In Machine Learning this classification happens through a learning algorithm and the characterization is applied to databases. The classification algorithms can be employed individually or by machine committees. The choice of the best methods to be used in the construction of a committee is a very arduous task. In this work, it will be investigated meta-learning techniques in selecting the best configuration parameters of homogeneous committees for applications in various classification problems. These parameters are: the base classifier, the architecture and the size of this architecture. We investigated nine types of inductors candidates for based classifier, two methods of generation of architecture and nine medium-sized groups for architecture. Dimensionality reduction techniques have been applied to metabases looking for improvement. Five classifiers methods are investigated as meta-learners in the process of choosing the best parameters of a homogeneous committee.

Um framework conceitual para apoiar a instrumentação da avaliação formativa da aprendizagem em jogos digitais

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior

Aprendizagem da língua japonesa apoiada por ferramentas computacionais: estudo e desenvolvimento do jogo Karuchā Ships Invaders

The use of technology tools for teaching and learning has grown increasingly in our daily life. In this context, a branch that has had tremendous growth is the area of teaching and learning language through computational tools. The study of CALL (Computer Assisted Language Learning), accomplished in this research, aims to evaluate existing tools in this context, focused specifically on the Japanese language; and from this study, accomplish the development of a new computational tool that can assist teaching/learning of the Japanese language. As results, we present a wide survey on the subject in various technologies/devices, as well as the complete development process of a new tool, the Karuchā Ships Invaders game, that proposes to teach basic concepts of the language, blended with entertainment, and still, focusing on the Brazilian students of Japanese language audience. We will present all the concept phases of the game and its evolution through the research, as well as an interface evaluation. Still, we present proposal and validation of a method to evaluate motivational aspects of computational tools with educational focus, and results extracted from an experiment accomplished with prospective users

Descobrindo novas ofertas: recursos histórico-culturais e oportunidades de inovação em turismo para a região do Marco/RN

Having as reference the fundamentals of regional innovation systems (RIS) and the policy guidelines defined in the regionalization program implemented by the federal government, this study focus on the analysis of the so-called "Landmark Region", northern coast of Polo Costa das Dunas-RN, in order to indicate how the historical and cultural resources can support innovation in the tourism of the region, represented here by the cities of Pedra Grande and São Miguel do Gostoso. This is a descriptive research, using qualitative methods of data collection and analysis, configuring, still, as a case study. Data were gathered from literature, documents, semi-structured interviews and mainly by participant observation methods. The results show a great diversity of cultural resources in the region, both material and immaterial, which however are disarticulated, and need to be worked in order to be included in the tourism productive chain. The main opportunity for innovation regards the return of the Landmark to the region, an invaluable monument, with the construction of a memorial. Taking in account the relevance of the monument and the growth of the region, we conclude that the return of the Landmark to its place of origin, in conjunction with other cultural resources, could attract a flow of cultural tourists. This fact could be, as the theory suggests, characterized as market or niche innovation, as the region is dominated by the sun and sea and wind sports tourism

Educação em engenharia: estudo de metodologias pedagógicas e desenvolvimento de um software aplicado ao ensino de estabilidade de sistemas de energia elétrica

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Desenvolvimento de uma ferramenta computacional de apoio ao ensino de sistemas eletrônicos digitais

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Uma proposta de inovação no cardápio escolar baseada na avaliação do programa de alimentação escolar de Piracicaba-SP

Pós-graduação em Alimentos e Nutrição - FCFAR

Televisão digital e Educação a distância: modelo de ambiente virtual de aprendizagem para mídia audiovisual

Pós-graduação em Televisão Digital: Informação e Conhecimento - FAAC

Usabilidade de software: estudo de recomendações básicas para verificação do nível de conhecimento dos alunos dos cursos de Design Gráfico e Sistemas de Informação da UNESP/Bauru

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Reflexões críticas sobre os sistemas apostilados de ensino

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)