Mestrado em Ciência da Computação (INF)
URI Permanente para esta coleção
Navegar
Navegando Mestrado em Ciência da Computação (INF) por Por Orientador "CARVALHO, Cedric Luiz de"
Agora exibindo 1 - 6 de 6
Resultados por página
Opções de Ordenação
Item Airetama Um Arcabouço Baseado em Sistemas Multiagentes para a Implantação de Comunidades Virtuais de Prática na Web(Universidade Federal de Goiás, 2010-10-04) ALARCÓN, Jair Abú Bechir Láscar; CARVALHO, Cedric Luiz de; http://lattes.cnpq.br/4090131106212286The objective of this dissertation is to present the framework Airetama. This framework is based on Multiagent Systems and Semantic Web principles. It provides a semantic, distributed and open-source infrastructure for the creation of Virtual Communities of Practice on the Web. It makes possible, through the use of agents, coupling of resources and tools that use semantic technologies. Integration of semantic in the current Web has as main objective to allow such software agents can use their pages more intelligently, thus offering better service.Item Uma Metodologia para a Construção Semiautomatizada de Ontologias a partir de Documentos Textuais(Universidade Federal de Goiás, 2009-09-01) MATOS, Hellen Carmo de Oliveira; COSTA, Fábio Moreira; http://lattes.cnpq.br/0925150626762308; CARVALHO, Cedric Luiz de; http://lattes.cnpq.br/4090131106212286Information organization became a fundamental process in face of the exponential increasing of available information, motivated by technology advances, Internet in particular. It demands effective approaches of information filtering and searching, like the information retrieval systems. Such systems depend on the document s semantic representation, which can be implemented through conceptual and semantic relationship representation instruments, as ontologies. The ontology construction is a complex and time-consuming process. It s difficult to know whether a given ontology is wide enough to represent the documents semantic information. Up to date ontologies are developed according to Ontology Engineering standards and methods, although there is no any universal solution. This work presents a methodology for semi-automatic construction of ontologies. It also demonstrates an ontology construction for grid computing domain, aiming to validate the proposal. Such domain is strongly associated to resources sharing to solve problems on dynamic and heterogeneous environment. The allocation of these resources is an essential task in the grid and depends on the quality of available information. The constructed ontology aims to provide a description of the resources available in a computational grid to help on the qualification of information contained in this environment. This will allow the semantic discovery of grid resources to run applications on an efficient wayItem Recuperação Contextualizada de Documentos Integrados pelo Protocolo OAI-PMH(Universidade Federal de Goiás, 2010-04-09) OLIVEIRA, Renan Rodrigues de; CARVALHO, Cedric Luiz de; http://lattes.cnpq.br/4090131106212286This work focuses on two aspects: the integration of a set of digital libraries, repositories and other data providers through the OAI-PMH protocol (Open Archives Initiative Protocol for Metadata Harvesting) and contextualized documents retrieval in this integrated repository. It is proposed the use of ontologies and content analysis of articles in wiki environments in the context definition. The interest in ontologies is in its use as artifacts of specification domain. An ontology is a data model that represents a set of concepts and their relationships within a domain of knowledge. A wiki is a collaborative environment, containing a collection of items connected by hyperlinks, which can be edited collectively by using a web browser. In this work, the wiki environments are used as an auxiliary repository of knowledge to the extraction of relevant terms. Thus, several concepts and relationships that may not be present in the ontology that specifies the domain of knowledge (since the construction of ontologies is a complex process) can be identified. The result of the developed tool processing is a ranking of documents ordered by a higher degree of importance with respect to the query provided by a user and a particular domain of knowledge, which is specified by an ontology.Item Variações do método kNN e suas aplicações na classificação automática de textos(Universidade Federal de Goiás, 2010-10-10) SANTOS, Fernando Chagas; ROSA, Thierson Couto; http://lattes.cnpq.br/4414718560764818; CARVALHO, Cedric Luiz de; http://lattes.cnpq.br/4090131106212286Most research on Automatic Text Categorization (ATC) seeks to improve the classifier performance (effective or efficient) responsible for automatically classifying a document d not yet rated. The k nearest neighbors (kNN) is simpler and it s one of automatic classification methods more effective as proposed. In this paper we proposed two kNN variations, Inverse kNN (kINN) and Symmetric kNN (kSNN) with the aim of improving the effectiveness of ACT. The kNN, kINN and kSNN methods were applied in Reuters, 20ng and Ohsumed collections and the results showed that kINN and kSNN methods were more effective than kNN method in Reuters and Ohsumed collections. kINN and kSNN methods were as effective as kNN method in 20NG collection. In addition, the performance achieved by kNN method is more stable than kINN and kSNN methods when the value k change. A parallel study was conducted to generate new features in documents from the similarity matrices resulting from the selection criteria for the best results obtained in kNN, kINN and kSNN methods. The SVM (considered a state of the art method) was applied in Reuters, 20NG and Ohsumed collections - before and after applying this approach to generate features in these documents and the results showed statistically significant gains for the original collection.Item Um estudo de técnicas da Inteligência Artificial aplicadas na distribuição de recursos em áreas geográficas(Universidade Federal de Goiás, 2011-04-28) TELES, Ronneesley Moura; CARVALHO, Cedric Luiz de; http://lattes.cnpq.br/4090131106212286This paper studies a problem that is the distribution of resources in geographical areas. Many organizations, from taxis, to the military faces this problem in their daily operations. In essence, it tries to answer the question: What are the best places in which I place my assets in the geographic area X, according to a set of constraints Y? . To answer the question, we studied representation models of the problem, known techniques have been applied in Artificial Intelligence and Operations Research, such as: testing all combinations, greedy algorithms, heuristics and genetic algorithms. Algorithms were created and simulations were performed. Furthermore, Multiagent System was developed that implements one of algorithms developed. In evaluating the proposals made in this dissertation, it was considered the field of Electric Companies in the task of distributing vehicles in a city.Item ServiçosWeb Semânticos Baseados em RESTful Um Estudo de Caso em Redes Sociais Online(Universidade Federal de Goiás, 2011-09-26) XAVIER, Otávio Calaça; CARVALHO, Cedric Luiz de; http://lattes.cnpq.br/4090131106212286The researches on Semantic Web Services are aimed, mostly, the SOAP architecture. This architecture is rarely used in Web 2.0 and therefore in Online Social Networks. This dissertation presents an approach for practical implementation of semantic descriptions in RESTfulWeb Services. It is a simplified architecture that gained much focus onWeb 2.0, increasingly replacing the SOAP architecture. The development of the tool, presented here, will fill a gap in the process of implanting the Semantic Web. Existing solutions expose a theoretical view and have no practical implementations. The solution proposed in this paper, relates existing standards and technologies to develop an integrated and free tool. From which, services of a popular Online Social Network are described. Finally, the automatic discovery, composition and invocation of such services are made.