Jairo Francisco de Souza

Adding meaning negotiation skills in multiagent systems

In order to perform its tasks on the semantic web, software agents must be able to communicate with other agents using domain ontologies, even when considering different ontologies. Thus, its necessary to address the semantic interoperability issue to enable agents to recognize common concepts and misunderstandings. This work proposes the use of negotiation concepts in business scenarios for addressing concept compatibilization problems in communication between software agents. Negotiation techniques are suitable in this context by providing a formal communication protocol useful for reaching conceptualization consensus. An architecture is proposed, with modules that encapsulate these negotiation concepts.

AUMENTANDO A TRANSPARÊNCIA DO GOVERNO POR MEIO DA TRANSFORMAÇÃO DE DADOS GOVERNAMENTAIS ABERTOS EM DADOS LIGADOS

Since its inception, the Web has undergone constant evolution in order to improve itself as a mean of global communication and information sharing. Open Government Data are increasingly being published on the Web, contributing to the transparency and the reusability of public data. At the same time, the use of Linked Data has been increasing in recent years, enabling the development of better and smarter applications. In this context, this paper proposes the publication of Open Government Data using the Linked Data practices, by creating a data set of Brazilian politicians with information collected from different sources.

Improving Software Agent Communication with Structural Ontology Alignment Methods

To perform tasks on the semantic web, software agents must be able to communicate with other agents using domain ontologies, even when considering different ontologies. In this regard, it is necessary to address semantic interoperability to enable agents to recognize common concepts and misunderstandings. In this paper, the authors propose the use of negotiation concepts in business scenarios for addressing concept compatibilization problems in communication between software agents and present an algorithm developed in the GNoSIS system. A validation of this approach is presented.

Combining resemblance functions for ontology alignment

Ontology alignment has impact in how ontologies will be treated by actors in semantic web and stills an unsolved issue. To contribute in this issue, we present an algorithm developed in the GNoSIS system. This solution uses both syntactic and semantic techniques in a structural approach. The algorithm uses distinct resemblance functions and calculates the degree of similarity between the concepts in a recursive manner, calculating the resemblance function result between concepts based on the total similarity degree between concepts with a close kinship. A validation of this approach is presented in this article.

Use of Automatic Speech Recognition Systems for Multimedia Applications

The need to retrieve information in multimedia content increases the demand for systems that use automatic speech recognition. A speech recognition system enables the computer to interpret audio signals, generating approximate textual transcriptions. These systems are based on probabilistic models that create a robust and correct model for human speech. In this paper it is presented a speech recognition systems architecture and a description of its basic components: the acoustic model, language model, lexical and decoder. The training process of acoustic and language models is also presented. Finally, it its presented how these systems can be used in several applications.

Comparativo entre fontes de dados para anotação automática de videoaulas

The volume of the educational video repositories has rapidly increased as the creation of new digital resources is facilited. However, such repositories need better indexing and searching engines. Users find it difficult to find useful information when educational videos has poor quality metadata. The proccess of adding new descriptors to videos is called annontation. In this work, we will discuss how the information extracted from educational videos influence the automatic semantic annotation task. We will present an comparative analysis among these information sources and we will demonstrate which information sources are most useful for annontation task. Resumo. A facilidade de criação de conteúdos digitais tem permitido que repositórios de recursos educacionais possam crescer rapidamente, gerando necessidade de melhores mecanismos de indexação e busca. Para usuários, ainda há muita dificuldade de encontrar vı́deos de interesse quando estes possuem metadados de baixa qualidade. O processo de atribuir novos descritores aos vı́deos é chamado de anotação. Este trabalho tem como objetivo explorar as fontes de informação presentes em videoaulas que podem auxiliar no processo no anotação semântica. O artigo apresenta uma análise comparativa entre a qualidade dessas fontes de dados de forma a demonstrar quais fontes geram melhor resultado para o processo de anotação.

Geração de Sequências Curriculares Adaptativas baseada em Computação Evolucionária: Estado da Arte e Tendências

For effective adoption of e-Learning systems, the student’s needs and context must be taken into consideration when delivering content. One of the most interesting challenges in this area is the selection of an Adaptive Curriculum Sequencing that provides individualized instruction. Such a challenge is known in the literature as an NP-hard problem, causing frequent use of metaheuristics, particularly of Evolutionary Computing, to approximate the best solution. In this paper a review of the lastest works in this field of research is presented with a comparison model according to the variables used for the sequencing. Resumo. Para efetiva adoção dos sistemas de e-Learning, as necessidades e o contexto do aluno precisam ser levados em consideração na entrega de conteúdo. Assim, um dos desafios mais interessantes da área é a seleção de uma Sequência Curricular Adaptativa que forneça um ensino individualizado. Tal desafio é conhecido na literatura como um problema NP-Difı́cil, causando uma frequente utilização de meta-heurı́sticas, particularmente de Computação Evolucionária, para aproximar à melhor solução. Neste artigo é feita uma revisão dos últimos trabalhos neste campo de pesquisa, apresentando um modelo de comparação de acordo com as variáveis utilizadas para o sequenciamento.

Uma abordagem estrutural para calcular similaridade entre conceitos de ontologias

Resumo: O problema da compatibilização entre ontologias ainda é um problema aberto. Para tratar esse problema, apresentamos o algoritmo implementado no sistema GNoSIS. Nossa solução faz uso tanto de técnicas sintáticas quanto semânticas numa abordagem estrutural, facilitando o mapeamento ou alinhamento entre ontologias de diferentes domínios. Esse algoritmo se utiliza de diferentes funções de similaridade e calcula o grau de similaridade entre os conceitos de forma recursiva, calculando o resultado da função de similaridade entre dois conceitos com base no grau de similaridade total entre os conceitos que possuem parentesco próximo. Uma validação da abordagem é apresentada neste artigo.