Rogério Cid Bastos

Uncertainty analysis in political forecasting

Medicine, engineering, and finance are traditional fields for the application of Fuzzy Logic (FL); however, in social sciences, the utilization of FL can be intensely explored as a valuable analysis instrument. Joining fuzzy with Multiple Criteria Decision Making (MCDM), the natural complex and uncertain criteria of social problems can be adequately explored. A suitable uncertainty analysis is the focal point in the social field. In this direction, an intelligent computational method for election forecasting is proposed as a practical result of this research. The main objective is to present a more flexible methodology for political assessment comparing to traditional methods.

Fuzzy MCDM in election prediction

The application of fuzzy logic (FL) in traditional fields like engineering, medicine or finance has become a common practice, however in social sciences, mainly in politics, the utilization of FL can be intensely explored. Joining fuzzy logic with multiple criteria decision making (MCDM), the natural, complex and uncertain criteria of political problems can be adequately treated. The practical result of the research is a computational system for election forecasting.

Integration of BDI agent with Fuzzy Logic in a Virtual Learning Environment

This research proposes and develops a framework that integrates the Belief-Desire-Intention (BDI) agent architecture to Fuzzy Logic (LF). The result of this integration is the development of a module, built in the specification of the proposed framework, which is able to follow the process of student learning through the analysis of his performance in Virtual Learning Environment (VLE). This framework is composed of four agents: student, evaluation, learning activities and monitoring. The student agent is a BDI agent, which has beliefs modeled by the fuzzy set theory. The other agents are reactive agents. The learning activities and evaluation agents collect data from the environment and exchange information with the student agent. This agent processes the data and determines the appropriate educational stimulus according to the student model. Following, the monitoring agent is triggered to perform the given pedagogical action. This architecture was implemented in a VLE that is used by graduate students at UFSC. The programming languages PHP, Perl and C, and the MySQL database were used in this work.

A human capital measurement scale

Purpose Despite the large number of academic publications in human capital, there are few instruments to measure it. The purpose of this paper is to develop a holistic scale to measure human capital, considering aspects related to competence, attitudes, skills, leadership, and organizational memory. Design/methodology/approach First, a literature review of the existing measurement models was carried out. Second, based on the results the authors developed a scale and a questionnaire that were applied in a financial institution in Santa Catarina, Brazil, supported by a factor analysis and a reliability analysis. Findings As a result of this study a scale consisting of 13 variables of human capital emerged that have been grouped into three factors – leadership and motivation; qualifications; and satisfaction and creativity – which can assist in the organization’s human capital measurement. From a theoretical view, a more holistic scale is provided, which helps to overcome a unilateral focus on knowledge (intangibles). Research limitations/implications This work points out that the survey data were collected from a sample of 220 relationship managers of a specific financial institution. The results should be tested in other banks or organizations from other sectors to check their suitability and to be generalized. Practical implications From a practical point of view, it contributes a “tool” that can assist in the measurement of human capital and in the knowledge contained, dimensioning the organizational memory and human repositories. Originality/value This is the first study that provides a scale to measure organizational human capital from the Brazilian financial perspective.

Improvement of the Short Term Load Forecasting Through the Similarity Among Consumption Profiles

In order to achieve high quality standards in electrical power systems, utility companies rely upon load forecasting to accomplish critical activities such as optimal dynamic dispatch and smart performance in the power wholesale market. Several works propose hybrid intelligent forecasting models to deal with the dynamic and non-linear characteristics of the load at a relatively high computational cost. While such approaches give emphasis to the forecasting itself, this paper presents a procedure to detect similarities among distinct consumption profiles. Empirical results show that similar profiles share similar sets of relevant predictors. As finding similarities among profiles is less costly than finding the set of relevant predictors from scratch, a new parameter selection method is proposed. Such method is employed to build some neural forecasters with a marked improvement in the learning time.

Fuzzy Modeling Built Through a Data Mining Process

This work uses fuzzy logic to identify the learning profile of students in a teaching and learning environment. The purpose of this identification is to lead the student to more appropriate use of the available resources in the environment. The fuzzy modeling has been developed from a process of data mining. The mined data set has several learning profiles of several students. The classification method called Decision Tree (DT) was applied in the mining process, and for the comparison two algorithms were used. The analysis of data from the DT allowed to validate and improve the results of fuzzy modeling. This validation process can be used in the remodeling of the characteristics of any fuzzy system, it is a way to build a more harmonious and consistent model, in this case, the student profile.

A Concept Map Extractor Tool for Teaching and Learning

This work presents a tool to help concept maps’ design process. This tool was developed to organize contents from thematic modules of a course, applying concept maps techniques. In this tool, teachers can build their own concept maps based in textual reference documents. Teachers also can use a visual editor to design maps and linking learning objects to concepts. Students can access learning objects and make their own notes in their own concept maps improving teaching and learning process. The concept map extractor is an algorithm based in text mining techniques for term extraction. This algorithm extracts relevant terms that can be considered concepts or links, making agile the concept map building process.

Radial basis function for classification of remote sensing images

This work presents a hybrid classifier for multispectral images using radial basis function networks (RBF). A Kohonen self-organization-map is used in substitution of the k-means algorithm in unsupervised stage of training. The algorithm of the pseudo-inverse is used for the determination of the weights of the supervised stage. The architecture proposed reduces the time required for processing. Also, it presents satisfactory results with small training samples. A practical application is accomplished and the results obtained between the classifier of maximum likelihood and the proposed hybrid classifier are compared.

Um módulo adaptativo para AVA baseado no desempenho do estudante

A educacao a distancia tem ganhado significativa atencao tanto na academia quanto nas iniciativas governamentais. Neste contexto, cresce tambem a preocupacao com a avaliacao da qualidade dos diversos aspectos destes cursos mediados pelas tecnologias da informacao e comunicacao. Apesar de muitos trabalhos discutirem diversos aspectos da avaliacao em Ead, a literatura carece de relatos de experiencia que, especialmente, abordem os cursos tecnicos a distancia que possuem especificidades relevantes. Assim, este trabalho relata uma experiencia onde se avalia e adapta uma das propostas existentes na literatura de avaliacao mediada por foruns, ao contexto dos cursos tecnicos a distancia, constituindo-se esta adaptacao e sua discussao as principais contribuicoes do mesmo.Em Educacao a Distância mediada por meio de Ambientes Virtuais de Aprendizagem, foruns de discussao sao um instrumento importante e amplamente utilizado na articulacao de debates e discussoes entre os atores envolvidos no processo de ensino e aprendizagem. Com a ampla utilizacao dos foruns muitas mensagens sao trocadas e isso, por vezes, excede a capacidade de monitoramento por parte dos professores e tutores. O presente trabalho apresenta a concepcao de um classificador de mensagens de foruns que classifica as mensagens em positivas ou negativas, a fim de identificar mensagens que necessitam de maior atencao. Este trabalho aplica conceitos de mineracao de textos, com o algoritmo SVM obtendo taxas de acerto satisfatorias.Este artigo apresenta o framework Contagious, cujo proposito e estabelecer diretrizes que norteiem a construcao de redes sociais online orientadas a Difusao de Inovacoes. Compreendo-se o fenomeno das redes sociais online como consequencia natural do carater social do ser humano, vislumbrou-se esse meio tecnologico de comunicacao e interacao social como potencial ferramenta para a extensao de praticas educativas, com vistas a formacao do carater integral do cidadao. Para isso, foi adotada a teoria de Difusao de Inovacoes, propria das ciencias sociais. As contribuicoes deste trabalho, portanto, compreendem duas vertentes: a) o mapeamento de principios de uma teoria social na forma de recursos computacionais e; b) um enfoque orientado a educacao sobre as redes sociais online.A proposta do trabalho consiste em desenvolver um sistema para ser usado no celular como ferramenta de auxilio para alfabetizacao, utilizando-se de imagens e sons como forma de facilitar o aprendizado. Como metodo de desenvolvimento utiliza-se o processo P@PSEduc (Processo Agil para Software Educativo) e a ferramenta JME (Java Micro Edition).O crescente uso e difusao de tecnologias Web, a ubiquidade de ferramentas educacionais vem proporcionado verdadeiras revolucoes nos ambientes de ensino. Atualmente, sabe-se que nao mais se deve tratar alunos de forma homogenea, como se assim os fossem. Em face disso, este artigo apresenta um sistema adaptativo de apoio a aprendizagem colaborativa, cujo tema e a construcao e representacao do conhecimento por meio de mapas mentais multimidia. Tal sistema, baseia-se na Teoria da Carga Cognitiva, cuja preocupacao primaria e a facilidade com a qual as informacoes sao processadas pelos individuos.

Sistemas multiagentes: mapeando a evasão na educação a distância

Uma instituicao, ao adotar a modalidade a distância, enfrenta preocupacoes que envolvem principalmente o fantasma da evasao. Esse fantasma nao e prerrogativa de uma instituicao em particular, mas de todas as instituicoes publicas e privadas. Estudar as causas que contribuem para a permanencia e exito escolar e combater a evasao. Para isso, e preciso trabalhar com duas frentes: uma de acao imediata, que busca resgatar o aluno “evadido”, e outra de reestruturacao interna, que implica a discussao e avaliacao nao so de combate a evasao, mas ao fracasso escolar como um todo. O artigo apresenta uma proposta de modelo conceitual preditivo de evasao na modalidade de educacao a distância, modelado sob uma arquitetura de Sistema Multiagentes. Espera-se que, a partir desta proposicao, o problema da evasao venha a ser mais bem visualizado, auferindo novas perspectivas de gestao.