Laci Mary Barbosa Manhães

Previsão de Estudantes com Risco de Evasão Utilizando Técnicas de Mineração de Dados

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.

WAVE: an architecture for predicting dropout in undergraduate courses using EDM

Predicting the academic progress of student is an issue faced by many public universities in emerging countries. Although, those institutions stores large amounts of educational data, they fail to recognize the students that are in danger to leave the system. This paper presents a novel architecture that uses EDM techniques to predict and to identify those who are at dropout risk. This approach allows academic managers to monitor the progress of the students in each academic semester, identifying the ones in difficult to fulfill their academic requirements. This paper shows initial experimental results using real world data about of three undergraduate engineering courses of one the largest Brazilian public university. According to the experiments, the classifier Naïve Bayes presented the highest true positive rate for all datasets used in the experiments.

Analysis of the performance of a fuzzy controller developed to guide a simulated robot

The main goal of this work is to compare two different configurations defined for a fuzzy controller that is used to guide a simulated robot through a virtual world populated with randomly placed obstacles. In the first configuration the system controls a single output, the rotation angle of the robot. In the second configuration there is an additional output that controls the robot step. In order to compare the performance of both controllers we studied the robot stability based on the removal of rules. We also measured two parameters: processing time and the amount of steps necessary to reach the final goal. The simplicity, easiness of design and robustness of both controllers suggests that for many control tasks, it is possible to create a fuzzy system that performs well under real conditions. The results show that an improved performance was obtained when the fuzzy module processed more variables from the environment, without compromising the simplicity of the design.

Analysis of the Stability of a Fuzzy Control System Developed to Control a Simulated Robot

This work presents a fuzzy system designed to guide a simple simulated robot through a virtual world populated with randomly placed obstacles. The environment simulates a situation where the robot has to move in a complex world and has to calculate not only its direction but also its speed. The main goal was to investigate the performance of a fuzzy controller studying its sensitivity and robustness. The sensors used by the robot were very simple, so its knowledge of the environment was limited. The system was quickly engineered and proved to be very successful reaching the goal in all designed tests. The tests also proved that the controller is very robust. The simplicity, easiness of design and robustness of the controller, suggests that for many control tasks, it is possible to create a fuzzy system that can perform very well under real conditions

Towards automatic prediction of student performance in STEM undergraduate degree programs

STEM is defined as learning in the fields of Science, Technology, Engineering and Mathematics. In Brazil, many students leave the educational system before achieving a tertiary degree in these fields. Poor academic performance in STEM undergraduate courses is an issue faced by many universities, both in developed and emerging countries. Although these universities store large amounts of data, there are few studies about educational data mining (EDM) software tools designed to aid educational managers in analyzing student learning and improving the quality of undergraduate degree programs. Our approach may assist managers in supervising students at the end of each academic term, thus enabling them to identify the students in difficulty of fulfilling the academic requirements toward a degree. This paper shows quantitative experimental studies using a large dataset of real data from five traditional STEM undergraduate courses of one of the largest public Brazilian universities. Finally, the results show that data mining algorithms can establish effective prediction models from existing student data.

Computational Neuroscience

Understanding the core function of the brain is one the major challenges of our times. In the areas of neuroscience and education, several new studies try to correlate the learning difficulties faced by children and youth with behavioral and social problems. This work aims to present the challenges and opportunities of computational neuroscience research, with the aim of detecting people with learning disorders. We present a line of investigation based on the key areas: neuroscience, cognitive sciences and computer science, which considers young people between nine and eighteen years of age, with or without a learning disorder. The adoption of neural networks reveals consistency in dealing with pattern recognition problems and they are shown to be effective for early detection in patients with these disorders. We argue that computational neuroscience can be used for identifying and analyzing young Brazilian people with several cognitive disorders.

The Impact of High Dropout Rates in a Large Public Brazilian University

This paper uses educational data mining techniques to identify the variables that can help educational managers to detect students that present low performance or are in risk to dropout their undergraduate education. We investigated real world academic data of students of the largest Public Federal Brazilian University. We established three categories of students with different academic trajectory in order to investigate their performance and the dropout rates. This study shows that even analyzing three different classes of 14.000 students it was possible to have a global precision above 80% for several classification algorithms. The results of Naive Bayes model were used to support the quantitative analysis. In this work, we stress that even few differences between the three classes of students that can be perceived on the basis of qualitative information.