No abstract

School dropout in Brazilian public education is a huge problem. One in four Brazilians leave school prematurely, before completing high school. This work deals with part of the problem, analyzing school dropout in the last year of Middle School on public schools of Pernambuco/Brazil, with data collected from the official National School Census, between 2011 and 2012. Decision Trees, Rules Induction and Logistic Regression were the Knowledge extraction techniques applied to identify the profile of a dropout student and estimate the propensity for that. Results show that age, classes' shift and geographic region strongly influence dropout. Resumo. A evasão escolar na educação pública brasileira é um problema de grandes proporções. Um em cada quatro brasileiros deixa a escola prematuramente, antes de terminar o ensino médio. Este trabalho faz um recorte do problema, ao analisar a evasão escolar no último ano do ensino fundamental nas escolas públicas estaduais e municipais do estado de Pernambuco, com base nos dados dos Censos Escolares 2011 e 2012. Árvore de Decisão, Indução de Regras e Regressão Logística foram as técnicas para extração de conhecimento aplicadas visando a identificar o perfil do aluno evasor e estimar a propensão à evasão. Os resultados mostraram que fatores como idade, turno das aulas e região geográfica das escolas influenciam fortemente a evasão.

No abstract

No abstract

A time series is a sequence of observations of a random variable. Hence, it is a stochastic process. Forecasting time series data is important component of operations research because these data often provide the foundation for decision models. This models are used to predict data points before they are measured based on known past events. Researches in this subject have been done in many areas like economy, energy production, ecology and others. To improve the process of time series forecasting it is important to identify which of past values will be considered to be used in the models by eliminating redundant or irrelevant attributes. Two hybrid systems Harmony Search with Neural Networks (HS) and Temporal Memory Search with Neural Networks (TMS) are improved and a new one is proposed: the Temporal Memory Search Limited with Neural Networks (TMSL). The performance of the techniques is investigated through an empirical evaluation on twenty real-world time series.