Entendimento e preparação de dados no processo de descoberta de conhecimento aplicado a sistema de alerta da ferrugem do cafeeiro.

Abstract

Knowledge Discovery in Databases is the extraction of implicit, previously unknown and potentially useful information from data. It is a process that establishes an initial data pre-processing which aims to help understand the problem and to better expose the data for the subsequent phases. This work discusses and presents the results of data understanding and data preparation of a knowledge discovery process instance applied to a coffee rust forecasting system. Different investigation and manipulation procedures has been adopted, and the results, in the form of data descriptions, identified data quality problems and prepared data sets, confirm the importance of this type of activity on the success of the project.