Early warning system for coffee rust disease based on error correcting output codes: a proposal
Article Sidebar
The total or partial reproduction of the contents of the journal for educational, research, or academic purposes is authorized as long as the source is cited. For reproduction for other purposes, express authorization from the Sello Editorial Universidad de Medellín is required.
Main Article Content
Abstract
Colombian coffee producers have had to face the severe consequences of the coffee rust disease since it was first reported in the country in 1983. Recently, machine learning researchers have tried to predict infection through classifiers such as decision trees, regression Support Vector MaÂchines (SVM), non-deterministic classifiers and Bayesian Networks, but it has been theoretically and empirically demonstrated that combining multiple classifiers can substantially improve the classification perforÂmance of the constituent members. An Early Warning System (EWS) for coffee rust disease was therefore proposed based on Error Correcting Output Codes (ECOC) and SVM to compute the binary functions of Plant Density, Shadow Level, Soil Acidity, Last Nighttime Rainfall Intensity and Last Days Relative Humidity.