Viability of an Alarm Predictor for Coffee Rust Disease Using Interval Regression

Author(s)

Luaces, Oscar ; Rodrigues, Luiz Henrique A. ; Alves Meira, Carlos Alberto ; Quevedo, Jose R. ; Bahamonde, Antonio ; GarciaPedrajas, N ; Herrera, F ; Fyfe, C ; Benitez, JM ; Ali, M

• Document type: Journal article
• Source: Lecture Notes in Computer Science; v. 6097, p. 2-pg., 2010-01-01.

Abstract

We present. a method to formulate pc:dicta:ins regal ding continuous variables using regressors able to predict. mter vats rather than single points They can be learned explicitly using the so-called insensitive zone of regression Support Vector Machines (SVM) The motivation for this research is the study of a meal case. we discuss the feasibility of an alarm system for coffee rust, the main coffee clop disease in the world The objective Is to pi edict whether the percentage of infected coffee leaves (the incidence of the disease) will be above a given threshold The 1 requirements Of such a system include avoiding false negatives, seeing as these would lead to not preventing the disease The ann of reliable predictions, on the other hand, is to use chemical prevention of the disease only when necessary in order to obtain healthier products and reductions in costs and environmental impact, Although the breadth of the predicted mter vas improves the reliability of predictions, it, also increases the number of uncertain situations re those whose predictions include Incidences both below and above the threshold These cases would require deeper analysis Our conclusion is that it is possible to reach a made-off that makes the implementation of an alarm system for coffee rust, disease feasible (AU)

• FAPESP's process: 09/07366-5 - Visit to university of Oviedo and university of Castilla-La Mancha, in Spain, aiming for a closer cooperation in the field of data mining and knowledge discovery in agricultural databases
• Grantee: Luiz Henrique Antunes Rodrigues
• Support Opportunities: Scholarships abroad - Research