EPIA'03 - 11th Portuguese Conference on Artificial Intelligence

	Session: December 6, 11:30-12:15, Room A
Title:	Predicting Harmful Algae Blooms
	Rita Ribeiro and Luis Torgo
Abstract:	In several applications the main interest resides in predicting rare and extreme values. This is the case of the prediction of harmful algae blooms. These rare phenomena consist of an unusual occurrence of certain algae in water samples. The occurrence of these blooms has a strong impact in river life forms and water quality and turns out to be a serious ecological problem. Being able to predict these blooms is of extreme importance. In this paper, we describe a data mining method whose main goal is to predict accurately this kind of rare extreme values, as well as to understand under which conditions these values occur. We propose a new splitting criterion for regression trees that enables the induction of trees achieving these goals. We carry out an analysis of the obtained results with our method on this application domain and compare them to those obtained with standard regression trees. We conclude that this new method achieves better results in terms of the evaluation statistics that are relevant for this kind of applications.

Back to schedule.