Fuzzy Lattice Reasoning (FLR) classifier and its application for ambient ozone estimation

By V.G. Kaburlasos, I.N. Athanasiadis & P.A. Mitkas
In International Journal of Approximate Reasoning, 45(1):152-188, 2007.

Abstract:
Cover image The Fuzzy Lattice Reasoning (FLR) classifier is presented for inducing descriptive, decision-making knowledge (rules) in a mathematical lattice data domain including the Euclidean space. Tunable generalization is possible based on non-linear (sigmoid) positive valuation functions; moreover, the FLR classifier can deal with missing data. Learning is carried out both incrementally and fast by computing disjunctions of join-lattice interval conjunctions, where a join-lattice interval conjunction corresponds to a hyperbox in Euclidean space. Our testbed in this work concerns the problem of estimating ambient ozone concentration from both meteorological and air-pollutant measurements. The results compare favorably with results obtained by C4.5 decision trees, fuzzy-ART as well as backpropagation neural networks. Novelties and advantages of classifier FLR are detailed extensively and in comparison with related work from the literature.

Read also: article in pdf - IJAR