05958761

a

05958761 Berzosa, Alba Villar, Jos\'e R. Sedano, Javier Garc{\'\i}a-Tamargo, Marco de la Cal, Enrique An study of the tree generation algorithms in equation based model learning with low quality data. Corchado, Emilio (ed.) et al., Hybrid artificial intelligent systems. 6th international conference, HAIS 2011, Wroclaw, Poland, May 23--25, 2011. Proceedings, Part II. Berlin: Springer (ISBN 978-3-642-21221-5/pbk). Lecture Notes in Computer Science 6679. Lecture Notes in Artificial Intelligence, 84-91 (2011). 2011 Berlin: Springer EN Genetic Programming Genetic Algorithm and Programming Low Quality Data Multiobjective Simulated Annealing

doi:10.1007/978-3-642-21222-2_11

Summary: The undesired effects of data gathered from real world can be produced by the noise in the process, the bias of the sensors and the presence of hysteresis, among other uncertainty sources. In previous works the learning models using the so-called Low Quality Data (LQD) has been studied in order to analyze the way to represent the uncertainty. It makes use of genetic programming and the multiobjective simmulated annealing heuristic, which has been hybridized with genetic operators. The role of the tree generation methods when learning LQD was studied in that paper. The present work deals with the analysis of the generation methods relevance in depth and provides with statistical studies on the obtained results.