Time series in time domains with a hierarchical structure may be summarized by means of sets of quantified fuzzy sentences of the form "Q of D is A", where Q is a quantifier, D is a linguistic time interval, and A is a linguistic value. Finding concise and accurate summaries that cover the whole time domain is a hard optimization problem, that we solve by proposing a multi-objective memetic algorithm based on NSGA-II with the addition of a number of intelligent mutation operators that apply heuristics to improve solutions.
A multi-objective memetic algorithm for the linguistic summarization of time series / R. Castillo Ortega, N. Marín, D. Sánchez, A.G.B. Tettamanzi - In: GECCO '11 : 13. annual Conference on genetic and evolutionary computation : proceedings / [a cura di] N. Krasnogor, P.L. Lanzi. - New York : Association for computing machinery, 2011. - ISBN 9781450306904. - pp. 171-172 (( Intervento presentato al 13. convegno Conference on Genetic and Evolutionary Computation Conference (GECCO) tenutosi a Dublin nel 2011 [10.1145/2001858.2001954].
A multi-objective memetic algorithm for the linguistic summarization of time series
A.G.B. TettamanziUltimo
2011
Abstract
Time series in time domains with a hierarchical structure may be summarized by means of sets of quantified fuzzy sentences of the form "Q of D is A", where Q is a quantifier, D is a linguistic time interval, and A is a linguistic value. Finding concise and accurate summaries that cover the whole time domain is a hard optimization problem, that we solve by proposing a multi-objective memetic algorithm based on NSGA-II with the addition of a number of intelligent mutation operators that apply heuristics to improve solutions.Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.