Title :
Evolving best-basis representations
Author :
Da Silva, Adelino R Ferreira
Author_Institution :
Univ. Nova de Lisboa, Monte de Caparica, Portugal
Abstract :
Adapted waveform analysis decomposes a signal or dataset into a linear expansion of waveforms that are selected from a redundant dictionary of functions. These waveforms are chosen in order to best match the signal structures. We consider decompositions using libraries of time shifted wavelet packet bases. We use evolutionary programming as the main tool to solve the optimization problem of finding the joint best basis, best shift and best wavelet filter for representing a given signal. The evolved best basis is combined with linear discriminant analysis for the purpose of temporal pattern identification
Keywords :
evolutionary computation; filters; pattern matching; signal processing; waveform analysis; wavelet transforms; adapted waveform analysis; best shift; best wavelet filter; best-basis representation evolution; dataset; evolutionary programming; joint best basis; linear discriminant analysis; linear expansion; optimization problem; redundant dictionary; signal decomposition; signal structures; temporal pattern identification; time shifted wavelet packet bases; Cost function; Dictionaries; Entropy; Filters; Genetic programming; Libraries; Linear discriminant analysis; Signal analysis; Time frequency analysis; Wavelet packets;
Conference_Titel :
Evolutionary Computation, 1999. CEC 99. Proceedings of the 1999 Congress on
Conference_Location :
Washington, DC
Print_ISBN :
0-7803-5536-9
DOI :
10.1109/CEC.1999.781940
