Title :
Closed loop optimization of features for neural classifiers
Author :
van der Merwe, N.T. ; Hoffman, A.J.
Author_Institution :
Sch. of Electron. & Electr. Eng., Potchefstroom Univ., South Africa
Abstract :
The selection and preprocessing of features are crucial to the success of a classifier for pattern recognition applications. The preprocessing often involves filters, transformations and non-linear processing of the raw data. Since the training data required is an exponential function of the number of features, a reduction or transformation of the features is essential. While it is frequently possible to heuristically select reasonable values pertaining to the selection of these parameters, an automated approach could be of great value in different application areas. Various factors relating to the optimization process are described and the results of continuous wavelet based optimization on seismic buffer recognition are described
Keywords :
closed loop systems; feature extraction; feedforward neural nets; fuzzy neural nets; geophysical signal processing; learning (artificial intelligence); matched filters; optimisation; pattern classification; radial basis function networks; seismology; wavelet transforms; closed loop optimization; continuous wavelet based optimization; exponential function; feature extraction; feature transformation; feedforward neural network; fuzzy logic neural network; matched filter; neural classifiers; pattern recognition applications; preprocessing; radial basis function neural network; seismic buffer recognition; training data; Chemical transducers; Continuous wavelet transforms; Data mining; Feature extraction; Feedforward neural networks; Filters; Neural networks; Pattern recognition; Testing; Training data;
Conference_Titel :
Communications and Signal Processing, 1998. COMSIG '98. Proceedings of the 1998 South African Symposium on
Conference_Location :
Rondebosch
Print_ISBN :
0-7803-5054-5
DOI :
10.1109/COMSIG.1998.736926
