Application of quadratic neural networks to seismic signal classification

This paper solves the seismic signal classification problem using the quadr atic neural networks with closed-boundary discriminating surfaces. In this study, we have demonstrated the quadratic neural network (QNN) potential ca pabilities in application to the seismic signal classification problems and show that the efficiency achieved here, is much better to what obtained wi th conventional multilayer neural networks. Firstly, we have performed some pre-processing on the long period recordings to cancel out the instrumenta l and attenuation side effects. Secondly, we have extracted the ARMA filter coefficients of the windowed P-wave phase through some matrix manipulation s using the conventional Prony ARMA modeling scheme. The derived coefficien ts are then applied to QNN for training and classification. The results hav e shown that a quadratic neuron is likely to have a performance similar to that of a multilayer perceptron when the target is to discriminate distribu tion of points in clusters within the input space. (C) 1999 Elsevier Scienc e B.V. All rights reserved.