A classifier of satellite signals based on the back-propagation neural network

Abstract

In order to achieve the fast classification for Ultra-low-frequency (ULF) electron field data in the Space, this paper designs an electric field classifier based on the back-propagation (BP) neural network with extracting the ULF section electric field waveform data of the Wenchuan earthquake, using the statistical methods to obtain four characteristics of the mean value, mean square error, skewness and kurtosis of an electric field components. Its findings are summarized as follows: (1) This classifier of electric signals is effective with normal data and abnormal data accounting for 72.3% and 27.7% respectively; (2) A momentum factor can improve effectively the BP network performance, which the momentum factor is smaller, the network convergence speed is faster; (3) An adaptive learning factor can reduce effectively the target error. This method is also suitable for the data classification of magnetic field and ion concentration to obtain the seismic precursor knowledge, which has the practical significance for earthquake monitoring and prediction.