Unusual signal detection using electromagnetic wave observation with multi-layer neural network

It is well known that the electromagnetic (EM) waves that radiate from the earth's crust are useful for predicting earthquakes. We observe electromagnetic waves in the extremely low frequency (ELF) band of 223Hz. These observed signals contain several undesired signals due to fluctuations in the magnetosphere or the ionized layer, lightning radiation from the tropics, and so on. We proposed a multi-layer neural network (NN) with a compressed data. The proposed NN is useful for precursor signal detection, however, detection sensitivity is not discussed enough. In this paper, the artificial signal is used for obtaining a detection rate. This uses as a parameter to avoid an over-fitting. Moreover, the uniform random number (RN) is added to input signal for improving generalization capability. It is shown that proposed NN is effective to improve a generalization capability of the problem of a precursor signal detection.