HMM based anomalous signal detection from ELF electromagnetic wave signals

It is known that the detection of a seismic radiation emitted from the earth's crust is useful for predicting earthquakes. We have been observing the electromagnetic (EM) wave in the Extremely Low Frequency (ELF) band. Various methods have been proposed to detect an anomalous EM radiation from recorded data. In this paper, we propose the anomalous signal detection based on HMM whose input vector is the amplitude density distribution of an EM wave. The amplitude density distribution is calculated from the image of an EM wave data. The optimal scale of an image to calculate an amplitude density distribution is examined with use of a false detection rate. Moreover the optimal number of states of HMM is investigated to achieve an accurate detection.