An investigation of two-step cascaded CNN for the detection of gravitational wave signal from two different astronomical sources

Abstract

Recently, Convolutional neural network (CNN), a class of deep neural network, has been widely used for processing images and video data. The reason that CNN performs better than the classic neural network on images and video is basically because convolutional layers take advantage of the inherent properties of images. Therefore, in this paper, we propose and investigate two-step a cascaded classification model using CNN for the detection of gravitational wave (GW) signals emitting from the two different heavenly astronomical objects in the noisy time-series data. To build a robust model for the detection of GW waves, we considered prominent binary black holes (BBH) and binary neutron stars (BNS). In the proposed model, first, we used CNN to know whether in the noisy data stream, the considered GW signal is present or not. While in the second step, we further applied CNN to know that the present GW signal in the stream is BBH or BNS. The analysis shows that the proposed two-step cascaded classification model can detect not only the presence of the signal but also able to distinguish between the type of signal i.e., whether the gravitational wave signal is from BBH or BNS.