Pulsar Candidates Classification with Deep Convolutional Neural Networks

TL;DR

This paper presents a deep CNN model for classifying pulsar candidates, utilizing raw subplots as inputs and a synthetic data augmentation technique to improve detection performance on imbalanced datasets.

Contribution

The study introduces a novel deep CNN architecture and a simple data augmentation method based on pulsar characteristics for improved pulsar candidate classification.

Findings

Achieved recall of 0.962 on HTRU 1 dataset

Achieved precision of 0.963 on HTRU 1 dataset

Effective data augmentation method for pulsar signals

Abstract

As performance of dedicated facilities continually improved, massive pulsar candidates are being received, which makes selecting valuable pulsar signals from candidates challenging. In this paper, we designed a deep convolutional neural network (CNN) with 11 layers for classifying pulsar candidates. Compared to artificial designed features, CNN chose sub-integrations plot and sub-bands plot in each candidate as inputs without carrying biases. To address the imbalanced problem, data augmentation method based on synthetic minority samples is proposed according to characteristics of pulsars. The maximum pulses of pulsar candidates were first translated to the same position, then new samples were generated by adding up multiple subplots of pulsars. The data augmentation method is simple and effective for obtaining varied and representative samples which keep pulsar characteristics. In the experiments on HTRU 1 dataset, it shows that this model can achieve recall as 0.962 while precision as 0.963.