Pulsar candidate classification using generative adversary networks
Pulsar candidate classification using generative adversary networks
复制标题
DOI：
10.1093/mnras/stz2975
复制
发表时间：
2019-12
影响因子：
4.8
通讯作者：
Ping Guo;Fuqing Duan;Pei Wang;Yao Yao-Yao;Qian Yin;Xin Xin-Xin;Di Li;L. Qian;Shen Wang;Z. Pan;Lei Zhang
中科院分区：
文献类型：
--
作者：
Ping Guo;Fuqing Duan;Pei Wang;Yao Yao-Yao;Qian Yin;Xin Xin-Xin;Di Li;L. Qian;Shen Wang;Z. Pan;Lei Zhang
发现脉冲星是射电天文学领域一个重要且有意义的研究课题。随着天文仪器的出现，数据采集的数量和速度呈指数级增长。这一发展需要关注能够挖掘大型天文数据集的人工智能（AI）技术。自动脉冲星候选识别（APCI）可以被视为一项确定潜在候选者以供进一步研究并消除射频干扰和其他非脉冲星信号的噪声的任务。据现有文献报道，APCI 已采用人工智能技术，特别是基于卷积神经网络（CNN）的技术。然而，提高基于 CNN 的脉冲星识别的性能具有挑战性，因为真实脉冲星样本的数量极其有限，这导致了严重的类别不平衡问题。为了解决这些问题，我们提出了一个将深度卷积生成对抗网络（DCGAN）与支持向量机（SVM）相结合的框架。 DCGAN用作样本生成和特征学习模型，SVM用作分类器，用于在推理阶段预测候选标签。所提出的框架是一种新颖的技术，它不仅可以解决类不平衡问题，而且可以学习脉冲星候选者的判别性特征表示，而不是在预处理步骤中计算手工制作的特征。该方法可以提高APCI的精度，并且在两个脉冲星数据集上进行的计算机实验验证了该方法的有效性和效率。
Discovering pulsars is a significant and meaningful research topic in the field of radio astronomy. With the advent of astronomical instruments, the volume and rate of data acquisition have grown exponentially. This development necessitates a focus on artificial intelligence (AI) technologies that can mine large astronomical data sets. Automatic pulsar candidate identification (APCI) can be considered as a task determining potential candidates for further investigation and eliminating the noise of radio-frequency interference and other non-pulsar signals. As reported in the existing literature, AI techniques, especially convolutional neural network (CNN)-based techniques, have been adopted for APCI. However, it is challenging to enhance the performance of CNN-based pulsar identification because only an extremely limited number of real pulsar samples exist, which results in a crucial class imbalance problem. To address these problems, we propose a framework that combines a deep convolution generative adversarial network (DCGAN) with a support vector machine (SVM). The DCGAN is used as a sample generation and feature learning model, and the SVM is adopted as the classifier for predicting the label of a candidate at the inference stage. The proposed framework is a novel technique, which not only can solve the class imbalance problem but also can learn the discriminative feature representations of pulsar candidates instead of computing hand-crafted features in the pre-processing steps. The proposed method can enhance the accuracy of the APCI, and the computer experiments performed on two pulsar data sets verified the effectiveness and efficiency of the proposed method.