| 基于卷积神经网络的快速射电暴候选体分类 |
| |
| 引用本文： | 刘艳玲,陈卯蒸,李健,闫浩,袁建平.基于卷积神经网络的快速射电暴候选体分类[J].天文学报,2022,63(4):48-116. |
| |
| 作者姓名： | 刘艳玲 陈卯蒸 李健 闫浩 袁建平 |
| |
| 作者单位： | 1. 中国科学院新疆天文台;2. 中国科学院大学;3. 中国科学院射电天文重点实验室 |
| |
| 基金项目： | 国家自然科学基金项目(11903071)； |
| |
| 摘 要： | 针对目前从海量的快速射电暴(Fast Radio Burst, FRB)候选体中人工筛选FRB事件难以为继的现状,提出了一种基于卷积神经网络(Convolutional Neural Networks, CNN)的FRB候选体分类方法.首先,通过真实的观测数据和仿真FRB组成训练和测试样本集.其次,建立了二输入的深度卷积神经网络模型,并对其进行训练、测试和优化,获取FRB候选体分类器.最后,利用来自脉冲星的单脉冲数据对该分类器的有效性和性能进行了验证.实验结果表明,该方法可以快速从大量候选体中准确识别出单脉冲事件,极大地提高了FRB候选体的处理速率和效率.
|
| 关 键 词： | 射电连续谱:暂现源 方法:数据分析 方法:分类 |
| 收稿时间： | 2021/10/8 0:00:00 |
Fast Radio Burst Candidate Classification with Convolutional Neural Networks |
| |
| LIU Yan-ling,CHEN Mao-zheng,LI Jian,YAN Hao,YUAN Jian-ping.Fast Radio Burst Candidate Classification with Convolutional Neural Networks[J].Acta Astronomica Sinica,2022,63(4):48-116. |
| |
| Authors: | LIU Yan-ling CHEN Mao-zheng LI Jian YAN Hao YUAN Jian-ping |
| |
| Institution: | Xinjiang Astronomical Observatory, Chinese Academy of Sciences, Urumqi 830011;University of Chinese Academy of Sciences, Beijing 100049;Key Laboratory of Radio Astronomy, Chinese Academy of Sciences, Nanjing 210023;Xinjiang Key Laboratory of Microwave Technology, Urumqi 830011;Xinjiang Astronomical Observatory, Chinese Academy of Sciences, Urumqi 830011;Key Laboratory of Radio Astronomy, Chinese Academy of Sciences, Nanjing 210023;Xinjiang Key Laboratory of Microwave Technology, Urumqi 830011 |
| |
| Abstract: | Manually identifying fast radio burst (FRB) events from the massive candidates by a human is a laborious and time-consuming task. It''s an unsustainable working mode for the constantly growing volume of observation data. In this paper, we present a method of FRB candidates classification based on convolutional neural networks (CNN). First, we build training and test sets with real observation data and simulated FRBs. Second, a two-input deep convolutional neural network model is constructed, trained and optimized, and the FRB candidate classifier is obtained. Then, the effectiveness and performance of the classifier are tested and verified by using single pulses from pulsar. Experiment results show that this method can quickly and accurately identify single pulse events from candidates, which greatly improves the processing speed and efficiency of FRB candidates. |
| |
| Keywords: | radio continuum: transients methods: data analysis methods: classification |
|
| 点击此处可从《天文学报》浏览原始摘要信息 |
| 点击此处可从《天文学报》下载免费的PDF全文 |
|
