| 本文已被：浏览 4989次 下载 1158次 |
码上扫一扫！ |
|
|
| 脉冲星候选样本分类方法综述 |
|
王元超1,2, 郑建华1,2, 潘之辰3,4,5, 李明涛1,2
|
|
1.中国科学院 国家空间科学中心, 北京 100190;2.中国科学院大学, 北京 100049;3.中国科学院 国家天文台, 北京 100012;4.中国科学院 天文大数据中心, 北京 100012;5.中国科学院FAST重点实验室, 北京 100012
|
|
| 摘要: |
| 脉冲星搜索是射电天文学中的重要前沿领域。随着现代搜索设备性能的不断提升，可以接收到更弱的信号，如何从海量信号中准确地识别出脉冲星疑似信号成为一个挑战。介绍了国内外关于脉冲星候选样本分类方法的发展历史和发展状态，归纳总结了发展过程中各个阶段的处理方法：人工识别方法和机器学习方法；最后对未来的发展趋势进行了分析。 |
| 关键词: 脉冲星 脉冲星候选样本 机器学习 |
| DOI：10.15982/j.issn.2095-7777.2018.3.001 |
| 分类号:P16 |
| 基金项目:中国科学院青年创新促进会优秀会员资助项目 |
|
| An Overview of Pulsar Candidate Classification Methods |
|
WANG Yuanchao1,2, ZHENG Jianhua1,2, PAN Zhichen3,4,5, LI Mingtao1,2
|
|
1.National Space Science Center, Chinese Academy of Sciences, Beijing 100190;2.University of Chinese Academy of Sciences, Beijing 100049;3.National Astronomical Observatories, Chinese Academy of Sciences, Beijing 100012;4.Center for Astronomical Mega-Science, Chinese Academy of Sciences, Beijing 100012;5.CAS Key Laboratory of FAST, NAOC, Chinese Academy of Sciences, Beijing 100012
|
| Abstract: |
| Pulsar searching is an important frontier in radio astronomy. Weaker signals can be received as the performance of search facilities continualy improved. However,how to accurately identify the suspected pulsar signal from massive candidates has become a challenge. The pulsar candidate classification methods about development history and current situation at home and abroad. The classification methods in each stage include:manual selection methods and machine learning methods. At last,the future development trends are analyzed. |
| Key words: pulsar pulsar candidate machine learning |