自动化学报2017，Vol.43Issue(12)：2170-2177,8.DOI:10.16383/j.aas.2017.c160289
天文瞬变源快速自动识别系统的研究与实现
Study and Development of a Fast and Automatic Astronomical-transient-identification System
摘要
Abstract
With the development of observational technology, modern transient survey projects are required to select the transient candidates fast and automatically from large volume data with noise. We present a fast and automatic identification system to search transients by the following methods: introducing 13 new features to measure objects'profiles by isophotometry in the place of PSF fit,using high simulation data based on real objects'profiles as training sample,and designing a special noise filter function. The identification system is realized by supervised machine learning technique of random forest. Our test demonstrates that the processing speed is 10 times faster than the popular identification system in the world,while their true and false positive rates are at the same level. Additionally,our system shows good performance for low signal-to-noise-ratio data due to its isophotometry's features. Our system has been successfully operating in the Mini-GWAC(Miniature ground wide angle camera)online data processing pipeline.关键词
机器学习/随机森林/瞬变源自动搜寻/星像轮廓/等光度测光Key words
Machine learning/random forest/robotic identification of transient/profile of star/isophotometry引用本文复制引用
吴潮,马冬,田海俊,李乡儒,魏建彦..天文瞬变源快速自动识别系统的研究与实现[J].自动化学报,2017,43(12):2170-2177,8.基金项目
国家自然科学基金(U1431108,U1231123,U1331202,61273248,11503012,U1731124),广东省自然科学基金(2014A030313425)资助Supported by National Natural Science Foundation of China(U1431108,U1231123,U1331202,61273248,11503012,U1731124)and Natural Science Foundation of Guangdong Province(2014A030313425) （U1431108,U1231123,U1331202,61273248,11503012,U1731124）
