基于机器学习的单脉冲候选体识别  

Single Pulse Candidate Identification Based on Machine Learning

作　　者：王春庆 游善平[1] 曾鹏 李宏伟 何兵 张鸿兵 刘子毅 WANG Chunqing;YOU Shanping;ZENG Peng;LI Hongwei;HE Bing;ZHANG Hongbing;LIU Ziyi(Guizhou Provincial Key Laboratory of Information and Computing Science,Guizhou Normal University,Guiyang,Guizhou 550001,China)

机构地区：[1]贵州师范大学贵州省信息与计算科学重点实验室,贵州贵阳550001

出　　处：《自动化应用》2024年第7期7-12,共6页Automation Application

基　　金：国家自然科学基金(U1631132,U183110134);贵州省科学技术基金(黔科合J字LKS[2010]38号)。

摘　　要：大规模射电天文巡天项目往往会产生海量数据,对其进行单脉冲搜索会得到数以亿计的单脉冲候选体信号,包含许多周期搜索无法找到的非周期性脉冲信号。500 m口径球面射电望远镜(FAST)多科学目标同时扫描巡天(CRAFTS)更会产生大量的数据,CRAFTS数据中信号量少,干扰其他无关信号多,逐一筛查耗时巨大,且现有AI模型对CRAFTS脉冲信号识别的准确率低。在FETCH的基础上,使用DenseNet121与Xception网络训练优化已有的模型,提高AI模型对弱信号识别率,降低干扰与脉冲信号同时存在时干扰对分类器的影响,并应用于单脉冲筛选流程。结果表明,使用DenseNet121与Xception网络训练优化模型,提高了对弱信号识别的准确率,并能在一定程度排除干扰的影响,在弱信号、干扰与信号并存的数据集中表现出77.78%的召回率、1.50%的假阳率及88.49%的准确率。Large scale radio astronomical surveys often generate massive amounts of data,and conducting single pulse searches on them will yield billions of single pulse candidate signals,including many non periodic pulse signals that cannot be found through periodic searches.The 500 m Aperture Spherical Radio Telescope(FAST)for simultaneous scanning of multiple scientific targets(CRAFTS)generates a large amount of data.CRAFTS data has less signal volume,interferes with other irrelevant signals,and takes a huge amount of time to screen one by one.In addition,existing AI models have low accuracy in identifying CRAFTS pulse signals.On the basis of FETCH,DenseNet121 and Xception networks are used to train and optimize existing models,improve the recognition rate of AI models for weak signals,reduce the impact of interference on classifiers when interference and pulse signals coexist,and apply them to the single pulse screening process.The results showed that using DenseNet121 and Xception networks to train optimization models improved the accuracy of weak signal recognition and to some extent eliminated the influence of interference.In datasets with weak signals,interference,and signals coexisting,it showed a recall rate of 77.78%,a false positive rate of 1.50%,and an accuracy rate of 88.49%.

关 键 词：单脉冲搜索 脉冲星 信噪比 机器学习 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程]