典型文献
Identifying Outliers in Astronomical Images with Unsupervised Machine Learning
文献摘要：
Astronomical outliers, such as unusual, rare or unknown types of astronomical objects or phenomena, constantly lead to the discovery of genuinely unforeseen knowledge in astronomy. More unpredictable outliers will be uncovered in principle with the increment of the coverage and quality of upcoming survey data. However, it is a severe challenge to mine rare and unexpected targets from enormous data with human inspection due to a significant workload. Supervised learning is also unsuitable for this purpose because designing proper training sets for unanticipated signals is unworkable. Motivated by these challenges, we adopt unsupervised machine learning approaches to identify outliers in the data of galaxy images to explore the paths for detecting astronomical outliers. For comparison, we construct three methods, which are built upon the k-nearest neighbors (KNN), Convolutional Auto-Encoder (CAE)+KNN, and CAE+KNN+Attention Mechanism (attCAE_KNN) separately. Testing sets are created based on the Galaxy Zoo image data published online to evaluate the performance of the above methods. Results show that attCAE_KNN achieves the best recall (78％), which is 53％higher than the classical KNN method and 22％higher than CAE+KNN. The efficiency of attCAE_KNN (10 minutes) is also superior to KNN (4 h) and equal to CAE+KNN (10 minutes) for accomplishing the same task. Thus, we believe that it is feasible to detect astronomical outliers in the data of galaxy images in an unsupervised manner. Next, we will apply attCAE_KNN to available survey data sets to assess its applicability and reliability.
文献关键词：
中图分类号：
作者姓名：
Yang Han;Zhiqiang Zou;Nan Li;Yanli Chen
作者机构：
School of Computer Science,Nanjing University of Posts and Telecommunications,Nanjing 210023,China;Jiangsu Key Laboratory of Big Data Security and Intelligent Processing,Nanjing 210023,China;Key Laboratory of Optical Astronomy,National Astronomical Observatories,Chinese Academy of Sciences,Beijing 100101,China;University of Chinese Academy of Sciences,Beijing 100049,China
文献出处：
引用格式：
[1]Yang Han;Zhiqiang Zou;Nan Li;Yanli Chen-.Identifying Outliers in Astronomical Images with Unsupervised Machine Learning)[J].天文和天体物理学研究,2022(08):74-84
A类：
Outliers,Astronomical,unworkable,+KNN,CAE+KNN+Attention,attCAE,CAE+KNN
B类：
Identifying,Images,Unsupervised,Machine,Learning,outliers,such,unusual,rare,unknown,types,astronomical,objects,phenomena,constantly,lead,discovery,genuinely,unforeseen,knowledge,astronomy,More,unpredictable,will,uncovered,principle,increment,coverage,quality,upcoming,survey,data,However,severe,mine,unexpected,targets,from,enormous,human,inspection,due,significant,workload,Supervised,learning,also,unsuitable,this,purpose,because,designing,proper,training,sets,unanticipated,signals,Motivated,by,these,challenges,adopt,unsupervised,machine,approaches,identify,galaxy,images,explore,paths,detecting,For,comparison,construct,three,methods,which,built,upon,nearest,neighbors,Convolutional,Auto,Encoder,Mechanism,separately,Testing,created,Galaxy,Zoo,published,online,evaluate,performance,above,Results,show,that,achieves,best,recall,higher,than,classical,efficiency,minutes,superior,equal,accomplishing,same,task,Thus,believe,feasible,manner,Next,apply,available,assess,its,applicability,reliability
AB值：
0.560379
相似文献
机标中图分类号，由域田数据科技根据网络公开资料自动分析生成，仅供学习研究参考。
