arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2006.08238astro-ph.IM
收藏

天文图像数据异常检测方法的比较

Comparison of outlier detection methods on astronomical image data

Lars Doorenbos, Stefano Cavuoti, Massimo Brescia, Antonio D'Isanto, Giuseppe Longo

摘要:

在新一代天文仪器产生的巨大数据量所带来的许多挑战中,还有寻找稀有和特殊物体的挑战。无监督离群值检测算法可以提供可行的解决方案。在这项工作中,我们比较了六种方法的性能:局部离群值因子,隔离森林,k-means聚类,新颖性度量,以及正常和卷积自动编码器。这些方法适用于从SDSS条纹82中提取的数据。在讨论了每种方法对自己的超参数集的敏感性之后,我们将每种方法的结果结合起来对对象进行排名,并生成最终的离群值列表。

英文摘要:

Among the many challenges posed by the huge data volumes produced by the new generation of astronomical instruments there is also the search for rare and peculiar objects. Unsupervised outlier detection algorithms may provide a viable solution. In this work we compare the performances of six methods: the Local Outlier Factor, Isolation Forest, k-means clustering, a measure of novelty, and both a normal and a convolutional autoencoder. These methods were applied to data extracted from SDSS stripe 82. After discussing the sensitivity of each method to its own set of hyperparameters, we combine the results from each method to rank the objects and produce a final list of outliers.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑