Comparing Multiclass, Binary, and Hierarchical Machine Learning Classification schemes for variable stars
Comparing Multiclass, Binary, and Hierarchical Machine Learning Classification schemes for variable stars
复制标题
DOI：
10.1093/mnras/stz1999
复制
发表时间：
2019-10-01
影响因子：
4.8
通讯作者：
Mootoovaloo, Arrykrishna
中科院分区：
文献类型：
--
作者：
Hosenie, Zafiirah;Lyon, Robert J.;Mootoovaloo, Arrykrishna
即将进行的天气调查将产生前所未有的数据量。这需要一个自动框架，可以快速有效地为几个新的对象分类挑战提供分类标签。使用数据描述11种类型的变星从卡塔利纳实时瞬态调查（CRTS），我们说明了如何捕捉最重要的信息，从计算的功能，并描述了详细的方法，如何稳健地使用信息理论的功能选择和评估。我们应用三种机器学习算法，并演示如何通过交叉验证技术优化这些分类器。对于CRTS数据集，我们发现随机森林分类器在平衡精度和几何平均值方面表现最好。我们展示了大幅改善的分类结果转换成一个二进制分类任务的多类问题，实现了类似于99%的三角洲盾牌和异常造父变星的分类的平衡准确率。此外，我们描述了如何通过将平面多类问题转换为层次分类来提高分类性能。我们开发了一个新的层次结构，并提出了一套新的分类功能，使准确识别的子类型的造父变星，RR天琴座，和食双星CRTS数据。
Upcoming synoptic surveys are set to generate an unprecedented amount of data. This requires an automatic framework that can quickly and efficiently provide classification labels for several new object classification challenges. Using data describing 11 types of variable stars from the Catalina Real-Time Transient Survey (CRTS), we illustrate how to capture the most important information from computed features and describe detailed methods of how to robustly use information theory for feature selection and evaluation. We apply three machine learning algorithms and demonstrate how to optimize these classifiers via cross-validation techniques. For the CRTS data set, we find that the random forest classifier performs best in terms of balanced accuracy and geometric means. We demonstrate substantially improved classification results by converting the multiclass problem into a binary classification task, achieving a balanced-accuracy rate of similar to 99percent for the classification of delta Scuti and anomalous Cepheids. Additionally, we describe how classification performance can be improved via converting a flat multiclass' problem into a hierarchical taxonomy. We develop a new hierarchical structure and propose a new set of classification features, enabling the accurate identification of subtypes of Cepheids, RRLyrae, and eclipsing binary stars in CRTS data.