基于密度的Kepler数据异常值评分
Density Based Outlier Scoring on Kepler Data
摘要：
在当前大规模调查的时代，大数据对异常数据的发现过程提出了新的挑战。这样的数据可以指示系统误差、已知现象的极端（或罕见）形式，或者最有趣的是，表现出尚未观察到的行为的真正新颖的现象。在这项工作中，我们提出了一种离群值评分方法来识别和描述最有希望的不寻常来源，以促进此类异常数据的发现。我们开发了一种基于特征空间中k-近邻距离的数据挖掘方法，以有效地识别最异常的光变曲线。我们测试了这种方法的变化，包括使用特征空间的主成分，删除选择功能，选择k的影响，并对子集样本进行评分。我们评估了我们在已知对象类上的评分的概率，发现我们的评分始终对罕见（<1000）对象类的评分高于常见类。我们对开普勒主要任务的1至17季度的所有长节奏光变曲线进行了评分，并为大约20万个物体的所有280万光变曲线提供了离群值分数。
英文摘要：
In the present era of large scale surveys, big data presents new challenges to the discovery process for anomalous data. Such data can be indicative of systematic errors, extreme (or rare) forms of known phenomena, or most interestingly, truly novel phenomena which exhibit as-of-yet unobserved behaviors. In this work we present an outlier scoring methodology to identify and characterize the most promising unusual sources to facilitate discoveries of such anomalous data. We have developed a data mining method based on k-Nearest Neighbor distance in feature space to efficiently identify the most anomalous lightcurves. We test variations of this method including using principal components of the feature space, removing select features, the effect of the choice of k, and scoring to subset samples. We evaluate the peformance of our scoring on known object classes and find that our scoring consistently scores rare (<1000) object classes higher than common classes. We have applied scoring to all long cadence lightcurves of quarters 1 to 17 of Kepler's prime mission and present outlier scores for all 2.8 million lightcurves for the roughly 200k objects.
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。
