Optimizing Automated Classification of Variable Stars in New Synoptic Surveys
العنوان: | Optimizing Automated Classification of Variable Stars in New Synoptic Surveys |
---|---|
المؤلفون: | Joshua S. Bloom, James P. Long, John Rice, Noureddine El Karoui, Joseph W. Richards |
المصدر: | Publications of the Astronomical Society of the Pacific. 124:280-295 |
بيانات النشر: | IOP Publishing, 2012. |
سنة النشر: | 2012 |
مصطلحات موضوعية: | business.industry, Computer science, Feature vector, Astronomy and Astrophysics, Pattern recognition, Astronomical survey, Light curve, 01 natural sciences, 010104 statistics & probability, ComputingMethodologies_PATTERNRECOGNITION, Space and Planetary Science, 0103 physical sciences, Artificial intelligence, 0101 mathematics, Variable star, business, 010303 astronomy & astrophysics, Classifier (UML) |
الوصف: | Efficient and automated classification of periodic variable stars is becoming increasingly important as the scale of astronomical surveys grows. Several recent articles have used methods from machine learning and statistics to construct classifiers on databases of labeled, multi-epoch sources with the intention of using these classifiers to automatically infer the classes of unlabeled sources from new surveys. However, the same source observed with two different synoptic surveys will generally yield different derived metrics (features) from the light curve. Since such features are used in classifiers, this survey-dependent mismatch in feature space will typically lead to degraded classifier performance. In this article we show how and why feature distributions change using OGLE and Hipparcos light curves. To overcome survey systematics, we apply a noisification method, which attempts to empirically match distributions of features between the labeled sources used to construct the classifier and th... |
تدمد: | 1538-3873 0004-6280 |
URL الوصول: | https://explore.openaire.eu/search/publication?articleId=doi_________::897a75b6e1aa7d24fb6cb484e565610b https://doi.org/10.1086/664960 |
حقوق: | OPEN |
رقم الأكسشن: | edsair.doi...........897a75b6e1aa7d24fb6cb484e565610b |
قاعدة البيانات: | OpenAIRE |
تدمد: | 15383873 00046280 |
---|