AUTOMATED VARIABLE STAR CLASSIFICATION USING THE NORTHERN SKY VARIABILITY SURVEY

ABSTRACT The accurate automated classification of variable stars into their respective subtypes is difficult. Machine learning–based solutions often fall foul of the imbalanced learning problem, which causes poor generalization performance in practice, especially on rare variable star subtypes. In previous work, we attempted to overcome such deficiencies via the development of a hierarchical machine learning classifier. This ‘algorithm-level’ approach to tackling imbalance yielded promising results on Catalina Real-Time Survey (CRTS) data, outperforming the binary and multiclass classification schemes previously applied in this area. In this work, we attempt to further improve hierarchical classification performance by applying ‘data-level’ approaches to directly augment the training data so that they better describe underrepresented classes. We apply and report results for three data augmentation methods in particular: Randomly Augmented Sampled Light curves from magnitude Error (RASLE), augmenting light curves with Gaussian Process modelling (GpFit) and the Synthetic Minority Oversampling Technique (SMOTE). When combining the ‘algorithm-level’ (i.e. the hierarchical scheme) together with the ‘data-level’ approach, we further improve variable star classification accuracy by 1–4 per cent. We found that a higher classification rate is obtained when using GpFit in the hierarchical model. Further improvement of the metric scores requires a better standard set of correctly identified variable stars, and perhaps enhanced features are needed.

Download Full-text

On the Inhomogeneity of Chemical Composition over the Surface of 21 Per

International Astronomical Union Colloquium ◽

10.1017/s0252921100080659 ◽

1976 ◽

Vol 32 ◽

pp. 343-349

Author(s):

Yu.V. Glagolevsky ◽

K.I. Kozlova ◽

V.S. Lebedev ◽

N.S. Polosukhina

Keyword(s):

Chemical Composition ◽

Spectral Line ◽

Variable Star ◽

Radial Velocities ◽

Crimean Astrophysical Observatory ◽

Line Intensities ◽

Magnetic Variable

SummaryThe magnetic variable star 21 Per has been studied from 4 and 8 Å/mm spectra obtained with the 2.6 - meter reflector of the Crimean Astrophysical Observatory. Spectral line intensities (Wλ) and radial velocities (Vr) have been measured.

Download Full-text

Production of New and Revised A.A.V.S.O. Charts

International Astronomical Union Colloquium ◽

10.1017/s0252921100073620 ◽

1979 ◽

Vol 46 ◽

pp. 368

Author(s):

Clinton B. Ford

Keyword(s):

Variable Star ◽

Standard Form ◽

Original Data ◽

University Of Pennsylvania ◽

Standard Format ◽

Additional Information ◽

The Gift ◽

The University

A “new charts program” for the Americal Association of Variable Star Observers was instigated in 1966 via the gift to the Association of the complete variable star observing records, charts, photographs, etc. of the late Prof. Charles P. Olivier of the University of Pennsylvania (USA). Adequate material covering about 60 variables, not previously charted by the AAVSO, was included in this original data, and was suitably charted in reproducible standard format.Since 1966, much additional information has been assembled from other sources, three Catalogs have been issued which list the new or revised charts produced, and which specify how copies of same may be obtained. The latest such Catalog is dated June 1978, and lists 670 different charts covering a total of 611 variables none of which was charted in reproducible standard form previous to 1966.

Download Full-text

Variable star

AccessScience ◽

10.1036/1097-8542.728000 ◽

2015 ◽

Keyword(s):

Variable Star

Download Full-text