Random forest automated supervised classification of Hipparcos periodic variable stars
By P. Dubath, L. Rimoldini, M. Suveges, J. Blomme, M. L'opez, L. Sarro, J. Ridder, J. Cuypers, L. Guy, I. Lecoeur and 7 more. 2011
153 citations recorded by the source corpus.
We present an evaluation of the performance of an automated classification of the Hipparcos periodic variable stars into 26 types. The sub-sample with the most reliable variability types available in the literature is used to train supervised algorithms to characterize the type dependencies on a number of attributes. The most useful attributes evaluated with the random forest methodology include, in decreasing order of importance, the period, the amplitude, the V − I colour index, the absolute magnitude, the residual around the folded light-curve model, the magnitude distribution skewness and the amplitude of the second harmonic of the Fourier series model relative to that of the fundamental frequency. Random forests and a multistage scheme involving Bayesian network and Gaussian mixture methods lead to statistically equivalent results. In standard 10-fold cross-validation (CV) experiments, the rate of correct classification is between 90 and 100 per cent, depending on the variability type. The main mis-classification cases, up to a rate of about 10 per cent, arise due to confusion between SPB and ACV blue variables and between eclipsing binaries, ellipsoidal variables and other variability types. Our training set and the predicted types for the other Hipparcos periodic stars are available online.
Subfields: Artificial Intelligence, Astronomy and Astrophysics
View Paper: https://www.semanticscholar.org/paper/5e88c9cbc4a697fdfefea085d7dc919ee8485e30
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Sergey E. Koposov
- V. Belokurov
- G. Torrealba
- Jalal Al-Tamimi
- Alice G. Laborte
- M. V. Lieshout
- Emmanuel John Muico Carranza
- Ottmar Cronie
In Astronomy and Astrophysics
- Jon M. Jenkins
- C. Burke
- Joseph D. Twicken
- V. Belokurov
- S. Seader
- P. Tenenbaum
- Jie Li
- Sergey E. Koposov
Citations in the corpus
- KEPLER ECLIPSING BINARY STARS. III. CLASSIFICATION OF KEPLER ECLIPSING BINARY LIGHT CURVES WITH LOCALLY LINEAR EMBEDDING (2012, background): “There have already been significant efforts focusing on the topic of automatic classification of variable star light curves (Eyer & Blake 2005; Sarro et al. 2006; Debosscher et al. 2007; Blomme et al. 2011; Dubath et al. 2011; Richards et al. 2011, among others).”
- THE CATALINA SURVEYS PERIODIC VARIABLE STAR CATALOG (2014, methodology): “In addition, we will apply Self-Organizing Maps and other machine learning techniques, similar to approaches that recently been applied to large sets of variable stars (e.g., Dubath et al. 2011; Blomme et al. 2011; Richards et al.”
- How Many Trees in a Random Forest? (2012, background): “Random Trees can be efficiently generated, and the combination of large sets of Random Trees generally lead to accurate models [35,10].”
- AUTOMATIC CLASSIFICATION OF KEPLER PLANETARY TRANSIT CANDIDATES (2014, background): “Random forests have been applied to a variety of classification problems; perhaps closest to this problem is that of classifying variable stars (Dubath et al.2011; Richards et al.2011).”