Imbalance Learning for Variable Star Classification

Abstract

The accurate automated classification of variable stars into their respective sub-types is difficult. Machine learning based solutions often fall foul of the imbalanced learning problem, which causes poor generalisation performance in practice, especially on rare variable star sub-types. 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 multi-class 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 under-represented classes. We apply and report results for three data augmentation methods in particular: $\text{R}$andomly $\text{A}$ugmented $\text{S}$ampled $\text{L}$ight curves from magnitude $\text{E}$rror ($\text{RASLE}$), augmenting light curves with Gaussian Process modelling ($\text{GpFit}$) and the Synthetic Minority Over-sampling Technique ($\text{SMOTE}$). 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$\%$. We found that a higher classification rate is obtained when using $\text{GpFit}$ 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.

11 pages, 8 figures, Accepted for publication in MNRAS

References in corpus (25)

• SMOTE: Synthetic Minority Over-sampling Technique
• Understanding the Lomb-Scargle Periodogram
• Kepler Mission Design, Realized Photometric Performance, and Early Science
• On Uncertainties in Cross-Correlation Lags and the Reality of Wavelength-Dependent Continuum Lags in Active Galactic Nuclei
• Photometric Supernova Classification With Machine Learning
• K2SC: Flexible systematics correction and detrending of K2 light curves using Gaussian Process regression
• Machine-Learned Identification of RR Lyrae Stars from Sparse, Multi-band Data: the PS1 Sample
• FETCH: A deep-learning based classifier for fast transient classification
• The Konkoly Blazhko Survey: Is light-curve modulation a common property of RRab stars?
• Machine Learning-based Brokers for Real-time Classification of the LSST Alert Stream
• A Package for the Automated Classification of Periodic Variable Stars
• 3FGL Demographics Outside the Galactic Plane using Supervised Machine Learning: Pulsar and Dark Matter Subhalo Interpretations
• Machine learning search for variable stars
• Overtone and multi-mode RR Lyrae stars in the globular cluster M3
• STACCATO: A Novel Solution to Supernova Photometric Classification with Biased Training Sets
• Data augmentation for machine learning redshifts applied to SDSS galaxies
• Comparing Multi-class, Binary and Hierarchical Machine Learning Classification schemes for variable stars
• Deep Neural Network Classifier for Variable Stars with Novelty Detection Capability
• Automatic Survey-Invariant Variable Star Classification
• The High Cadence Transient Survey (HITS): Compilation and characterization of light-curve catalogs
• Blazhko Effect in the first overtone RR Lyrae stars of the OGLE Galactic bulge collection
• Modeling Light Curves for Improved Classification
• Uncertain classification of Variable Stars: handling observational GAPS and noise
• Streaming Classification of Variable Stars
• Photometric light curves classification with machine learning

Cited by in corpus (18)

• Alert Classification for the ALeRCE Broker System: The Light Curve Classifier
• Data mining techniques on astronomical spectra data. II : Classification Analysis
• Classifying Kepler light curves for 12,000 A and F stars using supervised feature-based machine learning
• Light curve classification with recurrent neural networks for GOTO: dealing with imbalanced data
• Predicting machine failures from multivariate time series: an industrial case study
• Deep Attention-Based Supernovae Classification of Multi-Band Light-Curves
• Modelling the Multiwavelength Variability of Mrk 335 using Gaussian Processes
• MeerCRAB: MeerLICHT Classification of Real and Bogus Transients using Deep Learning
• Discovery of five new Galactic symbiotic stars in the VPHAS+ survey
• Periodic Variable Star Classification with Deep Learning: Handling Data Imbalance in an Ensemble Augmentation Way
• Semi-Supervised Classification and Clustering Analysis for Variable Stars
• Automatic Catalog of RRLyrae from $\sim$ 14 million VVV Light Curves: How far can we go with traditional machine-learning?
• Benchmark of Data Preprocessing Methods for Imbalanced Classification
• Real-time Light Curve Classification Framework for the Wide Field Survey Telescope Using Modified Semi-supervised Variational Auto-Encoder
• A search for new symbiotic stars in the Milky Way: Using machine learning techniques applied to photometric databases
• Automated all-sky detection of γ Doradus / δ Scuti hybrids in TESS data from positive unlabelled (PU) learning
• Drifting Features: Detection and evaluation in the context of automatic RRLs identification in VVV
• Photometric Redshift Estimation with Convolutional Neural Networks and Galaxy Images: A Case Study of Resolving Biases in Data-Driven Methods