The EPOCH (EROS-2 periodic variable star classification using machine learning) project aims to detect periodic variable stars in the EROS-2 light curve database. In this paper, we present the first result of the classification of periodic variable s
tars in the EROS-2 LMC database. To classify these variables, we first built a training set by compiling known variables in the Large Magellanic Cloud area from the OGLE and MACHO surveys. We crossmatched these variables with the EROS-2 sources and extracted 22 variability features from 28 392 light curves of the corresponding EROS-2 sources. We then used the random forest method to classify the EROS-2 sources in the training set. We designed the model to separate not only $delta$ Scuti stars, RR Lyraes, Cepheids, eclipsing binaries, and long-period variables, the superclasses, but also their subclasses, such as RRab, RRc, RRd, and RRe for RR Lyraes, and similarly for the other variable types. The model trained using only the superclasses shows 99% recall and precision, while the model trained on all subclasses shows 87% recall and precision. We applied the trained model to the entire EROS-2 LMC database, which contains about 29 million sources, and found 117 234 periodic variable candidates. Out of these 117 234 periodic variables, 55 285 have not been discovered by either OGLE or MACHO variability studies. This set comprises 1 906 $delta$ Scuti stars, 6 607 RR Lyraes, 638 Cepheids, 178 Type II Cepheids, 34 562 eclipsing binaries, and 11 394 long-period variables. A catalog of these EROS-2 LMC periodic variable stars will be available online at http://stardb.yonsei.ac.kr and at the CDS website (http://vizier.u-strasbg.fr/viz-bin/VizieR).
We present a new QSO selection algorithm using a Support Vector Machine (SVM), a supervised classification method, on a set of extracted times series features including period, amplitude, color, and autocorrelation value. We train a model that separa
tes QSOs from variable stars, non-variable stars and microlensing events using 58 known QSOs, 1,629 variable stars and 4,288 non-variables using the MAssive Compact Halo Object (MACHO) database as a training set. To estimate the efficiency and the accuracy of the model, we perform a cross-validation test using the training set. The test shows that the model correctly identifies ~80% of known QSOs with a 25% false positive rate. The majority of the false positives are Be stars. We applied the trained model to the MACHO Large Magellanic Cloud (LMC) dataset, which consists of 40 million lightcurves, and found 1,620 QSO candidates. During the selection none of the 33,242 known MACHO variables were misclassified as QSO candidates. In order to estimate the true false positive rate, we crossmatched the candidates with astronomical catalogs including the Spitzer Surveying the Agents of a Galaxys Evolution (SAGE) LMC catalog and a few X-ray catalogs. The results further suggest that the majority of the candidates, more than 70%, are QSOs.
We analyzed data accumulated during 2005 and 2006 by the Taiwan-American Occultation Survey (TAOS) in order to detect short-period variable stars (periods of <~ 1 hour) such as delta Scuti. TAOS is designed for the detection of stellar occultation by
small-size Kuiper Belt Objects (KBOs) and is operating four 50cm telescopes at an effective cadence of 5Hz. The four telescopes simultaneously monitor the same patch of the sky in order to reduce false positives. To detect short-period variables, we used the Fast Fourier Transform algorithm (FFT) inasmuch as the data points in TAOS light-curves are evenly spaced. Using FFT, we found 41 short-period variables with amplitudes smaller than a few hundredths of a magnitude and periods of about an hour, which suggest that they are low-amplitude delta Scuti stars (LADS). The light-curves of TAOS delta Scuti stars are accessible online at the Time Series Center website (http://timemachine.iic.harvard.edu)
We present a de-trending algorithm for the removal of trends in time series. Trends in time series could be caused by various systematic and random noise sources such as cloud passages, changes of airmass, telescope vibration or CCD noise. Those tren
ds undermine the intrinsic signals of stars and should be removed. We determine the trends from subsets of stars that are highly correlated among themselves. These subsets are selected based on a hierarchical tree clustering algorithm. A bottom-up merging algorithm based on the departure from normal distribution in the correlation is developed to identify subsets, which we call clusters. After identification of clusters, we determine a trend per cluster by weighted sum of normalized light-curves. We then use quadratic programming to de-trend all individual light-curves based on these determined trends. Experimental results with synthetic light-curves containing artificial trends and events are presented. Results from other de-trending methods are also compared. The developed algorithm can be applied to time series for trend removal in both narrow and wide field astronomy.
