Supervised Star Classification System for the OMC Archive

Entropy

This paper analyzes and compares the sensitivity and suitability of several artificial intelligence techniques applied to the Morgan–Keenan (MK) system for the classification of stars. The MK system is based on a sequence of spectral prototypes that allows classifying stars according to their effective temperature and luminosity through the study of their optical stellar spectra. Here, we include the method description and the results achieved by the different intelligent models developed thus far in our ongoing stellar classification project: fuzzy knowledge-based systems, backpropagation, radial basis function (RBF) and Kohonen artificial neural networks. Since one of today’s major challenges in this area of astrophysics is the exploitation of large terrestrial and space databases, we propose a final hybrid system that integrates the best intelligent techniques, automatically collects the most important spectral features, and determines the spectral type and luminosity level of th...

Proceedings of the 6th …, 2007

ALEJANDRA RODRIGUEZ Univ. of A Coru˜na Dep. of Infor. and Comm. Tech. Campus de Elvi˜na s/n, A Coru˜na SPAIN ... ICIAR CARRICAJO Univ. of A Coru˜na Dep. of Nav. and Earth Sciences Campus de Riazor s/n, A Coru˜na SPAIN ... CARLOS DAFONTE Univ. of A ...

Context. The Vista Variables in the Vía Láctea (VVV) ESO Public Survey is a variability survey of the Milky Way bulge and an adjacent section of the disk carried out from 2010 on ESO Visible and Infrared Survey Telescope for Astronomy (VISTA). The VVV survey will eventually deliver a deep near-IR atlas with photometry and positions in five passbands (ZYJHKS) and a catalogue of 1-10 million variable point sources - mostly unknown - that require classifications. Aims: The main goal of the VVV Templates Project, which we introduce in this work, is to develop and test the machine-learning algorithms for the automated classification of the VVV light-curves. As VVV is the first massive, multi-epoch survey of stellar variability in the near-IR, the template light-curves that are required for training the classification algorithms are not available. In the first paper of the series we describe the construction of this comprehensive database of infrared stellar variability. Methods: First, we performed a systematic search in the literature and public data archives; second, we coordinated a worldwide observational campaign; and third, we exploited the VVV variability database itself on (optically) well-known stars to gather high-quality infrared light-curves of several hundreds of variable stars. Results: We have now collected a significant (and still increasing) number of infrared template light-curves. This database will be used as a training-set for the machine-learning algorithms that will automatically classify the light-curves produced by VVV. The results of such an automated classification will be covered in forthcoming papers of the series.

Proceedings of the 2017 ACM on International Conference on Multimedia Retrieval, 2017

Although scarce, previous work on the application of machine learning and data mining techniques on large corpora of astronomical data has produced promising results. For example, on the task of detecting so-called Kepler objects of interest (KOIs), a range of di erent 'o the shelf' classi ers has demonstrated outstanding performance. ese rather preliminary research e orts motivate further exploration of this data domain. In the present work we focus on the analysis of threshold crossing events (TCEs) extracted from photometric data acquired by the Kepler spacecra. We show that the task of classifying TCEs as being e ected by actual planetary transits as opposed to confounding astrophysical phenomena is signi cantly more challenging than that of KOI detection, with di erent classi ers exhibiting vastly di erent performances. Nevertheless, the best performing classi er type, the random forest, achieved excellent accuracy, correctly predicting in approximately 96% of the cases. Our results and analysis should illuminate further e orts into the development of more sophisticated, automatic techniques, and encourage additional work in the area.

Astronomy and Computing, 2018

Machine learning algorithms are highly useful for the classification of time series data in astronomy in this era of peta-scale public survey data releases. These methods can facilitate the discovery of new unknown events in most astrophysical areas, as well as improving the analysis of samples of known phenomena. Machine learning algorithms use features extracted from collected data as input predictive variables. A public tool called Feature Analysis for Time Series (FATS) has proved an excellent workhorse for feature extraction, particularly light curve classification for variable objects. In this study, we present a major improvement to FATS, which corrects inconvenient design choices, minor details, and documentation for the re-engineering process. This improvement comprises a new Python package called feets, which is important for future code-refactoring for astronomical software tools.

arXiv: Astrophysics of Galaxies, 2019

We present a star/galaxy classification for the Southern Photometric Local Universe Survey (S-PLUS), based on a Machine Learning approach: the Random Forest algorithm. We train the algorithm using the S-PLUS optical photometry up to $r$=21, matched to SDSS/DR13, and morphological parameters. The metric of importance is defined as the relative decrease of the initial accuracy when all correlations related to a certain feature is vanished. In general, the broad photometric bands presented higher importance when compared to narrow ones. The influence of the morphological parameters has been evaluated training the RF with and without the inclusion of morphological parameters, presenting accuracy values of 95.0\% and 88.1\%, respectively. Particularly, the morphological parameter {\rm FWHM/PSF} performed the highest importance over all features to distinguish between stars and galaxies, indicating that it is crucial to classify objects into stars and galaxies. We investigate the misclass...

2017

The classification of point source objects into stars and galaxies largely depends on spectrographic surveys, which are expensive and time-consuming. This paper attempts to estimate, with a considerable accuracy, the possibility to classify these objects using only photometric data. Various machine learning algorithms are used to determine correlation, if any, between the properties of an object and photometric parameters. The focus is on the pre-processing of data to generate the most accurate predicting feature. Indepth analysis is performed for the respective model to determine the reason to give the most accurate fit. Efficient implementation of various machine learning algorithms, representing different mathematical models is done and the performance of the same is measured and compared against each other, based on accuracy and confusion matrix.

Emerging Technologies in Data Mining and Information Security, 2018

We present the results of various automated classification methods, based on machine learning (ML), of objects from data releases 6 and 7 (DR6 and DR7) of the Sloan Digital Sky Survey (SDSS), primarily distinguishing stars from quasars. We provide a careful scrutiny of approaches available in the literature and have highlighted the pitfalls in those approaches based on the nature of data used for the study. The aim is to investigate the appropriateness of the application of certain ML methods. The manuscript argues convincingly in favor of the efficacy of asymmetric AdaBoost to classify photometric data. The paper presents a critical review of existing study and puts forward an application of asymmetric AdaBoost, as an offspring of that exercise.

Lecture Notes in Computer Science, 2016

Modern time-domain astronomy is capable of collecting a staggeringly large amount of data on millions of objects in real time. This makes it almost impossible for objects to be identified manually. Therefore the production of methods and systems for the automated classification of time-domain astronomical objects is of great importance. The Liverpool Telescope has a number of wide-field image gathering instruments mounted upon its structure. Utilizing a database established by a pre-processing operation upon these images, containing millions of candidate variable stars with multiple time-varying magnitude observations, we applied a method designed to extract time-translation invariant features from the time-series light curves. These efforts were met with limited success due to noise and uneven sampling within the time-series data. Additionally, finely surveying these light curves is a processing intensive task. Fortunately, these algorithms are capable of multi-threaded implementations based on available resources. Therefore we propose a new system designed to utilize multiple intelligent agents that distribute the data analysis across multiple machines whilst simultaneously a powerful intelligence service operates to constrain the light curves and eliminate false signals due to noise and local alias periods.

Electronic Workshops in Computing, 2004

In this work we present ongoing lines of research carried out by the Group of Operations and Archives at LAEFF (Laboratory for Space Astrophysics and Fundamental Physics) in order to provide "intelligent" tools for the scientific exploitation of the astronomical archive data provided by its Scientific Data Center. We focus here in the problems of detecting non periodic variability and classifying periodic light curves in the ever increasing archive of the Optical Moniting Camera (hereafter OMC) on board INTEGRAL.