Go to the content. | Move to the navigation | Go to the site search | Go to the menu | Contacts | Accessibility

| Create Account

John, Prince (2018) Finite Dirichlet mixture models for classification and detection of new classes of variable stars. [Ph.D. thesis]

Full text disponibile come:

[img]
Preview
PDF Document
7Mb

Abstract (english)

The data that is being acquired by the Gaia space mission will allow us to compile a catalog of one billion stars. In the backdrop of this huge influx of data, it is crucial to have an efficient classification model. The aim of this thesis is, in particular, to develop appropriate models for the classification of variable stars based on the data that will be provided by the Gaia space survey.
The first contribution of the thesis is the development of a two-stage classification model, the Two Stage Dirichlet Mixture model (TSDM), based on finite mixtures of Dirichlet distributions. We validated this model on a well-studied subgroup of variable stars in the Hipparcos catalog analo- gously to what done by Dubath et al. (2011). We also propose two different transformations of the attributes used for the classification, which allow us to use the Dirichlet distribution whose support is a simplex. The adequacy of these transformations was evaluated with the selected data, highlighting an ability to correctly classify variable stars of 69.3%.
Secondly, we introduced an extension of the TSDM model, called the fixed backdrop (FB) model, whose purpose is to identify new variable star classes. Our proposal is based on the semi-supervised classification model developed by Vatanen et al. (2012) for the identification of anomalies. The FB model, in particular, combines the TSDM model, used to represent the already known classes (the so-called background), with a finite mixture of Dirichlet distributions which represent the new class. We have looked at the proposed model assuming a scenario in which the Beta Cephei (BCEP) class is the anomaly, achieving a sensitivity of 77%.
The third contribution of the thesis is the feasibility study for a Bayesian supervised variable stars classification using finite mixture of Dirichlet distributions. In particular, we propose a possible a priori conjugate distribution to the model.

Abstract (italian)

I dati che saranno acquisiti dalla missione spaziale Gaia consentiranno di compilare un catalogo contenente circa un miliardo di stelle. Alla luce di questo enorme afflusso di dati, è cruciale poter disporre di un modello di classificazione efficiente. L’obiettivo di questa tesi, in particolare, è sviluppare dei modelli adeguati per la classificazione delle stelle variabili in base ai dati che saranno forniti dalla missione spaziale Gaia.
Il primo contributo della tesi è lo sviluppo di un modello di classificazione a due stadi, detto modello Two Stage Dirichlet Mixture (TSDM), basato su delle misture finite di distribuzioni Dirichlet. Abbiamo validato questo modello su un sottogruppo ben studiato di stelle variabili riportate nel catalogo Hipparcos in analogia a quanto fatto da Dubath et al. (2011). Proponiamo, inoltre, due diverse trasformazioni delle caratteristiche utilizzate per la classificazione, che ci consentono di utilizzare per l’appunto la distribuzione di Dirichlet il cui supporto è un simplesso. L’adeguatezza di queste trasformazioni è stata vagliata con i dati selezionati, evidenziando una capacità di corretta classificazione delle stelle variabili considerate del 69.3%.
In secondo luogo, abbiamo introdotto un’estensione del modello TSDM, detta modello a sfondo fisso (FB), il cui scopo è identificare nuove classi di stelle variabili. La nostra proposta si basa sul modello per la classificazione semi supervisionata sviluppato da Vatanen et al. (2012) per l’identificazione di anomalie. Il modello FB, in particolare, combina il modello TSDM, usato per rappresentare le classi già note (il cosiddetto sfondo), con una mistura finita di distribuzioni di Dirichlet che rappresenta la nuova classe. Abbiamo vagliato il modello proposto assumendo uno scenario in cui la classe Beta Cephei (BCEP) rappresenta l’anomalia, conseguendo una sensibilità del 77%.
il terzo contributo della tesi valuta la fattiblità di una classificazione di stelle Bayesiana supervisionata tramite l’utilizzo di misture di distribuzioni di Dirichlet. In particolare, proponiamo una possibile distribuzione a priori coniugata per il modello.

Statistiche Download
EPrint type:Ph.D. thesis
Tutor:Brazzale, Alessandra Rosalba
Supervisor:Süveges, Maria
Ph.D. course:Ciclo 30 > Corsi 30 > SCIENZE STATISTICHE
Data di deposito della tesi:16 February 2018
Anno di Pubblicazione:16 February 2018
Key Words:variable stars, mixture models, Dirichlet distribution, supervised classification, unsupervised classification, new class detection,
Settori scientifico-disciplinari MIUR:Area 01 - Scienze matematiche e informatiche > MAT/06 Probabilità e statistica matematica
Struttura di riferimento:Dipartimenti > Dipartimento di Scienze Statistiche
Codice ID:11141
Depositato il:26 Oct 2018 09:56
Simple Metadata
Full Metadata
EndNote Format

Bibliografia

I riferimenti della bibliografia possono essere cercati con Cerca la citazione di AIRE, copiando il titolo dell'articolo (o del libro) e la rivista (se presente) nei campi appositi di "Cerca la Citazione di AIRE".
Le url contenute in alcuni riferimenti sono raggiungibili cliccando sul link alla fine della citazione (Vai!) e tramite Google (Ricerca con Google). Il risultato dipende dalla formattazione della citazione.

Aerts, C., Christensen-Dalsgaard, J., and Kurtz, D. W. (2010). Asteroseis- mology. Springer Science & Business Media. Cerca con Google

Aerts, C., Eyer, L., and Kestens, E. (1998). The discovery of new gamma doradus stars from the hipparcos mission. Astronomy and Astrophysics, 337:790–796. Cerca con Google

Akerlof, C., Amrose, S., Balsano, R., Bloch, J., Casperson, D., Fletcher, S., Gisler, G., Hills, J., Kehoe, R., Lee, B., et al. (2000). Rotse all-sky surveys for variable stars. i. test fields. The Astronomical Journal, 119(4):1901. Cerca con Google

Belokurov, V., Evans, N. W., and Du, Y. L. (2003). Light-curve classification in massive variability surveys—i. microlensing. Monthly Notices of the Royal Astronomical Society, 341(4):1373–1384. Cerca con Google

Belokurov, V., Evans, N. W., and Le Du, Y. (2004). Light-curve classification in massive variability surveys–ii. transients towards the large magellanic cloud. Monthly Notices of the Royal Astronomical Society, 352(1):233–242. Cerca con Google

Bernardo, J. and Girón, F. (1988). A bayesian analysis of simple mixture problems. Bayesian statistics, 3(3):67–78. Cerca con Google

Blomme, J., Debosscher, J., De Ridder, J., Aerts, C., Gilliland, R. L., Christensen-Dalsgaard, J., Kjeldsen, H., Brown, T. M., Borucki, W. J., Koch, D., et al. (2010). Automated classification of variable stars in the asteroseismology program of the kepler space mission. The Astrophysical Journal Letters, 713(2):L204. Cerca con Google

Blomme, J., Sarro, L., O’Donovan, F., Debosscher, J., Brown, T., Lopez, M., Dubath, P., Rimoldini, L., Charbonneau, D., Dunham, E., et al. (2011). Improved methodology for the automated classification of periodic variable stars. Monthly Notices of the Royal Astronomical Society, 418(1):96–106. Cerca con Google

Boldi, M.-O. (2004). Mixture models for multivariate extremes. Cerca con Google

Thèse École polytechnique fédérale de Lausanne EPFL, n. 3098, Section de mathématiques, Faculté des sciences de base, Institut de mathématiques, Chaire de statistique, page URL: https://infoscience.epfl.ch/record/33567. Vai! Cerca con Google

Breiman, L. (2001). Random forests. Machine learning, 45(1):5–32. Cerca con Google

Castellani, V., Degl’Innocenti, S., and Fiorentini, G. (1993). The pp reaction in the sun and solar neutrinos. Physics Letters B, 303(1-2):68–74. Cerca con Google

Catelan, M., Pritzl, B. J., and Smith, H. A. (2004). The rr lyrae period- luminosity relation. i. theoretical calibration. The Astrophysical Journal Supplement Series, 154(2):633. Cerca con Google

Debosscher, J., Sarro, L., Aerts, C., Cuypers, J., Vandenbussche, B., Garrido, R., and Solano, E. (2007). Automated supervised classification of variable stars-i. methodology. Astronomy & Astrophysics, 475(3):1159– 1183. Cerca con Google

Debosscher, J., Sarro, L., López, M., Deleuil, M., Aerts, C., Auvergne, M., Baglin, A., Baudin, F., Chadid, M., Charpinet, S., et al. (2009). Automated supervised classification of variable stars in the corot programme-method and application to the first four exoplanet fields. Astronomy & Astrophysics, 506(1):519–534. Cerca con Google

Deleuil, M., Meunier, J., Moutou, C., Surace, C., Deeg, H., Barbieri, M., Debosscher, J., Almenara, J., Agneray, F., Granet, Y., et al. (2009). Exodat: an information system in support of the corot/exoplanet science. The Astronomical Journal, 138(2):649. Cerca con Google

Diaconis, P., Ylvisaker, D., et al. (1979). Conjugate priors for exponential families. The Annals of statistics, 7(2):269–281. Cerca con Google

Drake, A., Graham, M., Djorgovski, S., Catelan, M., Mahabal, A., Torrealba, G., Garcia-Alvarez, D., Donalek, C., Prieto, J., Williams, R., et al. (2014). The catalina surveys periodic variable star catalog. Astrophysical Journal Supplement Series, 213(1):Art–No. Cerca con Google

Dubath, P., Rimoldini, L., Süveges, M., Blomme, J., López, M., Sarro, L., De Ridder, J., Cuypers, J., Guy, L., Lecoeur, I., et al. (2011). Random forest automated supervised classification of hipparcos periodic variable stars. Monthly Notices of the Royal Astronomical Society, 414(3):2602– 2617. Cerca con Google

Eker, Z., Filiz-Ak, N., Bilir, S., Dogru, D., Tuysuz, M., Soydugan, E., Bakis, H., Ugras, B., Soydugan, F., Erdem, A., et al. (2008). Vizier online data catalog: Chromospherically active binaries. third version (eker+, 2008). VizieR Online Data Catalog, 5128:0. Cerca con Google

Embrechts, P., Lindskog, F., and McNeil, A. (2001). Modelling dependence with copulas. Rapport technique, Département de mathématiques, Institut Fédéral de Technologie de Zurich, Zurich. Cerca con Google

Eyer, L. and Blake, C. (2002). Automated classification of variable stars for asas data. In IAU Colloq. 185: Radial and Nonradial Pulsationsn as Probes of Stellar Physics, volume 259, page 160. Cerca con Google

Eyer, L. and Blake, C. (2005). Automated classification of variable stars for all-sky automated survey 1–2 data. Monthly Notices of the Royal Astronomical Society, 358(1):30–38. Cerca con Google

Eyer, L. and Cuypers, J. (2000). Predictions on the number of variable stars for the gaia space mission and for surveys such as the ground-based international liquid mirror telescope. In International Astronomical Union Colloquium, volume 176, pages 71–72. Cambridge University Press. Cerca con Google

Feast, M. and Walker, A. (1987). Cepheids as distance indicators. Annual review of astronomy and astrophysics, 25(1):345–375. Cerca con Google

Friedman, J., Hastie, T., and Tibshirani, R. (2001). The elements of statistical learning, volume 1. Springer series in statistics Springer, Berlin. Cerca con Google

Frühwirth-Schnatter, S. (2006). Finite mixture and Markov switching models. Springer Science & Business Media. Cerca con Google

Furness, C. E. (1915). An Introduction to the Study of Variable Stars. Houghton Mifflin. Cerca con Google

Gautschy, A. and Saio, H. (1996). Stellar pulsations across the hr diagram: Part ii. Annual Review of Astronomy and Astrophysics, 34(1):551–606. Cerca con Google

Ghahramani, Z. and Beal, M. J. (2000). Variational inference for bayesian mixtures of factor analysers. In Advances in neural information processing systems, pages 449–455. Cerca con Google

Gilman, C. (1978). John goodricke and his variable stars. Sky and Telescope, 56. Cerca con Google

Hopkins, J. (1976). Glossary of astronomy and astrophysics. Chicago, University of Chicago Press, 1976. 174 p. Cerca con Google

Hoskin, M. (1982). Stellar astronomy. historical studies. Chalfont, St. Giles: Science History Publication, 1982. Cerca con Google

Kim, D.-W., Protopapas, P., Bailer-Jones, C. A., Byun, Y.-I., Chang, S.-W., Marquette, J.-B., and Shin, M.-S. (2014). The epoch project-i. periodic variable stars in the eros-2 lmc database. Astronomy & Astrophysics, 566:A43. Cerca con Google

Leavitt, H. S. (1908). 1777 variables in the magellanic clouds. Annals of Harvard College Observatory, 60:87–108. Cerca con Google

Leavitt, H. S. and Pickering, E. C. (1912). Periods of 25 variable stars in the small magellanic cloud. Harvard College Observatory Circular, 173:1–3. Cerca con Google

Liaw, A. and Wiener, M. (2002). Classification and regression by random- forest. R News, 2(3):18–22. Cerca con Google

Markou, M. and Singh, S. (2003). Novelty detection: a review—part 1: statistical approaches. Signal processing, 83(12):2481–2497. Cerca con Google

McLachlan, G. and Peel, D. (2004). Finite mixture models. John Wiley & Sons. Cerca con Google

Minniti, D., Lucas, P., Emerson, J., Saito, R., Hempel, M., Pietrukowicz, P., Ahumada, A., Alonso, M., Alonso-Garcia, J., Arias, J. I., et al. (2010). Vista variables in the via lactea (vvv): The public eso near-ir variability survey of the milky way. New Astronomy, 15(5):433–443. Cerca con Google

Ng, K. W., Tian, G.L., and Tang, M.-L. (2011). Dirichlet and related distributions: Theory, methods and applications, volume 888. John Wiley & Sons. Cerca con Google

Percy, J. R. (2007). Understanding variable stars. Cambridge University Press. Cerca con Google

Perryman, M. (1997). Esa 1997, the hipparcos and tycho catalogues. astrometric and photometric star catalogues derived from the esa hipparcos space astrometry mission. ESA SP, 1200. Cerca con Google

Perryman, M. (2010). The Making of History’s Greatest Star Map. Springer Science & Business Media. Cerca con Google

Perryman, M. A., Lindegren, L., Kovalevsky, J., Hoeg, E., Bastian, U., Bernacca, P., Crézé, M., Donati, F., Grenon, M., Grewing, M., et al. (1997). The hipparcos catalogue. Astronomy and Astrophysics, 323. Cerca con Google

Pietrukowicz, P., Dziembowski, W. A., Latour, M., Angeloni, R., Poleski, R., di Mille, F., Soszynski, I., Udalski, A., Szymanski, M. K., Wyrzykowski, L., et al. (2017). Blue large-amplitude pulsators as a new class of variable stars. arXiv preprint arXiv:1706.07802. Cerca con Google

Pojmanski, G. (2002). The all sky automated survey. catalog of variable stars. i. 0 h-6 hquarter of the southern hemisphere. Acta Astronomica, 52:397–427. Cerca con Google

Pojmanski, G. (2003). The all sky automated survey. the catalog of variable stars. ii. 6ˆ h-12ˆ h quarter of the southern hemisphere. Acta Astronomica, 53:341–369. Cerca con Google

Pojmanski, G. (2004). The all sky automated survey. the catalog of variable stars. ii. 6h-12h quarter of the southern hemisphere. arXiv preprint astro-ph/0401125. Cerca con Google

Powell, R. (2006). Hertzsprung russell diagram. An Atlas of the Universe. Cerca con Google

Richards, J. W., Starr, D. L., Butler, N. R., Bloom, J. S., Brewer, J. M., Crellin-Quick, A., Higgins, J., Kennedy, R., and Rischard, M. (2011). On machine-learned classification of variable stars with sparse and noisy time-series data. The Astrophysical Journal, 733(1):10. Cerca con Google

Samus, N., Kazarovets, E., and Durlevich, O. (2017). General catalogue of variable stars. Odessa Astronomical Publications, 14:266–269. Cerca con Google

Sarro, L., Debosscher, J., López, M., and Aerts, C. (2009). Automated supervised classification of variable stars-ii. application to the ogle database. Astronomy & Astrophysics, 494(2):739–768. Cerca con Google

Sesar, B., Vivas, A. K., Duffau, S., and Ivezic ́, Ž. (2010). Halo velocity groups in the pisces overdensity. The Astrophysical Journal, 717(1):133. Cerca con Google

Steinfadt, J. D., Kaplan, D. L., Shporer, A., Bildsten, L., and Howell, S. B. (2010). Discovery of the eclipsing detached double white dwarf binary nltt 11748. The Astrophysical Journal Letters, 716(2):L146. Cerca con Google

Süveges, M., Barblan, F., Lecoeur-Taïbi, I., Prša, A., Holl, B., Eyer, L., Kochoska, A., Mowlavi, N., and Rimoldini, L. (2017). Gaia eclipsing binary and multiple systems. supervised classification and self-organizing maps. Astronomy & Astrophysics, 603:A117. Cerca con Google

Turon, C., Crézé, M., Egret, D., Gómez, A., Grenon, M., Jahreiß, H., Réquieme, Y., Argue, A., Bec-Borsenberger, A., Dommanget, J., et al. (1992). The hipparcos input catalogue. Bulletin d’Information du Centre de Donnees Stellaires, 41:9. Cerca con Google

Turon, C., Requieme, Y., Grenon, M., Gomez, A., Morin, D., Crifo, F., Arenou, F., Froeschle, M., Mignard, F., Perryman, M., et al. (1995). Properties of the hipparcos input catalogue. Astronomy and Astrophysics, 304:82. Cerca con Google

Udalski, A., Szyman ́ski, M., and Szyman ́ski, G. (2015). Ogle-iv: fourth phase of the optical gravitational lensing experiment. arXiv preprint arXiv:1504.05966. Cerca con Google

Unsöld, A. (1969). Colour-magnitude diagrams of galactic and globular clusters. stellar evolution and abundances of the elements. In The New Cosmos, pages 259–280. Springer. Cerca con Google

Vatanen, T., Kuusela, M., Malmi, E., Raiko, T., Aaltonen, T., and Nagai, Y. (2012). Semi-supervised detection of collective anomalies with an application in high energy particle physics. In Neural Networks (IJCNN), The 2012 International Joint Conference on, pages 1–8. IEEE. Cerca con Google

Watson, C., Henden, A., and Price, A. (2009). Vizier online data catalog: Aavso international variable star index vsx (watson+, 2009). VizieR Online Data Catalog, 1:02027. Cerca con Google

Willemsen, P. and Eyer, L. (2007). A study of supervised classification of hipparcos variable stars using pca and support vector machines. arXiv preprint arXiv:0712.2898. Cerca con Google

Williams, T. R. and Saladyga, M. (2011). Advancing variable star astronomy: The centennial history of the american association of variable star observers. Cambridge University Press. Cerca con Google

Download statistics

Solo per lo Staff dell Archivio: Modifica questo record