DOI: https://doi.org/10.18524/1810-4215.2019.32.182538

VERIFICATION OF MACHINE LEARNING METHODS FOR BINARY MORPHOLOGICAL CLASSIFICATION OF GALAXIES FROM SDSS

M. Yu. Vasylenko, D. V. Dobrycheva, I. B. Vavilova, O. V. Melnyk, A. A. Elyiv

Анотація


We present a study on the verifica-
tion of Machine Learning methods to be applied for
binary morphological classification of galaxies. With
this aim we used the sample of 60561 galaxies from the
SDSSDR9 survey with a redshift of 0 . 02 < z < 0 . 06 and
absolute magnitudes of − 24 m < M r < − 19 . 4 m . We
applied the following classification methods using own
code in Python to predict correctly the morphology of
Late and Early galaxies: Naive Bayes, Random Forest,
Support Vector Machines, Logistic Regression, and k-
Nearest Neighbor algorithm. To study the classifier, we
used absolute magnitudes M u ,M g ,M r ,M i ,M z , color
indices M u − M r ,M g − M i ,M u − M g ,M r − M z , and
inverse concentration index to the center R50/R90.
We compared these new results with previous one
made with the KNIME Analytics Platform 3.5.3. It
turned out that Random Forest and Support Vector
Machine Classifiers provide a highest accuracy, as
in the previous study, but with help our code in
Python we increased an accuracy from 92.9 % of
correctly classified (96% – E and 84% – L ) to 94,6%
(96,9% – E and 89,7 % – L ). The accuracy of the
remaining methods also grew by 88% to 93%. So,
using these classifiers and the data on color indices,
absolute magnitudes, inverse concentration index of
galaxies with visual morphological types, we were able
to classify 60561 galaxies from the SDSSDR9 with
unknown morphological types and found 22301 E and
38260 L types among them.


Ключові слова


galaxies; morphological classification; machine learning

Повний текст:

PDF (English)

Посилання


Acero F., Ackermann M. et al.: 2015, ApJS, 218, 41.

Al-Jarrah O.Y., Yoo P.D., Muhaidat S. et al.: 2015, Efficient machine learning for big data: A review. Big Data Research, 2(3), 87.

Andrae R., Melchior P. et al.: 2010, A&A, 522, 19.

Banerji M., Lahav O. et al.: 2010, MNRAS, 406, 342.

Barchi P.H., de Carvalho R.R., Rosa R.R. et al.: 2019,

arXiv:1901.07047.

Blanton M.R., Bershady M.A., Abolfathi B. et al.: 2017, ApJ, 154, 35.

Braude S.Ya., Rashkovsky S.L., Sidorchuk K.M. et al.: 2002, Astrophysics and Space Science, 280, 235.

Burkov A.: 2019, The Hundred-Page Machine Learning Book.

Calderon V.F.; Berlind A.A.: 2019, arXiv:1902.02680.

Chilingarian I., Melchior A.L., Zolotukhin I.: 2010, MNRAS, 405, 1409.

Chilingarian I., Zolotukhin I.: 2012, MNRAS, 419 , 1727.

Dobrycheva D., Melnyk O.: 2012, AASP, 2, 42.

Dobrycheva D.V.: 2013, OAP, 26, 187.

Dobrycheva D.V., Melnyk O.V., Vavilova I.B. et al.: 2015, Astrophysics, 58, 168.

Dobrycheva D.V. et al.: 2017, arXiv:1712.08955.

Dobrycheva D.V., Vavilova I.B., Melnyk O.V. et al.: 2018, Kinemat. Phys. Celest. Bodies, 34, 290.

Dominguez S.H.; Huertas-Company M., Bernardi M. et al.: 2018, MNRAS, 476, 3661.

Elyiv A., Melnyk O. et al.: 2009, MNRAS, 394, 1409.

Elyiv A.A. et al.: 2019, arXiv:1910.07317.

Gunn J.E., Carr M. et al.: 1998, ApJ, 116, 3040.

Ivezic Z., Connelly A.J., VanderPlas J.T. et al.: 2014, Statistics, Data Mining, and Machine Learning in Astronomy, by Z. Ivenci´ c et al. Princeton, NJ: Princeton University Press.

Karachentseva V.E. et al.: 1994, Bull. SAO, 37, 98.

Khramtsov V., Sergeyev A., Spiniello, C. et al.: 2019, arXiv:1906.01638.

Khramtsov V. et al.: 2019, OAP this issue.

Lee J.C., Gil de Paz A. et al.: 2011, ApJS, 192, 33.

Melnyk O.V., Dobrycheva D.V., Vavilova I.B.: 2012, Astrophysics, 55, 293.

Norris R.P.: 2017, Nature Astronomy, 1, 671.

Pierre M., Pacaud F. et al.: 2016, A&A, 592, 16.

Rosen S.R., Webb N.A. et al.: 2016, A&A, 590, 22.

Scoville N., Abraham R.G. et al.: 2007, ApJS, 172 , 38.

Sergeyev A., Spiniello C. et al.: 2018, AAS, 2, 189.

Skrutskie M.F., Cutri R.M., Stiening R. et al.: 2006, Astron. J., 131, 1163.

Soria D., Garibaldi J.M., Ambrogi F, et al.: 2011, Knowledge Based Systems, 24, 775.

Smola A.J., Scholkopf B.: 2004, Statistics and Computing, 14, 199.

Srivastava A.N. (Ed.).: 2012, Advances in machine learning and data mining for astronomy. Chapman and Hall/CRC.

Storrie-Lombardi M.C., Lahav O., Sodre L.Jr. et al.: 1992, MNRAS, 259, 8.

Tolles J., Meurer W.J: 2016, Logistic Regression Relating Patient Characteristics to Outcomes, ISSN 0098-7484

Vavilova I.B., Karachentseva V.E., Makarov D.I. et al.: 2005, Kinemat. Physics Celest. Bodies, 21, 3.

Vavilova I.B., Melnyk O.V., Elyiv A.A.: 2009, Astron. Nachr., 330, 1004.

Vavilova I.B.: 2016, OAP, 29, 109.

Vavilova I.B., Elyiv A.A., Vasylenko M.Yu.: 2018, Radio Phys. Radio Astron., 23, 244.

Voges W., Aschenbach B., Boller Th. et al.: 2000, VizieR On-line Data Catalog, IX/29.

Wright E.L., Eisenhardt P.R.M., Mainzer A.K.: 2010, ApJ, 140, 1868.

Zaane O.R.: 1999. Introduction to data mining.

Zhixian Ma et al.: 2018 arXiv:1812.07190.




Copyright (c) 2019 Odessa Astronomical Publications

Creative Commons License
Ця робота ліцензована Creative Commons Attribution-NonCommercial 4.0 International License.