Detecting quasars in large-scale astronomical surveys

Fabian Gieseke; Kai Lars Polsterer; Andreas Thom; Peter Zinn; Dominik Bomanns; Ralf Jürgen Dettmar; Oliver Kramer; Jan Vahrenhold

doi:10.1109/ICMLA.2010.59

Detecting quasars in large-scale astronomical surveys

Fabian Gieseke^*, Kai Lars Polsterer, Andreas Thom, Peter Zinn, Dominik Bomanns, Ralf Jürgen Dettmar, Oliver Kramer, Jan Vahrenhold

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

13 Citations (Scopus)

Abstract

We present a classification-based approach to identify quasi-stellar radio sources (quasars) in the Sloan Digital Sky Survey and evaluate its performance on a manually labeled training set. While reasonable results can already be obtained via approaches working only on photometric data, our experiments indicate that simple but problem-specific features extracted from spectroscopic data can significantly improve the classification performance. Since our approach works orthogonal to existing classification schemes used for building the spectroscopic catalogs, our classification results are well suited for a mutual assessment of the approaches' accuracies.

Original language	English
Title of host publication	Proceedings - 9th International Conference on Machine Learning and Applications, ICMLA 2010
Number of pages	6
Publisher	IEEE
Publication date	2010
Pages	352-357
Article number	5708856
ISBN (Print)	978-0-7695-4300-0
DOIs	https://doi.org/10.1109/ICMLA.2010.59
Publication status	Published - 2010
Externally published	Yes
Event	9th International Conference on Machine Learning and Applications, ICMLA 2010 - Washington, DC, United States Duration: 12 Dec 2010 → 14 Dec 2010

Conference

Conference	9th International Conference on Machine Learning and Applications, ICMLA 2010
Country/Territory	United States
City	Washington, DC
Period	12/12/2010 → 14/12/2010
Sponsor	Association for Machine Learning and Applications, IEEE, California State University Bakersfield, Wayne State University

Keywords

Astronomy
Classification
Feature extraction

Access to Document

10.1109/ICMLA.2010.59

Cite this

Detecting quasars in large-scale astronomical surveys. / Gieseke, Fabian; Polsterer, Kai Lars; Thom, Andreas; Zinn, Peter; Bomanns, Dominik; Dettmar, Ralf Jürgen; Kramer, Oliver; Vahrenhold, Jan.

Proceedings - 9th International Conference on Machine Learning and Applications, ICMLA 2010. IEEE, 2010. p. 352-357 5708856.

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

Gieseke, F, Polsterer, KL, Thom, A, Zinn, P, Bomanns, D, Dettmar, RJ, Kramer, O & Vahrenhold, J 2010, Detecting quasars in large-scale astronomical surveys. in Proceedings - 9th International Conference on Machine Learning and Applications, ICMLA 2010., 5708856, IEEE, pp. 352-357, 9th International Conference on Machine Learning and Applications, ICMLA 2010, Washington, DC, United States, 12/12/2010. https://doi.org/10.1109/ICMLA.2010.59

@inproceedings{01cc1b7b57af4b65a542f0b99ebb6444,

title = "Detecting quasars in large-scale astronomical surveys",

abstract = "We present a classification-based approach to identify quasi-stellar radio sources (quasars) in the Sloan Digital Sky Survey and evaluate its performance on a manually labeled training set. While reasonable results can already be obtained via approaches working only on photometric data, our experiments indicate that simple but problem-specific features extracted from spectroscopic data can significantly improve the classification performance. Since our approach works orthogonal to existing classification schemes used for building the spectroscopic catalogs, our classification results are well suited for a mutual assessment of the approaches' accuracies.",

keywords = "Astronomy, Classification, Feature extraction",

author = "Fabian Gieseke and Polsterer, {Kai Lars} and Andreas Thom and Peter Zinn and Dominik Bomanns and Dettmar, {Ralf J{\"u}rgen} and Oliver Kramer and Jan Vahrenhold",

year = "2010",

doi = "10.1109/ICMLA.2010.59",

language = "English",

isbn = "978-0-7695-4300-0",

pages = "352--357",

booktitle = "Proceedings - 9th International Conference on Machine Learning and Applications, ICMLA 2010",

publisher = "IEEE",

note = "9th International Conference on Machine Learning and Applications, ICMLA 2010 ; Conference date: 12-12-2010 Through 14-12-2010",

}

TY - GEN

T1 - Detecting quasars in large-scale astronomical surveys

AU - Gieseke, Fabian

AU - Polsterer, Kai Lars

AU - Thom, Andreas

AU - Zinn, Peter

AU - Bomanns, Dominik

AU - Dettmar, Ralf Jürgen

AU - Kramer, Oliver

AU - Vahrenhold, Jan

PY - 2010

Y1 - 2010

N2 - We present a classification-based approach to identify quasi-stellar radio sources (quasars) in the Sloan Digital Sky Survey and evaluate its performance on a manually labeled training set. While reasonable results can already be obtained via approaches working only on photometric data, our experiments indicate that simple but problem-specific features extracted from spectroscopic data can significantly improve the classification performance. Since our approach works orthogonal to existing classification schemes used for building the spectroscopic catalogs, our classification results are well suited for a mutual assessment of the approaches' accuracies.

AB - We present a classification-based approach to identify quasi-stellar radio sources (quasars) in the Sloan Digital Sky Survey and evaluate its performance on a manually labeled training set. While reasonable results can already be obtained via approaches working only on photometric data, our experiments indicate that simple but problem-specific features extracted from spectroscopic data can significantly improve the classification performance. Since our approach works orthogonal to existing classification schemes used for building the spectroscopic catalogs, our classification results are well suited for a mutual assessment of the approaches' accuracies.

KW - Astronomy

KW - Classification

KW - Feature extraction

U2 - 10.1109/ICMLA.2010.59

DO - 10.1109/ICMLA.2010.59

M3 - Article in proceedings

AN - SCOPUS:79952412202

SN - 978-0-7695-4300-0

SP - 352

EP - 357

BT - Proceedings - 9th International Conference on Machine Learning and Applications, ICMLA 2010

PB - IEEE

T2 - 9th International Conference on Machine Learning and Applications, ICMLA 2010

Y2 - 12 December 2010 through 14 December 2010

ER -