An unsupervised, ensemble clustering algorithm: A new approach for classification of X-ray sources

S. M. Hojnacki, G. Micela, S. M. LaLonde, E. D. Feigelson, J. H. Kastner

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

A large volume of CCD X-ray spectra is being generated by the Chandra X-ray Observatory (Chandra) and XMM-Newton. Automated spectral analysis and classification methods can aid in sorting, characterizing, and classifying this large volume of CCD X-ray spectra in a non-parametric fashion, complementary to current parametric model fits. We have developed an algorithm that uses multivariate statistical techniques, including an ensemble clustering method, applied for the first time for X-ray spectral classification. The algorithm uses spectral data to group similar discrete sources of X-ray emission by placing the X-ray sources in a three-dimensional spectral sequence and then grouping the ordered sources into clusters based on their spectra. This new method can handle large quantities of data and operate independently of the requirement of spectral source models and a priori knowledge concerning the nature of the sources (i.e., young stars, interacting binaries, active galactic nuclei). We apply the method to Chandra imaging spectroscopy of the young stellar clusters in the Orion Nebula Cluster and the NGC 1333 star formation region.

Original languageEnglish (US)
Pages (from-to)350-360
Number of pages11
JournalStatistical Methodology
Volume5
Issue number4
DOIs
StatePublished - Jul 1 2008

Fingerprint

Clustering Algorithm
Ensemble
Star
Imaging Spectroscopy
Active Galactic nuclei
Ensemble Methods
Spectral Sequence
Parametric Model
Spectral Analysis
Observatory
Clustering Methods
Sorting
Grouping
Binary
Three-dimensional
Requirements

All Science Journal Classification (ASJC) codes

  • Statistics and Probability

Cite this

Hojnacki, S. M. ; Micela, G. ; LaLonde, S. M. ; Feigelson, E. D. ; Kastner, J. H. / An unsupervised, ensemble clustering algorithm : A new approach for classification of X-ray sources. In: Statistical Methodology. 2008 ; Vol. 5, No. 4. pp. 350-360.
@article{3aea2b6f97964a45b3de079a8f41accf,
title = "An unsupervised, ensemble clustering algorithm: A new approach for classification of X-ray sources",
abstract = "A large volume of CCD X-ray spectra is being generated by the Chandra X-ray Observatory (Chandra) and XMM-Newton. Automated spectral analysis and classification methods can aid in sorting, characterizing, and classifying this large volume of CCD X-ray spectra in a non-parametric fashion, complementary to current parametric model fits. We have developed an algorithm that uses multivariate statistical techniques, including an ensemble clustering method, applied for the first time for X-ray spectral classification. The algorithm uses spectral data to group similar discrete sources of X-ray emission by placing the X-ray sources in a three-dimensional spectral sequence and then grouping the ordered sources into clusters based on their spectra. This new method can handle large quantities of data and operate independently of the requirement of spectral source models and a priori knowledge concerning the nature of the sources (i.e., young stars, interacting binaries, active galactic nuclei). We apply the method to Chandra imaging spectroscopy of the young stellar clusters in the Orion Nebula Cluster and the NGC 1333 star formation region.",
author = "Hojnacki, {S. M.} and G. Micela and LaLonde, {S. M.} and Feigelson, {E. D.} and Kastner, {J. H.}",
year = "2008",
month = "7",
day = "1",
doi = "10.1016/j.stamet.2008.02.008",
language = "English (US)",
volume = "5",
pages = "350--360",
journal = "Statistical Methodology",
issn = "1572-3127",
publisher = "Elsevier",
number = "4",

}

An unsupervised, ensemble clustering algorithm : A new approach for classification of X-ray sources. / Hojnacki, S. M.; Micela, G.; LaLonde, S. M.; Feigelson, E. D.; Kastner, J. H.

In: Statistical Methodology, Vol. 5, No. 4, 01.07.2008, p. 350-360.

Research output: Contribution to journalArticle

TY - JOUR

T1 - An unsupervised, ensemble clustering algorithm

T2 - A new approach for classification of X-ray sources

AU - Hojnacki, S. M.

AU - Micela, G.

AU - LaLonde, S. M.

AU - Feigelson, E. D.

AU - Kastner, J. H.

PY - 2008/7/1

Y1 - 2008/7/1

N2 - A large volume of CCD X-ray spectra is being generated by the Chandra X-ray Observatory (Chandra) and XMM-Newton. Automated spectral analysis and classification methods can aid in sorting, characterizing, and classifying this large volume of CCD X-ray spectra in a non-parametric fashion, complementary to current parametric model fits. We have developed an algorithm that uses multivariate statistical techniques, including an ensemble clustering method, applied for the first time for X-ray spectral classification. The algorithm uses spectral data to group similar discrete sources of X-ray emission by placing the X-ray sources in a three-dimensional spectral sequence and then grouping the ordered sources into clusters based on their spectra. This new method can handle large quantities of data and operate independently of the requirement of spectral source models and a priori knowledge concerning the nature of the sources (i.e., young stars, interacting binaries, active galactic nuclei). We apply the method to Chandra imaging spectroscopy of the young stellar clusters in the Orion Nebula Cluster and the NGC 1333 star formation region.

AB - A large volume of CCD X-ray spectra is being generated by the Chandra X-ray Observatory (Chandra) and XMM-Newton. Automated spectral analysis and classification methods can aid in sorting, characterizing, and classifying this large volume of CCD X-ray spectra in a non-parametric fashion, complementary to current parametric model fits. We have developed an algorithm that uses multivariate statistical techniques, including an ensemble clustering method, applied for the first time for X-ray spectral classification. The algorithm uses spectral data to group similar discrete sources of X-ray emission by placing the X-ray sources in a three-dimensional spectral sequence and then grouping the ordered sources into clusters based on their spectra. This new method can handle large quantities of data and operate independently of the requirement of spectral source models and a priori knowledge concerning the nature of the sources (i.e., young stars, interacting binaries, active galactic nuclei). We apply the method to Chandra imaging spectroscopy of the young stellar clusters in the Orion Nebula Cluster and the NGC 1333 star formation region.

UR - http://www.scopus.com/inward/record.url?scp=44649129936&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=44649129936&partnerID=8YFLogxK

U2 - 10.1016/j.stamet.2008.02.008

DO - 10.1016/j.stamet.2008.02.008

M3 - Article

AN - SCOPUS:44649129936

VL - 5

SP - 350

EP - 360

JO - Statistical Methodology

JF - Statistical Methodology

SN - 1572-3127

IS - 4

ER -