Hostname: page-component-84b7d79bbc-tsvsl Total loading time: 0 Render date: 2024-07-29T21:07:14.672Z Has data issue: false hasContentIssue false
  • English
  • Français

Machine Classification of Transient Images

Published online by Cambridge University Press:  01 July 2015

Lise du Buisson ,
Navin Sivanandam ,
Bruce A. Bassett  and
Mathew Smith
Lise du Buisson*
Affiliation:
Department of Mathematics and Applied Mathematics, University of Cape Town, Cross Campus Rd, Rondebosch 7700, South Africa
Navin Sivanandam*
Affiliation:
African Institute for Mathematical Sciences, 6–8 Melrose Rd, Muizenberg 7945, South Africa
Bruce A. Bassett*
Affiliation:
Department of Mathematics and Applied Mathematics, University of Cape Town, Cross Campus Rd, Rondebosch 7700, South Africa African Institute for Mathematical Sciences, 6–8 Melrose Rd, Muizenberg 7945, South Africa South African Astronomical Observatory, Observatory Rd, Observatory 7925, South Africa
Mathew Smith
Affiliation:
University of the Western Cape, Robert Sobukwe Rd, Bellville 7535, South Africa
*
†Email: lisedubuisson@gmail.com
‡Email: navin.sivanandam@gmail.com
Email: bruce.a.bassett@gmail.com
Rights & Permissions [Opens in a new window]

Abstract

Core share and HTML view are not available for this content. However, as you have access to this content, a full PDF is available via the ‘Save PDF’ action button.

Using transient imaging data from the 2nd and 3rd years of the SDSS supernova survey, we apply various machine learning techniques to the problem of classifying transients (e.g. SNe) from artefacts, one of the first steps in any transient detection pipeline, and one that is often still carried out by human scanners. Using features mostly obtained from PCA, we show that we can match human levels of classification success, and find that a K-nearest neighbours algorithm and SkyNet perform best, while the Naive Bayes, SVM and minimum error classifier have performances varying from slightly to significantly worse.

Keywords

methods: data analysismethods: statisticaltechniques: image processingtechniques: photometricsurveys
Type
Contributed Papers
Information
Proceedings of the International Astronomical Union , Volume 10 , Symposium S306: Statistical Challenges in 21st Century Cosmology , May 2014 , pp. 288 - 291
Copyright
Copyright © International Astronomical Union 2015 

References

Bassett, B. A., Richmond, M., & Frieman, J. 2005, url: http://spiff.rit.edu/richmond/sdss/sn_survey/scan_manual/sn_scan.htmlGoogle Scholar
Cohen, J. 1960, Educational and Psychological Measurement, 20, 37CrossRefGoogle Scholar
duBuisson, L. Buisson, L., Sivanandam, N., & Bassett, B. A., Smith, M., 2015, submitted to MNRAS, arXiv:1407.4118 [astro-ph.IM]Google Scholar
Frieman, J. A., Bassett, B., Becker, A., & Choi, C., et al. 2008, AJ, 135, 338CrossRefGoogle Scholar
Graff, P., Feroz, F., Hobson, M. P., & Lasenby, A. 2014, MNRAS, 441, 1741Google Scholar
Hanley, J. & McNeil, B. J. 1982, Radiology, 143, 29CrossRefGoogle Scholar
Kessler, R. 2007, Private CommunicationGoogle Scholar
Landis, J. R. & Koch, G. G. 1977, Biometrics, 33, 159Google Scholar
Sako, M., Bassett, B., Becker, A. C., & Brown, P. J., et al. 1977, ArXiv e-prints, adsurl: http://adsabs.harvard.edu/abs/2014arXiv1401.3317SGoogle Scholar