skip to main content
Language:
Search Limited to: Search Limited to: Resource type Show Results with: Show Results with: Search type Index

On Machine-learned Classification of Variable Stars with Sparse and Noisy Time-series Data

The Astrophysical journal, 2011-05, Vol.733 (1), p.10-jQuery1323908261630='48' [Peer Reviewed Journal]

2015 INIST-CNRS ;ISSN: 0004-637X ;EISSN: 1538-4357 ;DOI: 10.1088/0004-637X/733/1/10 ;CODEN: ASJOAB

Full text available

Citations Cited by
  • Title:
    On Machine-learned Classification of Variable Stars with Sparse and Noisy Time-series Data
  • Author: Richards, Joseph W ; Starr, Dan L ; Butler, Nathaniel R ; Bloom, Joshua S ; Brewer, John M ; Crellin-Quick, Arien ; Higgins, Justin ; Kennedy, Rachel ; Rischard, Maxime
  • Subjects: Astronomy ; ASTROPHYSICS, COSMOLOGY AND ASTRONOMY ; CLASSIFICATION ; Classifiers ; DATA ANALYSIS ; Earth, ocean, space ; Errors ; Estimates ; Exact sciences and technology ; INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND TECHNOLOGY ; Mathematical analysis ; Mathematical models ; Methodology ; Radio frequencies ; STARS ; VARIABLE STARS
  • Is Part Of: The Astrophysical journal, 2011-05, Vol.733 (1), p.10-jQuery1323908261630='48'
  • Description: With the coming data deluge from synoptic surveys, there is a need for frameworks that can quickly and automatically produce calibrated classification probabilities for newly observed variables based on small numbers of time-series measurements. In this paper, we introduce a methodology for variable-star classification, drawing from modern machine-learning techniques. We describe how to homogenize the information gleaned from light curves by selection and computation of real-numbered metrics (features), detail methods to robustly estimate periodic features, introduce tree-ensemble methods for accurate variable-star classification, and show how to rigorously evaluate a classifier using cross validation. On a 25-class data set of 1542 well-studied variable stars, we achieve a 22.8% error rate using the random forest (RF) classifier; this represents a 24% improvement over the best previous classifier on these data. This methodology is effective for identifying samples of specific science classes: for pulsational variables used in Milky Way tomography we obtain a discovery efficiency of 98.2% and for eclipsing systems we find an efficiency of 99.1%, both at 95% purity. The RF classifier is superior to other methods in terms of accuracy, speed, and relative immunity to irrelevant features; the RF can also be used to estimate the importance of each feature in classification. Additionally, we present the first astronomical use of hierarchical classification methods to incorporate a known class taxonomy in the classifier, which reduces the catastrophic error rate from 8% to 7.8%. Excluding low-amplitude sources, the overall error rate improves to 14%, with a catastrophic error rate of 3.5%.
  • Publisher: Bristol: IOP Publishing
  • Language: English
  • Identifier: ISSN: 0004-637X
    EISSN: 1538-4357
    DOI: 10.1088/0004-637X/733/1/10
    CODEN: ASJOAB
  • Source: Alma/SFX Local Collection
Back to results list
INSPIRE LIBRARY - TON DUC THANG UNIVERSITY (84-028) 37 755 057 Feedback
19 Nguyen Huu Tho St. Dist.7, HCM thuvien@tdtu.edu.vn

Copyright © 2017 INSPIRE LIBRARY - TON DUC THANG UNIVERSITY

Searching Remote Databases, Please Wait