Providing contexts for classification of transients in a wide-area sky survey: An application of noise-induced cluster ensemble

With new sensor systems that capture sky survey at high quality level, analyzing the resulting data within a limited time frame appears to be the next challenge. Specific to the GOTO project, this task proves to be crucial to discover new transients from a pool of large candidates. Initial works bas...

Full description

Saved in:
Bibliographic Details
Main Authors: Tossapon Boongoen, Natthakan Iam-On, James Mullaney
Format: Article
Language:English
Published: Springer 2022-09-01
Series:Journal of King Saud University: Computer and Information Sciences
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S131915782100166X
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849315850254811136
author Tossapon Boongoen
Natthakan Iam-On
James Mullaney
author_facet Tossapon Boongoen
Natthakan Iam-On
James Mullaney
author_sort Tossapon Boongoen
collection DOAJ
description With new sensor systems that capture sky survey at high quality level, analyzing the resulting data within a limited time frame appears to be the next challenge. Specific to the GOTO project, this task proves to be crucial to discover new transients from a pool of large candidates. Initial works based on the feature-based approach design this detection as imbalance classification, where a data-level method can be used to resolve the difference in cardinality between classes. This paper presents a context generation framework to complement the previously proposed model. In particular, samples are clustered to form data contexts to which different learning strategies may be applied. To ensure the quality of data clustering, a noise-induced cluster ensemble technique that has been recently introduced in the literature is employed here. The results with simulated data and algorithms of NB, C4.5 and KNN have shown that the proposed framework can filter out some negative samples quickly, while making classification of the rest more effective. In particular, it enhances predictive performance of basic classifiers by lifting F1 scores from less than 0.1 to around 0.3–0.5. Besides, parameter analysis is also given as a guideline for its application.
format Article
id doaj-art-a34a31d154644075b1f66820c682cab6
institution Kabale University
issn 1319-1578
language English
publishDate 2022-09-01
publisher Springer
record_format Article
series Journal of King Saud University: Computer and Information Sciences
spelling doaj-art-a34a31d154644075b1f66820c682cab62025-08-20T03:52:02ZengSpringerJournal of King Saud University: Computer and Information Sciences1319-15782022-09-013485007501910.1016/j.jksuci.2021.06.019Providing contexts for classification of transients in a wide-area sky survey: An application of noise-induced cluster ensembleTossapon Boongoen0Natthakan Iam-On1James Mullaney2Center of Excellence in AI and Emerging Technologies, School of Information Technology, Mae Fah Luang University, Tasud, Muang District, Chiang Rai 57100, ThailandCenter of Excellence in AI and Emerging Technologies, School of Information Technology, Mae Fah Luang University, Tasud, Muang District, Chiang Rai 57100, Thailand; Corresponding author.Department of Physics and Astronomy, University of Sheffield, UKWith new sensor systems that capture sky survey at high quality level, analyzing the resulting data within a limited time frame appears to be the next challenge. Specific to the GOTO project, this task proves to be crucial to discover new transients from a pool of large candidates. Initial works based on the feature-based approach design this detection as imbalance classification, where a data-level method can be used to resolve the difference in cardinality between classes. This paper presents a context generation framework to complement the previously proposed model. In particular, samples are clustered to form data contexts to which different learning strategies may be applied. To ensure the quality of data clustering, a noise-induced cluster ensemble technique that has been recently introduced in the literature is employed here. The results with simulated data and algorithms of NB, C4.5 and KNN have shown that the proposed framework can filter out some negative samples quickly, while making classification of the rest more effective. In particular, it enhances predictive performance of basic classifiers by lifting F1 scores from less than 0.1 to around 0.3–0.5. Besides, parameter analysis is also given as a guideline for its application.http://www.sciencedirect.com/science/article/pii/S131915782100166XAstronomical dataAnalytical methodMachine learningImbalance classificationCluster ensemble
spellingShingle Tossapon Boongoen
Natthakan Iam-On
James Mullaney
Providing contexts for classification of transients in a wide-area sky survey: An application of noise-induced cluster ensemble
Journal of King Saud University: Computer and Information Sciences
Astronomical data
Analytical method
Machine learning
Imbalance classification
Cluster ensemble
title Providing contexts for classification of transients in a wide-area sky survey: An application of noise-induced cluster ensemble
title_full Providing contexts for classification of transients in a wide-area sky survey: An application of noise-induced cluster ensemble
title_fullStr Providing contexts for classification of transients in a wide-area sky survey: An application of noise-induced cluster ensemble
title_full_unstemmed Providing contexts for classification of transients in a wide-area sky survey: An application of noise-induced cluster ensemble
title_short Providing contexts for classification of transients in a wide-area sky survey: An application of noise-induced cluster ensemble
title_sort providing contexts for classification of transients in a wide area sky survey an application of noise induced cluster ensemble
topic Astronomical data
Analytical method
Machine learning
Imbalance classification
Cluster ensemble
url http://www.sciencedirect.com/science/article/pii/S131915782100166X
work_keys_str_mv AT tossaponboongoen providingcontextsforclassificationoftransientsinawideareaskysurveyanapplicationofnoiseinducedclusterensemble
AT natthakaniamon providingcontextsforclassificationoftransientsinawideareaskysurveyanapplicationofnoiseinducedclusterensemble
AT jamesmullaney providingcontextsforclassificationoftransientsinawideareaskysurveyanapplicationofnoiseinducedclusterensemble