ICON
NAVO Directory
X Tip: What's a "Resource"?
Hosted By
STScI Home
Space Telescope
Science Institute

Resource Record Summary

Catalog Service:
Machine learning technique to classify CoNFIG gal.

Short name: J/ApJS/230/20
IVOA Identifier: ivo://CDS.VizieR/J/ApJS/230/20
DOI (Digital Object Identifier): 10.26093/cds/vizier.22300020
Publisher: CDSivo://CDS[Pub. ID]
More Info: http://cdsarc.unistra.fr/cgi-bin/cat/J/ApJS/230/20
VO Compliance: Level 2: This is a VO-compliant resource.
Status: active
Registered: 2017 Aug 17 14:51:41Z
Get XML

Description


We present the application of a deep machine learning technique to classify radio images of extended sources on a morphological basis using convolutional neural networks (CNN). In this study, we have taken the case of the Fanaroff-Riley (FR) class of radio galaxies as well as radio galaxies with bent-tailed morphology. We have used archival data from the Very Large Array (VLA)-Faint Images of the Radio Sky at Twenty Centimeters survey and existing visually classified samples available in the literature to train a neural network for morphological classification of these categories of radio sources. Our training sample size for each of these categories is ~200 sources, which has been augmented by rotated versions of the same. Our study shows that CNNs can classify images of the FRI and FRII and bent-tailed radio galaxies with high accuracy (maximum precision at 95%) using well-defined samples and a "fusion classifier," which combines the results of binary classifications, while allowing for a mechanism to find sources with unusual morphologies. The individual precision is highest for bent-tailed radio galaxies at 95% and is 91% and 75% for the FRI and FRII classes, respectively, whereas the recall is highest for FRI and FRIIs at 91% each, while the bent-tailed class has a recall of 79%. These results show that our results are comparable to that of manual classification, while being much faster. Finally, we discuss the computational and data-related challenges associated with the morphological classification of radio galaxies with CNNs.

More About this Resource

About the Resource Providers

This section describes who is responsible for this resource

Publisher: CDSivo://CDS[Pub. ID]

Creators:
Aniyan A.K.Thorat K.

Contact Information:
X CDS support team
Email: cds-question at unistra.fr
Address: CDS
Observatoire de Strasbourg
11 rue de l'Universite
F-67000 Strasbourg
France

Status of This Resource

This section provides some status information: the resource version, availability, and relevant dates.

Version: n/a
Availability: This is an active resource.
  • This service provides only public data.
Relevant dates for this Resource:
  • Updated: 2017 Sep 04 08:43:37Z
  • Created: 2017 Aug 17 14:51:41Z

This resource was registered on: 2017 Aug 17 14:51:41Z
This resource description was last updated on: 2021 Oct 21 00:00:00Z

What This Resource is About

This section describes what the resource is, what it contains, and how it might be relevant.

Resource Class: CatalogService
This resource is a service that provides access to catalog data. You can extract data from the catalog by issuing a query, and the matching data is returned as a table.
Resource type keywords:
  • Catalog
Subject keywords:
  • Galaxies
  • Radio galaxies
Intended audience or use:
  • Research: This resource provides information appropriate for supporting scientific research.
More Info: http://cdsarc.unistra.fr/cgi-bin/cat/J/ApJS/230/20 Literature Reference: 2017ApJS..230...20A

Related Resources:

Other Related Resources
TAP VizieR generic service(IsServedBy) ivo://CDS.VizieR/TAP [Res. ID]
Conesearch service(IsServedBy)
VIII/65 : 1.4GHz NRAO VLA Sky Survey (NVSS) (Condon+ 1998) ivo://CDS.VizieR/VIII/65 [Res. ID]

Data Coverage Information

This section describes the data's coverage over the sky, frequency, and time.

Wavebands covered:

  • Radio

Rights and Usage Information

This section describes the rights and usage information for this data.

Rights:

Available Service Interfaces

Custom Service

This is service that does not comply with any IVOA standard but instead provides access to special capabilities specific to this resource.

VO Compliance: Level 2: This is a VO-compliant resource.
Available endpoints for this service interface:
Custom Service

This is service that does not comply with any IVOA standard but instead provides access to special capabilities specific to this resource.

VO Compliance: Level 2: This is a VO-compliant resource.
Available endpoints for this service interface:
  • URL-based interface: http://vizier.unistra.fr/viz-bin/votable?-source=J/ApJS/230/20
Table Access Protocol - Auxiliary ServiceXX

This is a standard IVOA service that takes as input an ADQL or PQL query and returns tabular data.

VO Compliance: Level 2: This is a VO-compliant resource.
Available endpoints for the standard interface:
  • http://tapvizier.u-strasbg.fr/TAPVizieR/tap
Simple Cone SearchXXSearch Me

This is a standard IVOA service that takes as input a position in the sky and a radius and returns catalog records with positions within that radius.

VO Compliance: Level 2: This is a VO-compliant resource.
Description:
Cone search capability for table J/ApJS/230/20/table5 (Table of predictions for validation samples)
Available endpoints for the standard interface:
  • http://vizier.unistra.fr/viz-bin/conesearch/J/ApJS/230/20/table5?
Maximum search radius accepted: 180.0 degrees
Maximum number of matching records returned: 50000
This service supports the VERB input parameter:
Use VERB=1 to minimize the returned columns or VERB=3 to maximize.


Developed with the support of the National Science Foundation
under Cooperative Agreement AST0122449 with the Johns Hopkins University
The NAVO project is a member of the International Virtual Observatory Alliance

This NAVO Application is hosted by the Space Telescope Science Institute

Member
ivoa logo
Contact Us