The Open UniversitySkip to content
 

Morphological classification of radio galaxies: Capsule Networks versus Convolutional Neural Networks

Lukic, V.; Brüggen, M.; Mingo, B.; Croston, J.H.; Kasieczka, G. and Best, P.N. (2019). Morphological classification of radio galaxies: Capsule Networks versus Convolutional Neural Networks. Monthly Notices of the Royal Astronomical Society, 487(2) pp. 1729–1744.

Full text available as:
[img]
Preview
PDF (Version of Record) - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
Download (2MB) | Preview
DOI (Digital Object Identifier) Link: https://doi.org/10.1093/mnras/stz1289
Google Scholar: Look up in Google Scholar

Abstract

Next-generation radio surveys will yield an unprecedented amount of data, warranting analysis by use of machine learning techniques. Convolutional neural networks are the deep learning technique that has proven to be the most successful in classifying image data. Capsule networks are a more recently developed technique that use capsules comprised of groups of neurons, that describe properties of an image including the relative spatial locations of features. The current work explores the performance of different capsule network architectures against simpler convolutional neural network architectures, in reproducing the classifications into the classes of unresolved, FRI and FRII morphologies. We utilise images from a LOFAR survey which is the deepest, wide-area radio survey to date, revealing more complex radio-source structures compared to previous surveys, presenting further challenges for machine learning algorithms. The 4- and 8-layer convolutional networks attain an average precision of 93.3% and 94.3% respectively, compared to 89.7% obtained with the capsule network, when training on original and augmented images. Implementing transfer learning achieves a precision of 94.4%, that is within the confidence interval of the 8-layer convolutional network. The convolutional networks always outperform any variation of the capsule network, as they prove to be more robust to the presence of noise in images. The use of pooling appears to allow more freedom for the intra-class variability of radio galaxy morphologies, as well as reducing the impact of noise.

Item Type: Journal Item
Copyright Holders: 2019 The Authors
ISSN: 1365-2966
Keywords: Astronomical instrumentation; methods and techniques; radio continuum; galaxies
Academic Unit/School: Faculty of Science, Technology, Engineering and Mathematics (STEM) > Physical Sciences
Faculty of Science, Technology, Engineering and Mathematics (STEM)
Item ID: 61511
SWORD Depositor: Jisc Publications-Router
Depositing User: Jisc Publications-Router
Date Deposited: 30 May 2019 08:48
Last Modified: 19 Aug 2019 21:15
URI: http://oro.open.ac.uk/id/eprint/61511
Share this page:

Metrics

Altmetrics from Altmetric

Citations from Dimensions

Download history for this item

These details should be considered as only a guide to the number of downloads performed manually. Algorithmic methods have been applied in an attempt to remove automated downloads from the displayed statistics but no guarantee can be made as to the accuracy of the figures.

Actions (login may be required)

Policies | Disclaimer

© The Open University   contact the OU