The FIRST Classifier: Compact and Extended Radio Galaxy Classification using (...)
-
by
zutopian
The FIRST Classifier: Compact and Extended Radio Galaxy Classification using Deep Convolutional Neural Networks.
(...) In this work we present the FIRST Classifier, an on-line system for automated classification of Compact and Extended radio sources. We developed the FIRST Classifier based on a trained Deep Convolutional Neural Network Model to automate the morphological classification of compact and extended radio sources observed in the FIRST radio survey. Our model achieved an overall accuracy of 97% and a recall of 98%, 100%, 98% and 93% for Compact, BENT, FRI and FRII galaxies respectively. The current version of the FIRST classifier is able to predict the morphological class for a single source or for a list of sources as Compact or Extended (FRI, FRII and BENT).
Wathela Alhassan, A.R. Taylor, Mattia Vaccari.
(Submitted on 26 Jul 2018).
https://arxiv.org/abs/1807.10380Posted
-
by
zutopian
There is given following statement concerning RGZ.:
Following the developments in optical galaxy morphol- ogy classification, the Radio Galaxy Zoo project (Banfield et al. 2015) has recently engaged many citizen scientists to identify the morphological type of radio sources and deter- mine their host galaxy by combining infrared and radio ob- servations. However, their classification scheme is based on the number of components of extended radio sources and does not lend itself to be interpreted in terms of FRIs, FRIIs and bent sources. However, Lukic et al. (2018) have applied convolutional neural networks to the classification of sources according to this scheme and achieved a final test accuracy of 94.8 per cent on Radio Galaxy Zoo Data Release 1.
https://arxiv.org/abs/1807.10380
Posted
-
by
ivywong
scientist, admin
Thanks @zutopian. I haven't read this paper yet so am not sure what it says.
Posted