Please use this identifier to cite or link to this item: http://hdl.handle.net/2248/7545
Title: Detecting outliers in SDSS using Convolutional Neural Network
Authors: Sharma, Kaushal
Kembhavi, Ajit
Kembhavi, Aniruddha
Sivarani, T
Abraham, Sheelu
Keywords: Astronomical databases;Spectroscopy;Deep learning;Autoencoder;Outlier detection
Issue Date: Oct-2019
Publisher: Societe Royale des Sciences de Liege
Citation: Bulletin de la Societe Royale des Sciences de Liege, Vol. 88, pp. 174-181
Abstract: We propose an automated algorithm based on Convolutional Neural Network (CNN) for the detection of peculiar objects in large databases using their spectral observations. A convolutional neural network is a class of deep-learning algorithms which allows the detection of significant features/patterns in sequential data like images, audio, time-series etc. by applying convolutional neurons (kernels) along the sequence. For detecting unusual spectra, we use eight-layer deep convolutional network with autoencoder architecture on ∼ 60,000 spectra collected from the Sloan Digital Sky Survey. The training of the network is done in an unsupervised manner. We show that the trained network is able to retrieve the spectra of rare objects from a large collection of spectra. Such algorithms can easily be rescaled to other surveys and therefore can serve as a potential component of the data reduction pipelines for automatically detecting spectra with unusual features and recovering defective spectra.
Description: Open Access
URI: http://hdl.handle.net/2248/7545
ISSN: 1783-5720
???metadata.dc.rights???: © Societe Royale des Sciences de Liege
???metadata.dc.relation.uri???: https://doi.org/10.25518/0037-9565.8811
Appears in Collections:IIAP Publications

Files in This Item:
File Description SizeFormat 
Detecting Outliers in SDSS using Convolutional Neural Network.pdfOpen Access436.59 kBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.