Please use this identifier to cite or link to this item: http://hdl.handle.net/2248/7545
Full metadata record
DC FieldValueLanguage
dc.contributor.authorSharma, Kaushal-
dc.contributor.authorKembhavi, Ajit-
dc.contributor.authorKembhavi, Aniruddha-
dc.contributor.authorSivarani, T-
dc.contributor.authorAbraham, Sheelu-
dc.date.accessioned2019-12-02T11:03:11Z-
dc.date.available2019-12-02T11:03:11Z-
dc.date.issued2019-10-
dc.identifier.citationBulletin de la Societe Royale des Sciences de Liege, Vol. 88, pp. 174-181en_US
dc.identifier.issn1783-5720-
dc.identifier.urihttp://hdl.handle.net/2248/7545-
dc.descriptionOpen Accessen_US
dc.description.abstractWe 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.en_US
dc.language.isoenen_US
dc.publisherSociete Royale des Sciences de Liegeen_US
dc.relation.urihttps://doi.org/10.25518/0037-9565.8811-
dc.rights© Societe Royale des Sciences de Liege-
dc.subjectAstronomical databasesen_US
dc.subjectSpectroscopyen_US
dc.subjectDeep learningen_US
dc.subjectAutoencoderen_US
dc.subjectOutlier detectionen_US
dc.titleDetecting outliers in SDSS using Convolutional Neural Networken_US
dc.typeArticleen_US
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.