dc.contributor.author |
Sharma, K |
|
dc.contributor.author |
Kembhavi, Ajit |
|
dc.contributor.author |
Kembhavi, Aniruddha |
|
dc.contributor.author |
Sivarani, T |
|
dc.contributor.author |
Abraham, S. |
|
dc.date.accessioned |
2020-11-26T15:46:32Z |
|
dc.date.available |
2020-11-26T15:46:32Z |
|
dc.date.issued |
2019-10 |
|
dc.identifier.citation |
Bulletin de la Societe Royale des Sciences de Liege, Vol. 88, pp. 174-181 |
en_US |
dc.identifier.issn |
0037-9565 |
|
dc.identifier.uri |
http://prints.iiap.res.in/handle/2248/7425 |
|
dc.description |
Open Access © Societe Royale des Sciences de Liege https://doi.org/10.25518/0037-9565.8811 |
en_US |
dc.description.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. |
en_US |
dc.language.iso |
en |
en_US |
dc.publisher |
Societe Royale des Sciences de Liege |
en_US |
dc.subject |
Astronomical databases |
en_US |
dc.subject |
Spectroscopy |
en_US |
dc.subject |
Deep learning |
en_US |
dc.subject |
Autoencoder |
en_US |
dc.subject |
Outlier detection |
en_US |
dc.title |
Detecting Outliers in SDSS using Convolutional Neural Network |
en_US |
dc.type |
Article |
en_US |