J/A+A/606/A39 OCSVM anomalies (Solarz+, 2017)
Automated novelty detection in the WISE survey with one-class support vector
machines.
Solarz A., Bilicki M., Gromadzki M., Pollo A., Durkalec A., Wypych M.
<Astron. Astrophys. 606, A39 (2017)>
=2017A&A...606A..39S 2017A&A...606A..39S (SIMBAD/NED BibCode)
ADC_Keywords: Galaxies, IR ; Active gal. nuclei ; Photometry, infrared
Keywords: infrared: galaxies - infrared: stars - galaxies: statistics -
stars: statistics - Galaxy: fundamental parameters
Abstract:
Wide-angle photometric surveys of previously uncharted sky areas or
wavelength regimes will always bring in unexpected sources -
novelties or even anomalies - whose existence and properties cannot
be easily predicted from earlier observations. Such objects can be
efficiently located with novelty detection algorithms. Here we present
an application of such a method, called one-class support vector
machines (OCSVM), to search for anomalous patterns among sources
preselected from the mid-infrared AllWISE catalogue covering the whole
sky. To create a model of expected data we train the algorithm on a
set of objects with spectroscopic identifications from the SDSS DR13
database, present also in AllWISE. The OCSVM method detects as
anomalous those sources whose patterns - WISE photometric
measurements in this case - are inconsistent with the model. Among
the detected anomalies we find artefacts, such as objects with
spurious photometry due to blending, but more importantly also real
sources of genuine astrophysical interest. Among the latter, OCSVM has
identified a sample of heavily reddened AGN/quasar candidates
distributed uniformly over the sky and in a large part absent from
other WISE-based AGN catalogues. It also allowed us to find a specific
group of sources of mixed types, mostly stars and compact galaxies. By
combining the semi-supervised OCSVM algorithm with standard
classification methods it will be possible to improve the latter by
accounting for sources which are not present in the training sample,
but are otherwise well-represented in the target set. Anomaly
detection adds flexibility to automated source separation procedures
and helps verify the reliability and representativeness of the
training samples. It should be thus considered as an essential step in
supervised classification schemes to ensure completeness and purity of
produced catalogues.
Description:
One table containing 642,353 sources selected as anomalous with
one-class support vector machine algorithm in AllWISE data release.
Data have AllWISE photometry in W1, W2 and W3 passband and include W3
flux correction described in Krakowski et al. (2016A&A...596A..39K 2016A&A...596A..39K).
File Summary:
--------------------------------------------------------------------------------
FileName Lrecl Records Explanations
--------------------------------------------------------------------------------
ReadMe 80 . This file
ocsvm_an.dat 103 642353 OCSVM anomalies
--------------------------------------------------------------------------------
See also:
II/328 : AllWISE Data Release (Cutri+ 2013)
Byte-by-byte Description of file: ocsvm_an.dat
--------------------------------------------------------------------------------
Bytes Format Units Label Explanations
--------------------------------------------------------------------------------
1- 19 A19 --- Name AllWISE identifier (JHHMMSS.ss+DDMMSS.s)
21- 31 F11.7 deg RAdeg Right ascension (J2000.0)
33- 43 F11.7 deg DEdeg Declination (J2000.0)
45- 50 F6.3 mag W1mag Instrumental profile-fit photometry
magnitude, band 1
52- 56 F5.3 mag e_W1mag Instrumental profile-fit photometry flux
uncertainty in mag units, band 1
58- 63 F6.3 mag W2mag Instrumental profile-fit photometry
magnitude, band 2
65- 69 F5.3 mag e_W2mag Instrumental profile-fit photometry flux
uncertainty in mag units, band 2
71- 76 F6.3 mag W3mag ?=- Instrumental profile-fit photometry
magnitude, band 3
78- 82 F5.3 mag e_W3mag ?=- Instrumental profile-fit photometry flux
uncertainty in mag units, band 3
84- 89 F6.3 mag W1mag1 W1 5.5" radius aperture magnitude
91- 96 F6.3 mag W1mag3 W1 11.0" radius aperture magnitude
98-103 F6.3 mag W3corr ?=- Correction to W3 mag for objects with
W3 upper limits only (W3mag+0.75)
--------------------------------------------------------------------------------
Acknowledgements:
Aleksandra Solarz, aleksandra.solarz(at)ncbj.gov.pl
(End) Aleksandra Solarz [NCBJ, Poland], Patricia Vannier [CDS] 04-Jul-2017