A source identification algorithm for INTEGRAL

Simone Scaringi; Antony J. Bird; David J. Clark; Anthony J. Dean; Adam B. Hill; Vanessa A. McBride; Simon E. Shaw

doi:10.1063/1.3059068

A source identification algorithm for INTEGRAL

Simone Scaringi, Antony J. Bird, David J. Clark, Anthony J. Dean, Adam B. Hill, Vanessa A. McBride, Simon E. Shaw

Physics

Research output: Contribution to journal › Conference article › peer-review

1 Scopus citations

Abstract

We give an overview of ISINA: INTEGRAL Source Identification Network Algorithm. This machine learning algorithm, using Random Forests, is applied to the IBIS/ISGRI dataset in order to ease the production of unbiased future soft gamma-ray source catalogues. The key steps of candidate searching, filtering and feature extraction are described. Three training and testing sets are created in order to deal with the diverse timescales and diverse objects encountered when dealing with the gamma-ray sky. Three independent Random Forest are built: one dealing with faint persistent source recognition, one dealing with strong persistent sources and a final one dealing with transients. For the latter, a new transient detection technique is introduced and described: the Transient Matrix. Finally the performance of the network is assessed and discussed using the testing set and some illustrative source examples.

Original language	English
Pages (from-to)	307-314
Number of pages	8
Journal	AIP Conference Proceedings
Volume	1082
DOIs	https://doi.org/10.1063/1.3059068
State	Published - 2008
Event	Classification and Discovery in Large Astronomical Surveys - Ringberg Castle, Germany Duration: Oct 14 2008 → Oct 17 2008

Keywords

Catalogues
Gamma-ray
Machine learning
Surveys
Transients

Access to Document

10.1063/1.3059068

Cite this

@article{e2ed34f9f51648458784fb5dd98879dd,

title = "A source identification algorithm for INTEGRAL",

abstract = "We give an overview of ISINA: INTEGRAL Source Identification Network Algorithm. This machine learning algorithm, using Random Forests, is applied to the IBIS/ISGRI dataset in order to ease the production of unbiased future soft gamma-ray source catalogues. The key steps of candidate searching, filtering and feature extraction are described. Three training and testing sets are created in order to deal with the diverse timescales and diverse objects encountered when dealing with the gamma-ray sky. Three independent Random Forest are built: one dealing with faint persistent source recognition, one dealing with strong persistent sources and a final one dealing with transients. For the latter, a new transient detection technique is introduced and described: the Transient Matrix. Finally the performance of the network is assessed and discussed using the testing set and some illustrative source examples.",

keywords = "Catalogues, Gamma-ray, Machine learning, Surveys, Transients",

author = "Simone Scaringi and Bird, {Antony J.} and Clark, {David J.} and Dean, {Anthony J.} and Hill, {Adam B.} and McBride, {Vanessa A.} and Shaw, {Simon E.}",

year = "2008",

doi = "10.1063/1.3059068",

language = "English",

volume = "1082",

pages = "307--314",

journal = "AIP Conference Proceedings",

issn = "0094-243X",

note = "Classification and Discovery in Large Astronomical Surveys ; Conference date: 14-10-2008 Through 17-10-2008",

}

TY - JOUR

T1 - A source identification algorithm for INTEGRAL

AU - Scaringi, Simone

AU - Bird, Antony J.

AU - Clark, David J.

AU - Dean, Anthony J.

AU - Hill, Adam B.

AU - McBride, Vanessa A.

AU - Shaw, Simon E.

PY - 2008

Y1 - 2008

N2 - We give an overview of ISINA: INTEGRAL Source Identification Network Algorithm. This machine learning algorithm, using Random Forests, is applied to the IBIS/ISGRI dataset in order to ease the production of unbiased future soft gamma-ray source catalogues. The key steps of candidate searching, filtering and feature extraction are described. Three training and testing sets are created in order to deal with the diverse timescales and diverse objects encountered when dealing with the gamma-ray sky. Three independent Random Forest are built: one dealing with faint persistent source recognition, one dealing with strong persistent sources and a final one dealing with transients. For the latter, a new transient detection technique is introduced and described: the Transient Matrix. Finally the performance of the network is assessed and discussed using the testing set and some illustrative source examples.

AB - We give an overview of ISINA: INTEGRAL Source Identification Network Algorithm. This machine learning algorithm, using Random Forests, is applied to the IBIS/ISGRI dataset in order to ease the production of unbiased future soft gamma-ray source catalogues. The key steps of candidate searching, filtering and feature extraction are described. Three training and testing sets are created in order to deal with the diverse timescales and diverse objects encountered when dealing with the gamma-ray sky. Three independent Random Forest are built: one dealing with faint persistent source recognition, one dealing with strong persistent sources and a final one dealing with transients. For the latter, a new transient detection technique is introduced and described: the Transient Matrix. Finally the performance of the network is assessed and discussed using the testing set and some illustrative source examples.

KW - Catalogues

KW - Gamma-ray

KW - Machine learning

KW - Surveys

KW - Transients

UR - http://www.scopus.com/inward/record.url?scp=61849146248&partnerID=8YFLogxK

U2 - 10.1063/1.3059068

DO - 10.1063/1.3059068

M3 - Conference article

AN - SCOPUS:61849146248

SN - 0094-243X

VL - 1082

SP - 307

EP - 314

JO - AIP Conference Proceedings

JF - AIP Conference Proceedings

T2 - Classification and Discovery in Large Astronomical Surveys

Y2 - 14 October 2008 through 17 October 2008

ER -

A source identification algorithm for INTEGRAL

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this