Expertise evaluation using PathFinder networks scaling in ranking of satellite images

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In this article we propose a methodology to evaluate the level of expertise of image analysts when searching domain-specific images by semantics. We apply our methodology to ranking high-resolution satellite images by semantics. Our methodology applies PathFinder Network Scaling methods to create concept maps for representing associations of semantics to regions of a feature space for each image analyst. The relevance of each node in a concept map is evaluated using a hits authority algorithm. The expertise of each image analyst is then evaluated by comparing to ground truth models using the Kendall tau rank correlation coefficient. Our system allows us to identify areas of expert disagreement by evaluating the relative difference individual models place on features as well as recommend areas of that needs to be stressed by novice image analysts.

Original languageEnglish (US)
Title of host publicationIMSCI 2013 - 7th International Multi-Conference on Society, Cybernetics and Informatics, Proceedings
PublisherInternational Institute of Informatics and Systemics, IIIS
Pages147-152
Number of pages6
ISBN (Print)9781936338832
StatePublished - Jan 1 2013
Event7th International Multi-Conference on Society, Cybernetics and Informatics, IMSCI 2013 - Orlando, FL, United States
Duration: Jul 9 2013Jul 12 2013

Publication series

NameIMSCI 2013 - 7th International Multi-Conference on Society, Cybernetics and Informatics, Proceedings

Other

Other7th International Multi-Conference on Society, Cybernetics and Informatics, IMSCI 2013
CountryUnited States
CityOrlando, FL
Period7/9/137/12/13

Fingerprint

Semantics
Satellites

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence
  • Information Systems

Cite this

Barb, A. S. (2013). Expertise evaluation using PathFinder networks scaling in ranking of satellite images. In IMSCI 2013 - 7th International Multi-Conference on Society, Cybernetics and Informatics, Proceedings (pp. 147-152). (IMSCI 2013 - 7th International Multi-Conference on Society, Cybernetics and Informatics, Proceedings). International Institute of Informatics and Systemics, IIIS.
Barb, Adrian Sorin. / Expertise evaluation using PathFinder networks scaling in ranking of satellite images. IMSCI 2013 - 7th International Multi-Conference on Society, Cybernetics and Informatics, Proceedings. International Institute of Informatics and Systemics, IIIS, 2013. pp. 147-152 (IMSCI 2013 - 7th International Multi-Conference on Society, Cybernetics and Informatics, Proceedings).
@inproceedings{7b1cff2e309c4fabb36e076b54ad6bf2,
title = "Expertise evaluation using PathFinder networks scaling in ranking of satellite images",
abstract = "In this article we propose a methodology to evaluate the level of expertise of image analysts when searching domain-specific images by semantics. We apply our methodology to ranking high-resolution satellite images by semantics. Our methodology applies PathFinder Network Scaling methods to create concept maps for representing associations of semantics to regions of a feature space for each image analyst. The relevance of each node in a concept map is evaluated using a hits authority algorithm. The expertise of each image analyst is then evaluated by comparing to ground truth models using the Kendall tau rank correlation coefficient. Our system allows us to identify areas of expert disagreement by evaluating the relative difference individual models place on features as well as recommend areas of that needs to be stressed by novice image analysts.",
author = "Barb, {Adrian Sorin}",
year = "2013",
month = "1",
day = "1",
language = "English (US)",
isbn = "9781936338832",
series = "IMSCI 2013 - 7th International Multi-Conference on Society, Cybernetics and Informatics, Proceedings",
publisher = "International Institute of Informatics and Systemics, IIIS",
pages = "147--152",
booktitle = "IMSCI 2013 - 7th International Multi-Conference on Society, Cybernetics and Informatics, Proceedings",

}

Barb, AS 2013, Expertise evaluation using PathFinder networks scaling in ranking of satellite images. in IMSCI 2013 - 7th International Multi-Conference on Society, Cybernetics and Informatics, Proceedings. IMSCI 2013 - 7th International Multi-Conference on Society, Cybernetics and Informatics, Proceedings, International Institute of Informatics and Systemics, IIIS, pp. 147-152, 7th International Multi-Conference on Society, Cybernetics and Informatics, IMSCI 2013, Orlando, FL, United States, 7/9/13.

Expertise evaluation using PathFinder networks scaling in ranking of satellite images. / Barb, Adrian Sorin.

IMSCI 2013 - 7th International Multi-Conference on Society, Cybernetics and Informatics, Proceedings. International Institute of Informatics and Systemics, IIIS, 2013. p. 147-152 (IMSCI 2013 - 7th International Multi-Conference on Society, Cybernetics and Informatics, Proceedings).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Expertise evaluation using PathFinder networks scaling in ranking of satellite images

AU - Barb, Adrian Sorin

PY - 2013/1/1

Y1 - 2013/1/1

N2 - In this article we propose a methodology to evaluate the level of expertise of image analysts when searching domain-specific images by semantics. We apply our methodology to ranking high-resolution satellite images by semantics. Our methodology applies PathFinder Network Scaling methods to create concept maps for representing associations of semantics to regions of a feature space for each image analyst. The relevance of each node in a concept map is evaluated using a hits authority algorithm. The expertise of each image analyst is then evaluated by comparing to ground truth models using the Kendall tau rank correlation coefficient. Our system allows us to identify areas of expert disagreement by evaluating the relative difference individual models place on features as well as recommend areas of that needs to be stressed by novice image analysts.

AB - In this article we propose a methodology to evaluate the level of expertise of image analysts when searching domain-specific images by semantics. We apply our methodology to ranking high-resolution satellite images by semantics. Our methodology applies PathFinder Network Scaling methods to create concept maps for representing associations of semantics to regions of a feature space for each image analyst. The relevance of each node in a concept map is evaluated using a hits authority algorithm. The expertise of each image analyst is then evaluated by comparing to ground truth models using the Kendall tau rank correlation coefficient. Our system allows us to identify areas of expert disagreement by evaluating the relative difference individual models place on features as well as recommend areas of that needs to be stressed by novice image analysts.

UR - http://www.scopus.com/inward/record.url?scp=84896456487&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84896456487&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9781936338832

T3 - IMSCI 2013 - 7th International Multi-Conference on Society, Cybernetics and Informatics, Proceedings

SP - 147

EP - 152

BT - IMSCI 2013 - 7th International Multi-Conference on Society, Cybernetics and Informatics, Proceedings

PB - International Institute of Informatics and Systemics, IIIS

ER -

Barb AS. Expertise evaluation using PathFinder networks scaling in ranking of satellite images. In IMSCI 2013 - 7th International Multi-Conference on Society, Cybernetics and Informatics, Proceedings. International Institute of Informatics and Systemics, IIIS. 2013. p. 147-152. (IMSCI 2013 - 7th International Multi-Conference on Society, Cybernetics and Informatics, Proceedings).