Consensus-based credibility estimation of soft evidence for robust data fusion

Thanuka L. Wickramarathne, Kamal Premaratne, Manohar Murthi

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

7 Citations (Scopus)

Abstract

Due to its subjective naturewhich can otherwise compromise the integrity of the fusion process, it is critical that soft evidence (generated by human sources) be validated prior to its incorporation into the fusion engine. The strategy of discounting evidence based on source reliability may not be applicable when dealing with soft sources because their reliability (e.g., an eye witnesses account) is often unknown beforehand. In this paper, we propose a methodology based on the notion of consensus to estimate the credibility of (soft) evidence in the absence of a 'ground truth.' This estimated credibility can then be used for source reliability estimation, discounting or appropriately 'weighting' evidence for fusion. The consensus procedure is set up via Dempster-Shafer belief theoretic notions. Further, the proposed procedure allows one to constrain the consensus by an estimate of the ground truth if/when it is available. We illustrate several interesting and intuitively appealing properties of the consensus procedure via a numerical example.

Original languageEnglish
Title of host publicationAdvances in Intelligent and Soft Computing
Pages301-309
Number of pages9
Volume164 AISC
DOIs
StatePublished - May 18 2012
Event2nd International Conferenceon Belief Functions - Compiegne, France
Duration: May 9 2012May 11 2012

Publication series

NameAdvances in Intelligent and Soft Computing
Volume164 AISC
ISSN (Print)18675662

Other

Other2nd International Conferenceon Belief Functions
CountryFrance
CityCompiegne
Period5/9/125/11/12

Fingerprint

Data fusion
Engines

ASJC Scopus subject areas

  • Computer Science(all)

Cite this

Wickramarathne, T. L., Premaratne, K., & Murthi, M. (2012). Consensus-based credibility estimation of soft evidence for robust data fusion. In Advances in Intelligent and Soft Computing (Vol. 164 AISC, pp. 301-309). (Advances in Intelligent and Soft Computing; Vol. 164 AISC). https://doi.org/10.1007/978-3-642-29461-7_35

Consensus-based credibility estimation of soft evidence for robust data fusion. / Wickramarathne, Thanuka L.; Premaratne, Kamal; Murthi, Manohar.

Advances in Intelligent and Soft Computing. Vol. 164 AISC 2012. p. 301-309 (Advances in Intelligent and Soft Computing; Vol. 164 AISC).

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

Wickramarathne, TL, Premaratne, K & Murthi, M 2012, Consensus-based credibility estimation of soft evidence for robust data fusion. in Advances in Intelligent and Soft Computing. vol. 164 AISC, Advances in Intelligent and Soft Computing, vol. 164 AISC, pp. 301-309, 2nd International Conferenceon Belief Functions, Compiegne, France, 5/9/12. https://doi.org/10.1007/978-3-642-29461-7_35
Wickramarathne TL, Premaratne K, Murthi M. Consensus-based credibility estimation of soft evidence for robust data fusion. In Advances in Intelligent and Soft Computing. Vol. 164 AISC. 2012. p. 301-309. (Advances in Intelligent and Soft Computing). https://doi.org/10.1007/978-3-642-29461-7_35
Wickramarathne, Thanuka L. ; Premaratne, Kamal ; Murthi, Manohar. / Consensus-based credibility estimation of soft evidence for robust data fusion. Advances in Intelligent and Soft Computing. Vol. 164 AISC 2012. pp. 301-309 (Advances in Intelligent and Soft Computing).
@inproceedings{24ef17843be142928ed65fb7996c7c2a,
title = "Consensus-based credibility estimation of soft evidence for robust data fusion",
abstract = "Due to its subjective naturewhich can otherwise compromise the integrity of the fusion process, it is critical that soft evidence (generated by human sources) be validated prior to its incorporation into the fusion engine. The strategy of discounting evidence based on source reliability may not be applicable when dealing with soft sources because their reliability (e.g., an eye witnesses account) is often unknown beforehand. In this paper, we propose a methodology based on the notion of consensus to estimate the credibility of (soft) evidence in the absence of a 'ground truth.' This estimated credibility can then be used for source reliability estimation, discounting or appropriately 'weighting' evidence for fusion. The consensus procedure is set up via Dempster-Shafer belief theoretic notions. Further, the proposed procedure allows one to constrain the consensus by an estimate of the ground truth if/when it is available. We illustrate several interesting and intuitively appealing properties of the consensus procedure via a numerical example.",
author = "Wickramarathne, {Thanuka L.} and Kamal Premaratne and Manohar Murthi",
year = "2012",
month = "5",
day = "18",
doi = "10.1007/978-3-642-29461-7_35",
language = "English",
isbn = "9783642294600",
volume = "164 AISC",
series = "Advances in Intelligent and Soft Computing",
pages = "301--309",
booktitle = "Advances in Intelligent and Soft Computing",

}

TY - GEN

T1 - Consensus-based credibility estimation of soft evidence for robust data fusion

AU - Wickramarathne, Thanuka L.

AU - Premaratne, Kamal

AU - Murthi, Manohar

PY - 2012/5/18

Y1 - 2012/5/18

N2 - Due to its subjective naturewhich can otherwise compromise the integrity of the fusion process, it is critical that soft evidence (generated by human sources) be validated prior to its incorporation into the fusion engine. The strategy of discounting evidence based on source reliability may not be applicable when dealing with soft sources because their reliability (e.g., an eye witnesses account) is often unknown beforehand. In this paper, we propose a methodology based on the notion of consensus to estimate the credibility of (soft) evidence in the absence of a 'ground truth.' This estimated credibility can then be used for source reliability estimation, discounting or appropriately 'weighting' evidence for fusion. The consensus procedure is set up via Dempster-Shafer belief theoretic notions. Further, the proposed procedure allows one to constrain the consensus by an estimate of the ground truth if/when it is available. We illustrate several interesting and intuitively appealing properties of the consensus procedure via a numerical example.

AB - Due to its subjective naturewhich can otherwise compromise the integrity of the fusion process, it is critical that soft evidence (generated by human sources) be validated prior to its incorporation into the fusion engine. The strategy of discounting evidence based on source reliability may not be applicable when dealing with soft sources because their reliability (e.g., an eye witnesses account) is often unknown beforehand. In this paper, we propose a methodology based on the notion of consensus to estimate the credibility of (soft) evidence in the absence of a 'ground truth.' This estimated credibility can then be used for source reliability estimation, discounting or appropriately 'weighting' evidence for fusion. The consensus procedure is set up via Dempster-Shafer belief theoretic notions. Further, the proposed procedure allows one to constrain the consensus by an estimate of the ground truth if/when it is available. We illustrate several interesting and intuitively appealing properties of the consensus procedure via a numerical example.

UR - http://www.scopus.com/inward/record.url?scp=84860992329&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84860992329&partnerID=8YFLogxK

U2 - 10.1007/978-3-642-29461-7_35

DO - 10.1007/978-3-642-29461-7_35

M3 - Conference contribution

AN - SCOPUS:84860992329

SN - 9783642294600

VL - 164 AISC

T3 - Advances in Intelligent and Soft Computing

SP - 301

EP - 309

BT - Advances in Intelligent and Soft Computing

ER -