Dependency based reasoning in a Dempster-Shafer theoretic framework

Rohitha Hewawasam, Kamal Premaratne

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

1 Citation (Scopus)

Abstract

Bayesian Networks (BNs) represent joint space probabilities compactly and enable one to carry out efficient inferencing. Although the Dempster-Shafer (DS) belief theoretic framework captures a wider class of imperfections, its utility in such graphical models is limited. This is mainly due to the requirement of having to maintain a basic probability assignment (BPA) for the whole power set of propositions of interest. In this paper, we introduce a simpler BPA that can still capture many types of imperfections that are commonly encountered in practice. This BPA is then used to develop the DS-BN, a graphical dependency model that represents the joint space belief distribution. We show how this DS-BN can efficiently carry out inferences within the DS theoretic framework. Its utility is illustrated by modeling a problem involving missing values and then comparing the inferences made with those obtained via a BN that learns its parameters using the EM algorithm.

Original languageEnglish
Title of host publicationFUSION 2007 - 2007 10th International Conference on Information Fusion
DOIs
StatePublished - Dec 1 2007
EventFUSION 2007 - 2007 10th International Conference on Information Fusion - Quebec, QC, Canada
Duration: Jul 9 2007Jul 12 2007

Other

OtherFUSION 2007 - 2007 10th International Conference on Information Fusion
CountryCanada
CityQuebec, QC
Period7/9/077/12/07

Fingerprint

Bayesian networks
Defects

Keywords

  • Belief network
  • Data imperfection
  • Dempster shafer theory
  • Learning

ASJC Scopus subject areas

  • Hardware and Architecture
  • Information Systems
  • Signal Processing
  • Software

Cite this

Hewawasam, R., & Premaratne, K. (2007). Dependency based reasoning in a Dempster-Shafer theoretic framework. In FUSION 2007 - 2007 10th International Conference on Information Fusion [4408135] https://doi.org/10.1109/ICIF.2007.4408135

Dependency based reasoning in a Dempster-Shafer theoretic framework. / Hewawasam, Rohitha; Premaratne, Kamal.

FUSION 2007 - 2007 10th International Conference on Information Fusion. 2007. 4408135.

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

Hewawasam, R & Premaratne, K 2007, Dependency based reasoning in a Dempster-Shafer theoretic framework. in FUSION 2007 - 2007 10th International Conference on Information Fusion., 4408135, FUSION 2007 - 2007 10th International Conference on Information Fusion, Quebec, QC, Canada, 7/9/07. https://doi.org/10.1109/ICIF.2007.4408135
Hewawasam R, Premaratne K. Dependency based reasoning in a Dempster-Shafer theoretic framework. In FUSION 2007 - 2007 10th International Conference on Information Fusion. 2007. 4408135 https://doi.org/10.1109/ICIF.2007.4408135
Hewawasam, Rohitha ; Premaratne, Kamal. / Dependency based reasoning in a Dempster-Shafer theoretic framework. FUSION 2007 - 2007 10th International Conference on Information Fusion. 2007.
@inproceedings{eff5042ae1db4d4ea363e8fb7f6c0c41,
title = "Dependency based reasoning in a Dempster-Shafer theoretic framework",
abstract = "Bayesian Networks (BNs) represent joint space probabilities compactly and enable one to carry out efficient inferencing. Although the Dempster-Shafer (DS) belief theoretic framework captures a wider class of imperfections, its utility in such graphical models is limited. This is mainly due to the requirement of having to maintain a basic probability assignment (BPA) for the whole power set of propositions of interest. In this paper, we introduce a simpler BPA that can still capture many types of imperfections that are commonly encountered in practice. This BPA is then used to develop the DS-BN, a graphical dependency model that represents the joint space belief distribution. We show how this DS-BN can efficiently carry out inferences within the DS theoretic framework. Its utility is illustrated by modeling a problem involving missing values and then comparing the inferences made with those obtained via a BN that learns its parameters using the EM algorithm.",
keywords = "Belief network, Data imperfection, Dempster shafer theory, Learning",
author = "Rohitha Hewawasam and Kamal Premaratne",
year = "2007",
month = "12",
day = "1",
doi = "10.1109/ICIF.2007.4408135",
language = "English",
isbn = "0662478304",
booktitle = "FUSION 2007 - 2007 10th International Conference on Information Fusion",

}

TY - GEN

T1 - Dependency based reasoning in a Dempster-Shafer theoretic framework

AU - Hewawasam, Rohitha

AU - Premaratne, Kamal

PY - 2007/12/1

Y1 - 2007/12/1

N2 - Bayesian Networks (BNs) represent joint space probabilities compactly and enable one to carry out efficient inferencing. Although the Dempster-Shafer (DS) belief theoretic framework captures a wider class of imperfections, its utility in such graphical models is limited. This is mainly due to the requirement of having to maintain a basic probability assignment (BPA) for the whole power set of propositions of interest. In this paper, we introduce a simpler BPA that can still capture many types of imperfections that are commonly encountered in practice. This BPA is then used to develop the DS-BN, a graphical dependency model that represents the joint space belief distribution. We show how this DS-BN can efficiently carry out inferences within the DS theoretic framework. Its utility is illustrated by modeling a problem involving missing values and then comparing the inferences made with those obtained via a BN that learns its parameters using the EM algorithm.

AB - Bayesian Networks (BNs) represent joint space probabilities compactly and enable one to carry out efficient inferencing. Although the Dempster-Shafer (DS) belief theoretic framework captures a wider class of imperfections, its utility in such graphical models is limited. This is mainly due to the requirement of having to maintain a basic probability assignment (BPA) for the whole power set of propositions of interest. In this paper, we introduce a simpler BPA that can still capture many types of imperfections that are commonly encountered in practice. This BPA is then used to develop the DS-BN, a graphical dependency model that represents the joint space belief distribution. We show how this DS-BN can efficiently carry out inferences within the DS theoretic framework. Its utility is illustrated by modeling a problem involving missing values and then comparing the inferences made with those obtained via a BN that learns its parameters using the EM algorithm.

KW - Belief network

KW - Data imperfection

KW - Dempster shafer theory

KW - Learning

UR - http://www.scopus.com/inward/record.url?scp=50149092180&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=50149092180&partnerID=8YFLogxK

U2 - 10.1109/ICIF.2007.4408135

DO - 10.1109/ICIF.2007.4408135

M3 - Conference contribution

SN - 0662478304

SN - 9780662478300

BT - FUSION 2007 - 2007 10th International Conference on Information Fusion

ER -