Belief theoretic methods for soft and hard data fusion

T. L. Wickramarathne, Kamal Premaratne, Manohar Murthi, M. Scheutz, S. Kübler, M. Pravia

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

19 Citations (Scopus)

Abstract

In many contexts, one is confronted with the problem of extracting information from large amounts of different types soft data (e.g., text) and hard data (from e.g., physics-based sensing systems). In handling hard data, signal and data processing offers a wealth of methods related to modeling, estimation, tracking, and inference tasks. However, soft data present several challenges that necessitate the development of new data processing methods. For example, with suitable statistical natural language processing (NLP) methods, text can be converted into logic statements that are associated with various forms of associated uncertainty related to the credibility of the statement, the reliability of the text source, and so forth. In combining or fusing soft data with either soft or hard data, one must deploy methods that can suitably preserve and update the uncertainty associated with the data, thereby providing uncertainty bounds related to any inferences regarding semantics. Since standard Bayesian probabilistic approaches have problems with suitably handling uncertain logic statements, there is an emerging need for new methods for processing heterogeneous data. In this paper, we describe a framework for fusing soft and hard data based on the Dempster-Shafer (DS) belief theoretic approach which is well-suited to the task of capturing the types of models and uncertain rules that are more typical of soft data. Since the effectiveness of traditional DS methods has been hampered by high computational requirements, we base the processing framework on our new conditional approach to DS theoretic evidence updating and fusion. We address the issue of laying the foundation for a theoretically justifiable, and computationally efficient framework for fusing soft and hard data taking into account the inherent data uncertainty such as reliability and credibility. Moreover, we present an illustrative example that highlights the potential for the DS conditional approach for fusing heterogeneous data.

Original languageEnglish
Title of host publicationICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Pages2388-2391
Number of pages4
DOIs
StatePublished - Aug 18 2011
Event36th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2011 - Prague, Czech Republic
Duration: May 22 2011May 27 2011

Other

Other36th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2011
CountryCzech Republic
CityPrague
Period5/22/115/27/11

Fingerprint

Data fusion
Processing
Signal processing
Physics
Semantics
Uncertainty

Keywords

  • Dempster-Shafer belief theory
  • evidence fusion
  • evidence updating
  • soft information

ASJC Scopus subject areas

  • Signal Processing
  • Software
  • Electrical and Electronic Engineering

Cite this

Wickramarathne, T. L., Premaratne, K., Murthi, M., Scheutz, M., Kübler, S., & Pravia, M. (2011). Belief theoretic methods for soft and hard data fusion. In ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings (pp. 2388-2391). [5946964] https://doi.org/10.1109/ICASSP.2011.5946964

Belief theoretic methods for soft and hard data fusion. / Wickramarathne, T. L.; Premaratne, Kamal; Murthi, Manohar; Scheutz, M.; Kübler, S.; Pravia, M.

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. 2011. p. 2388-2391 5946964.

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

Wickramarathne, TL, Premaratne, K, Murthi, M, Scheutz, M, Kübler, S & Pravia, M 2011, Belief theoretic methods for soft and hard data fusion. in ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings., 5946964, pp. 2388-2391, 36th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2011, Prague, Czech Republic, 5/22/11. https://doi.org/10.1109/ICASSP.2011.5946964
Wickramarathne TL, Premaratne K, Murthi M, Scheutz M, Kübler S, Pravia M. Belief theoretic methods for soft and hard data fusion. In ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. 2011. p. 2388-2391. 5946964 https://doi.org/10.1109/ICASSP.2011.5946964
Wickramarathne, T. L. ; Premaratne, Kamal ; Murthi, Manohar ; Scheutz, M. ; Kübler, S. ; Pravia, M. / Belief theoretic methods for soft and hard data fusion. ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. 2011. pp. 2388-2391
@inproceedings{71c8f948910747faae5ffdec853b3fad,
title = "Belief theoretic methods for soft and hard data fusion",
abstract = "In many contexts, one is confronted with the problem of extracting information from large amounts of different types soft data (e.g., text) and hard data (from e.g., physics-based sensing systems). In handling hard data, signal and data processing offers a wealth of methods related to modeling, estimation, tracking, and inference tasks. However, soft data present several challenges that necessitate the development of new data processing methods. For example, with suitable statistical natural language processing (NLP) methods, text can be converted into logic statements that are associated with various forms of associated uncertainty related to the credibility of the statement, the reliability of the text source, and so forth. In combining or fusing soft data with either soft or hard data, one must deploy methods that can suitably preserve and update the uncertainty associated with the data, thereby providing uncertainty bounds related to any inferences regarding semantics. Since standard Bayesian probabilistic approaches have problems with suitably handling uncertain logic statements, there is an emerging need for new methods for processing heterogeneous data. In this paper, we describe a framework for fusing soft and hard data based on the Dempster-Shafer (DS) belief theoretic approach which is well-suited to the task of capturing the types of models and uncertain rules that are more typical of soft data. Since the effectiveness of traditional DS methods has been hampered by high computational requirements, we base the processing framework on our new conditional approach to DS theoretic evidence updating and fusion. We address the issue of laying the foundation for a theoretically justifiable, and computationally efficient framework for fusing soft and hard data taking into account the inherent data uncertainty such as reliability and credibility. Moreover, we present an illustrative example that highlights the potential for the DS conditional approach for fusing heterogeneous data.",
keywords = "Dempster-Shafer belief theory, evidence fusion, evidence updating, soft information",
author = "Wickramarathne, {T. L.} and Kamal Premaratne and Manohar Murthi and M. Scheutz and S. K{\"u}bler and M. Pravia",
year = "2011",
month = "8",
day = "18",
doi = "10.1109/ICASSP.2011.5946964",
language = "English",
isbn = "9781457705397",
pages = "2388--2391",
booktitle = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",

}

TY - GEN

T1 - Belief theoretic methods for soft and hard data fusion

AU - Wickramarathne, T. L.

AU - Premaratne, Kamal

AU - Murthi, Manohar

AU - Scheutz, M.

AU - Kübler, S.

AU - Pravia, M.

PY - 2011/8/18

Y1 - 2011/8/18

N2 - In many contexts, one is confronted with the problem of extracting information from large amounts of different types soft data (e.g., text) and hard data (from e.g., physics-based sensing systems). In handling hard data, signal and data processing offers a wealth of methods related to modeling, estimation, tracking, and inference tasks. However, soft data present several challenges that necessitate the development of new data processing methods. For example, with suitable statistical natural language processing (NLP) methods, text can be converted into logic statements that are associated with various forms of associated uncertainty related to the credibility of the statement, the reliability of the text source, and so forth. In combining or fusing soft data with either soft or hard data, one must deploy methods that can suitably preserve and update the uncertainty associated with the data, thereby providing uncertainty bounds related to any inferences regarding semantics. Since standard Bayesian probabilistic approaches have problems with suitably handling uncertain logic statements, there is an emerging need for new methods for processing heterogeneous data. In this paper, we describe a framework for fusing soft and hard data based on the Dempster-Shafer (DS) belief theoretic approach which is well-suited to the task of capturing the types of models and uncertain rules that are more typical of soft data. Since the effectiveness of traditional DS methods has been hampered by high computational requirements, we base the processing framework on our new conditional approach to DS theoretic evidence updating and fusion. We address the issue of laying the foundation for a theoretically justifiable, and computationally efficient framework for fusing soft and hard data taking into account the inherent data uncertainty such as reliability and credibility. Moreover, we present an illustrative example that highlights the potential for the DS conditional approach for fusing heterogeneous data.

AB - In many contexts, one is confronted with the problem of extracting information from large amounts of different types soft data (e.g., text) and hard data (from e.g., physics-based sensing systems). In handling hard data, signal and data processing offers a wealth of methods related to modeling, estimation, tracking, and inference tasks. However, soft data present several challenges that necessitate the development of new data processing methods. For example, with suitable statistical natural language processing (NLP) methods, text can be converted into logic statements that are associated with various forms of associated uncertainty related to the credibility of the statement, the reliability of the text source, and so forth. In combining or fusing soft data with either soft or hard data, one must deploy methods that can suitably preserve and update the uncertainty associated with the data, thereby providing uncertainty bounds related to any inferences regarding semantics. Since standard Bayesian probabilistic approaches have problems with suitably handling uncertain logic statements, there is an emerging need for new methods for processing heterogeneous data. In this paper, we describe a framework for fusing soft and hard data based on the Dempster-Shafer (DS) belief theoretic approach which is well-suited to the task of capturing the types of models and uncertain rules that are more typical of soft data. Since the effectiveness of traditional DS methods has been hampered by high computational requirements, we base the processing framework on our new conditional approach to DS theoretic evidence updating and fusion. We address the issue of laying the foundation for a theoretically justifiable, and computationally efficient framework for fusing soft and hard data taking into account the inherent data uncertainty such as reliability and credibility. Moreover, we present an illustrative example that highlights the potential for the DS conditional approach for fusing heterogeneous data.

KW - Dempster-Shafer belief theory

KW - evidence fusion

KW - evidence updating

KW - soft information

UR - http://www.scopus.com/inward/record.url?scp=80051652479&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80051652479&partnerID=8YFLogxK

U2 - 10.1109/ICASSP.2011.5946964

DO - 10.1109/ICASSP.2011.5946964

M3 - Conference contribution

AN - SCOPUS:80051652479

SN - 9781457705397

SP - 2388

EP - 2391

BT - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

ER -