Inference Degradation of Active Information Fusion within Bayesian Network Models

Xiangyang Li
Additional contact information
Xiangyang Li: University of Michigan – Dearborn, USA

International Journal of Intelligent Information Technologies (IJIIT), 2008, vol. 4, issue 4, 1-17

Abstract: Bayesian networks have been extensively used in active information fusion that selects the best sensor based on expected utility calculation. However, inference degradation happens when the same sensors are selected repeatedly over time if the applied strategy is not well designed to consider the history of sensor engagement. This phenomenon decreases fusion accuracy and efficiency, in direct conflict to the objective of information integration with multiple sensors. This paper provides mathematical scrutiny of the inference degradation problem in the popular myopia planning. It examines the generic dynamic Bayesian network models and shows experimentation results for mental state recognition tasks. It also discusses the candidate solutions with initial results. The inference degradation problem is not limited to the discussed fusion tasks and may emerge in variants of sensor planning strategies with more global optimization approach. This study provides common guidelines in information integration applications for information awareness and intelligent decision.

Date: 2008
References: Add references at CitEc
Citations:

Downloads: (external link)
http://services.igi-global.com/resolvedoi/resolve. ... 4018/jiit.2008100101 (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:igg:jiit00:v:4:y:2008:i:4:p:1-17

Access Statistics for this article

International Journal of Intelligent Information Technologies (IJIIT) is currently edited by Vijayan Sugumaran

More articles in International Journal of Intelligent Information Technologies (IJIIT) from IGI Global
Bibliographic data for series maintained by Journal Editor ().