Dynamic hierarchical committee for mulitple agent decision in wireless sensor networks

Xue Wang; Sheng Wang; Aiguo Jiang

doi:10.1117/12.717523

6 November 2006 Dynamic hierarchical committee for mulitple agent decision in wireless sensor networks

Xue Wang, Sheng Wang, Aiguo Jiang

Proceedings Volume 6357, Sixth International Symposium on Instrumentation and Control Technology: Signal Analysis, Measurement Theory, Photo-Electronic Technology, and Artificial Intelligence; 635755 (2006) https://doi.org/10.1117/12.717523
Event: Sixth International Symposium on Instrumentation and Control Technology, 2006, Beijing, China

Abstract

Decision methods for information processing affect significantly the efficiency and accuracy of networked sensing in wireless sensor networks. Mobile agent technology supplies an efficient cooperation mechanism, which can compensate the poor capability of single node. This paper proposes a dynamic hierarchical committee for multiple agent decision, which is a two-level structure: in the lower level, several sub-committees, concluding a local decision respectively, are dynamically organized by the energy-efficient optimization of adapted genetic algorithm; local decisions of sub-committees are nonlinearly combined in the upper level. The performance of dynamic hierarchical committee is verified through simulation and practical defect location of printed circuit board. The results show the proposed method can remarkably decrease the energy consumption with sacrifice of real-time. The confidence and accuracy of decision is more precise than centralized non-committee method.

Citation Download Citation

Xue Wang, Sheng Wang, and Aiguo Jiang "Dynamic hierarchical committee for mulitple agent decision in wireless sensor networks", Proc. SPIE 6357, Sixth International Symposium on Instrumentation and Control Technology: Signal Analysis, Measurement Theory, Photo-Electronic Technology, and Artificial Intelligence, 635755 (6 November 2006); https://doi.org/10.1117/12.717523

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available