A hybrid neural network-fuzzy logic architecture for multisensor data fusion in target tracking system
Authors
Xiu Wang1, Jian Rong, Xiaochun Zhong
1School of Physical Electronic, University of Electronic Science and Technology of China
Corresponding Author
Xiu Wang
Available Online October 2007.
- DOI
- 10.2991/iske.2007.208How to use a DOI?
- Keywords
- Neural network, Fuzzy logic, Multisensor data fusion, Target tracking
- Abstract
In this work, a new multisensor data fusion architecture integrating neural network and fuzzy logic techniques is introduced, which has the ability of fast adjusting acceleration parameter and covariance of measurement noise of sensors. In this architecture, the neural network estimates acceleration and fuzzy logic adapts the covariance of measurement noise on-line and also offers degree of confidence of sensors for fusion. The results of simulation prove this new architecture can adjust maneuver parameter in nearly one sample time and change the covariance of measurement noise effectively.
- Copyright
- © 2007, the Authors. Published by Atlantis Press.
- Open Access
- This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).
Cite this article
TY - CONF AU - Xiu Wang AU - Jian Rong AU - Xiaochun Zhong PY - 2007/10 DA - 2007/10 TI - A hybrid neural network-fuzzy logic architecture for multisensor data fusion in target tracking system BT - Proceedings of the 2007 International Conference on Intelligent Systems and Knowledge Engineering (ISKE 2007) PB - Atlantis Press SP - 1222 EP - 1229 SN - 1951-6851 UR - https://doi.org/10.2991/iske.2007.208 DO - 10.2991/iske.2007.208 ID - Wang2007/10 ER -