Ship recognition based on improved forwards-backwards algorithm

Authors:
Haiyang Chen;Xiaoguang Gao
Affiliations:
School of Electronics and Information, Northwestern Polytechnical University, Xi'an, China;School of Electronics and Information, Northwestern Polytechnical University, Xi'an, China
Venue:
FSKD'09 Proceedings of the 6th international conference on Fuzzy systems and knowledge discovery - Volume 5
Year:
2009

Citing 2
Cited 0

Pattern Recognition for Ship Based on Bayesian Networks

FSKD '07 Proceedings of the Fourth International Conference on Fuzzy Systems and Knowledge Discovery - Volume 04
Artificial Intelligence: A Modern Approach

Artificial Intelligence: A Modern Approach

Quantified Score

Hi-index	0.00

Visualization

Abstract

Classical Forwards-Backwards (FB) algorithm can only be used to compute the input evidences with a single state. In order to break through its limitation, we presented a kind of improved FB algorithm to compute evidences with a single or more states, which generalized classical FB algorithm. First, we deduced the improved FB algorithm, then constructed fuzzy discrete dynamic Bayesian network model for ship recognition. This algorithm is very useful for effectively combining feature information to infer the type of the target accurately, which is proved by the simulation results. In addition, we can use the improved forwards algorithm to perform online reference, and the improved FB algorithm to perform offline reference and analysis, the accuracy of the target recognition can be ensured.