Ship recognition based on improved forwards-backwards algorithm

Haiyang Chen; Xiaoguang Gao

doi:10.1109/FSKD.2009.336

Ship recognition based on improved forwards-backwards algorithm

Haiyang Chen, Xiaoguang Gao

School of Electronics and Information

Northwestern Polytechnical University Xian

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

10 Scopus citations

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.

Original language	English
Title of host publication	6th International Conference on Fuzzy Systems and Knowledge Discovery, FSKD 2009
Pages	509-513
Number of pages	5
DOIs	https://doi.org/10.1109/FSKD.2009.336
State	Published - 2009
Event	6th International Conference on Fuzzy Systems and Knowledge Discovery, FSKD 2009 - Tianjin, China Duration: 14 Aug 2009 → 16 Aug 2009

Publication series

Name	6th International Conference on Fuzzy Systems and Knowledge Discovery, FSKD 2009
Volume	5

Conference

Conference	6th International Conference on Fuzzy Systems and Knowledge Discovery, FSKD 2009
Country/Territory	China
City	Tianjin
Period	14/08/09 → 16/08/09

Keywords

Discrete dynamic bayesian networks
Forwards-backwards algorithm
Membership degree
Target recognition

Access to Document

10.1109/FSKD.2009.336

Cite this

@inproceedings{47da0cd166c64bcebc819904f240247a,

title = "Ship recognition based on improved forwards-backwards algorithm",

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.",

keywords = "Discrete dynamic bayesian networks, Forwards-backwards algorithm, Membership degree, Target recognition",

author = "Haiyang Chen and Xiaoguang Gao",

year = "2009",

doi = "10.1109/FSKD.2009.336",

language = "英语",

isbn = "9780769537351",

series = "6th International Conference on Fuzzy Systems and Knowledge Discovery, FSKD 2009",

pages = "509--513",

booktitle = "6th International Conference on Fuzzy Systems and Knowledge Discovery, FSKD 2009",

note = "6th International Conference on Fuzzy Systems and Knowledge Discovery, FSKD 2009 ; Conference date: 14-08-2009 Through 16-08-2009",

}

Chen, H & Gao, X 2009, Ship recognition based on improved forwards-backwards algorithm. in 6th International Conference on Fuzzy Systems and Knowledge Discovery, FSKD 2009., 5360568, 6th International Conference on Fuzzy Systems and Knowledge Discovery, FSKD 2009, vol. 5, pp. 509-513, 6th International Conference on Fuzzy Systems and Knowledge Discovery, FSKD 2009, Tianjin, China, 14/08/09. https://doi.org/10.1109/FSKD.2009.336

Ship recognition based on improved forwards-backwards algorithm. / Chen, Haiyang; Gao, Xiaoguang.
6th International Conference on Fuzzy Systems and Knowledge Discovery, FSKD 2009. 2009. p. 509-513 5360568 (6th International Conference on Fuzzy Systems and Knowledge Discovery, FSKD 2009; Vol. 5).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Ship recognition based on improved forwards-backwards algorithm

AU - Chen, Haiyang

AU - Gao, Xiaoguang

PY - 2009

Y1 - 2009

N2 - 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.

AB - 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.

KW - Discrete dynamic bayesian networks

KW - Forwards-backwards algorithm

KW - Membership degree

KW - Target recognition

UR - http://www.scopus.com/inward/record.url?scp=76549115566&partnerID=8YFLogxK

U2 - 10.1109/FSKD.2009.336

DO - 10.1109/FSKD.2009.336

M3 - 会议稿件

AN - SCOPUS:76549115566

SN - 9780769537351

T3 - 6th International Conference on Fuzzy Systems and Knowledge Discovery, FSKD 2009

SP - 509

EP - 513

BT - 6th International Conference on Fuzzy Systems and Knowledge Discovery, FSKD 2009

T2 - 6th International Conference on Fuzzy Systems and Knowledge Discovery, FSKD 2009

Y2 - 14 August 2009 through 16 August 2009

ER -

Ship recognition based on improved forwards-backwards algorithm

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this