Method of Learning Dynamic Bayesian Network Parameter Based on DEQPK Algorithm

Weinan Li; Jingping Shi; Weiguo Zhang; Yunyan Wu

doi:10.1007/978-981-19-6613-2_138

Method of Learning Dynamic Bayesian Network Parameter Based on DEQPK Algorithm

Weinan Li, Jingping Shi, Weiguo Zhang, Yunyan Wu

School of Automation

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

Abstract

For the problem of DBN parameter learning from small sample data, a differential evolution based on qualitative prior knowledge (DEQPK) is proposed. Firstly, the feasible region defined by the parameter qualitative constrains is sampled by the Monte Carlo to obtain the qualitative prior knowledge (QPK); secondly, the search space is reduced according to the QPK, and then the DE algorithm is used for parameter learning; finally, the QPK and the results of the DE algorithm are fused to acquire the real parameters. In the simulation experiment, three algorithms are used for parameter learning. The results show that the DEQPK is the most precise as well as the least time-consuming. At the same time, the parameters learned by the DEQPK algorithm is substituted into DBN, and the situations of battlefield targets are assessed.

Original language	English
Title of host publication	Advances in Guidance, Navigation and Control - Proceedings of 2022 International Conference on Guidance, Navigation and Control
Editors	Liang Yan, Haibin Duan, Yimin Deng, Liang Yan
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	1402-1412
Number of pages	11
ISBN (Print)	9789811966125
DOIs	https://doi.org/10.1007/978-981-19-6613-2_138
State	Published - 2023
Event	International Conference on Guidance, Navigation and Control, ICGNC 2022 - Harbin, China Duration: 5 Aug 2022 → 7 Aug 2022

Publication series

Name	Lecture Notes in Electrical Engineering
Volume	845 LNEE
ISSN (Print)	1876-1100
ISSN (Electronic)	1876-1119

Conference

Conference	International Conference on Guidance, Navigation and Control, ICGNC 2022
Country/Territory	China
City	Harbin
Period	5/08/22 → 7/08/22

Keywords

Differential evolution
Dynamic bayesian network
Parameter learning
Qualitative prior knowledge
Situation assessment

Access to Document

10.1007/978-981-19-6613-2_138

Cite this

Li, W., Shi, J., Zhang, W., & Wu, Y. (2023). Method of Learning Dynamic Bayesian Network Parameter Based on DEQPK Algorithm. In L. Yan, H. Duan, Y. Deng, & L. Yan (Eds.), Advances in Guidance, Navigation and Control - Proceedings of 2022 International Conference on Guidance, Navigation and Control (pp. 1402-1412). (Lecture Notes in Electrical Engineering; Vol. 845 LNEE). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-981-19-6613-2_138

Li, Weinan ; Shi, Jingping ; Zhang, Weiguo et al. / Method of Learning Dynamic Bayesian Network Parameter Based on DEQPK Algorithm. Advances in Guidance, Navigation and Control - Proceedings of 2022 International Conference on Guidance, Navigation and Control. editor / Liang Yan ; Haibin Duan ; Yimin Deng ; Liang Yan. Springer Science and Business Media Deutschland GmbH, 2023. pp. 1402-1412 (Lecture Notes in Electrical Engineering).

@inproceedings{6c87e3b3d46e4d3cadc56125b4afddde,

title = "Method of Learning Dynamic Bayesian Network Parameter Based on DEQPK Algorithm",

abstract = "For the problem of DBN parameter learning from small sample data, a differential evolution based on qualitative prior knowledge (DEQPK) is proposed. Firstly, the feasible region defined by the parameter qualitative constrains is sampled by the Monte Carlo to obtain the qualitative prior knowledge (QPK); secondly, the search space is reduced according to the QPK, and then the DE algorithm is used for parameter learning; finally, the QPK and the results of the DE algorithm are fused to acquire the real parameters. In the simulation experiment, three algorithms are used for parameter learning. The results show that the DEQPK is the most precise as well as the least time-consuming. At the same time, the parameters learned by the DEQPK algorithm is substituted into DBN, and the situations of battlefield targets are assessed.",

keywords = "Differential evolution, Dynamic bayesian network, Parameter learning, Qualitative prior knowledge, Situation assessment",

author = "Weinan Li and Jingping Shi and Weiguo Zhang and Yunyan Wu",

note = "Publisher Copyright: {\textcopyright} 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.; International Conference on Guidance, Navigation and Control, ICGNC 2022 ; Conference date: 05-08-2022 Through 07-08-2022",

year = "2023",

doi = "10.1007/978-981-19-6613-2_138",

language = "英语",

isbn = "9789811966125",

series = "Lecture Notes in Electrical Engineering",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "1402--1412",

editor = "Liang Yan and Haibin Duan and Yimin Deng and Liang Yan",

booktitle = "Advances in Guidance, Navigation and Control - Proceedings of 2022 International Conference on Guidance, Navigation and Control",

}

Li, W, Shi, J , Zhang, W & Wu, Y 2023, Method of Learning Dynamic Bayesian Network Parameter Based on DEQPK Algorithm. in L Yan, H Duan, Y Deng & L Yan (eds), Advances in Guidance, Navigation and Control - Proceedings of 2022 International Conference on Guidance, Navigation and Control. Lecture Notes in Electrical Engineering, vol. 845 LNEE, Springer Science and Business Media Deutschland GmbH, pp. 1402-1412, International Conference on Guidance, Navigation and Control, ICGNC 2022, Harbin, China, 5/08/22. https://doi.org/10.1007/978-981-19-6613-2_138

Method of Learning Dynamic Bayesian Network Parameter Based on DEQPK Algorithm. / Li, Weinan; Shi, Jingping ; Zhang, Weiguo et al.
Advances in Guidance, Navigation and Control - Proceedings of 2022 International Conference on Guidance, Navigation and Control. ed. / Liang Yan; Haibin Duan; Yimin Deng; Liang Yan. Springer Science and Business Media Deutschland GmbH, 2023. p. 1402-1412 (Lecture Notes in Electrical Engineering; Vol. 845 LNEE).

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

TY - GEN

T1 - Method of Learning Dynamic Bayesian Network Parameter Based on DEQPK Algorithm

AU - Li, Weinan

AU - Shi, Jingping

AU - Zhang, Weiguo

AU - Wu, Yunyan

PY - 2023

Y1 - 2023

N2 - For the problem of DBN parameter learning from small sample data, a differential evolution based on qualitative prior knowledge (DEQPK) is proposed. Firstly, the feasible region defined by the parameter qualitative constrains is sampled by the Monte Carlo to obtain the qualitative prior knowledge (QPK); secondly, the search space is reduced according to the QPK, and then the DE algorithm is used for parameter learning; finally, the QPK and the results of the DE algorithm are fused to acquire the real parameters. In the simulation experiment, three algorithms are used for parameter learning. The results show that the DEQPK is the most precise as well as the least time-consuming. At the same time, the parameters learned by the DEQPK algorithm is substituted into DBN, and the situations of battlefield targets are assessed.

AB - For the problem of DBN parameter learning from small sample data, a differential evolution based on qualitative prior knowledge (DEQPK) is proposed. Firstly, the feasible region defined by the parameter qualitative constrains is sampled by the Monte Carlo to obtain the qualitative prior knowledge (QPK); secondly, the search space is reduced according to the QPK, and then the DE algorithm is used for parameter learning; finally, the QPK and the results of the DE algorithm are fused to acquire the real parameters. In the simulation experiment, three algorithms are used for parameter learning. The results show that the DEQPK is the most precise as well as the least time-consuming. At the same time, the parameters learned by the DEQPK algorithm is substituted into DBN, and the situations of battlefield targets are assessed.

KW - Differential evolution

KW - Dynamic bayesian network

KW - Parameter learning

KW - Qualitative prior knowledge

KW - Situation assessment

UR - http://www.scopus.com/inward/record.url?scp=85151152840&partnerID=8YFLogxK

U2 - 10.1007/978-981-19-6613-2_138

DO - 10.1007/978-981-19-6613-2_138

M3 - 会议稿件

AN - SCOPUS:85151152840

SN - 9789811966125

T3 - Lecture Notes in Electrical Engineering

SP - 1402

EP - 1412

BT - Advances in Guidance, Navigation and Control - Proceedings of 2022 International Conference on Guidance, Navigation and Control

A2 - Yan, Liang

A2 - Duan, Haibin

A2 - Deng, Yimin

A2 - Yan, Liang

PB - Springer Science and Business Media Deutschland GmbH

T2 - International Conference on Guidance, Navigation and Control, ICGNC 2022

Y2 - 5 August 2022 through 7 August 2022

ER -

Li W, Shi J , Zhang W, Wu Y. Method of Learning Dynamic Bayesian Network Parameter Based on DEQPK Algorithm. In Yan L, Duan H, Deng Y, Yan L, editors, Advances in Guidance, Navigation and Control - Proceedings of 2022 International Conference on Guidance, Navigation and Control. Springer Science and Business Media Deutschland GmbH. 2023. p. 1402-1412. (Lecture Notes in Electrical Engineering). doi: 10.1007/978-981-19-6613-2_138

Method of Learning Dynamic Bayesian Network Parameter Based on DEQPK Algorithm

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this