Data Prediction Compensation for Dynamic Target Tracking System Based on BP Neural Network

Shuqing Xu, Yongrui Qin, Haiyin Zhou, Bowen Sun, Jiongqi Wang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

During the target tracking process, some observation data may be missing due to the equipment problems or the operation errors, which may affect the filtering process of the target state and the position determination accuracy. Therefore, the missing data needs to be effectively compensated. This paper provides a method to compensate the missing data by using the characteristics of BP neural network learning system aiming at the dynamic target tracking system. The neural network is trained by using the complete data of the dynamic system, and then the missing data is predicted by the trained neural network. The simulation results for both of the linear system and the nonlinear system show that the method is indeed effective, compared to the traditional time update prediction, the prediction accuracy is much higher.

Original languageEnglish
Title of host publicationProceedings 2018 Chinese Automation Congress
Subtitle of host publicationCAC 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1034-1039
Number of pages6
ISBN (Electronic)9781728113128
ISBN (Print)9781728113135
DOIs
Publication statusPublished - 24 Jan 2019
Event2018 Chinese Automation Congress - Xi'an, China
Duration: 30 Nov 20182 Dec 2018

Conference

Conference2018 Chinese Automation Congress
Abbreviated titleCAC 2018
CountryChina
CityXi'an
Period30/11/182/12/18

Fingerprint

Target tracking
Neural networks
Linear systems
Learning systems
Nonlinear systems
Dynamical systems
Compensation and Redress

Cite this

Xu, S., Qin, Y., Zhou, H., Sun, B., & Wang, J. (2019). Data Prediction Compensation for Dynamic Target Tracking System Based on BP Neural Network. In Proceedings 2018 Chinese Automation Congress: CAC 2018 (pp. 1034-1039). [8623495] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/CAC.2018.8623495
Xu, Shuqing ; Qin, Yongrui ; Zhou, Haiyin ; Sun, Bowen ; Wang, Jiongqi. / Data Prediction Compensation for Dynamic Target Tracking System Based on BP Neural Network. Proceedings 2018 Chinese Automation Congress: CAC 2018. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 1034-1039
@inproceedings{311952906cc247048c84ab981a07b07d,
title = "Data Prediction Compensation for Dynamic Target Tracking System Based on BP Neural Network",
abstract = "During the target tracking process, some observation data may be missing due to the equipment problems or the operation errors, which may affect the filtering process of the target state and the position determination accuracy. Therefore, the missing data needs to be effectively compensated. This paper provides a method to compensate the missing data by using the characteristics of BP neural network learning system aiming at the dynamic target tracking system. The neural network is trained by using the complete data of the dynamic system, and then the missing data is predicted by the trained neural network. The simulation results for both of the linear system and the nonlinear system show that the method is indeed effective, compared to the traditional time update prediction, the prediction accuracy is much higher.",
keywords = "Accuracy Analysis, BP Neural Network, Dynamic System, Extended Kalman Filter, Prediction Compensation, Target Tracking",
author = "Shuqing Xu and Yongrui Qin and Haiyin Zhou and Bowen Sun and Jiongqi Wang",
year = "2019",
month = "1",
day = "24",
doi = "10.1109/CAC.2018.8623495",
language = "English",
isbn = "9781728113135",
pages = "1034--1039",
booktitle = "Proceedings 2018 Chinese Automation Congress",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

Xu, S, Qin, Y, Zhou, H, Sun, B & Wang, J 2019, Data Prediction Compensation for Dynamic Target Tracking System Based on BP Neural Network. in Proceedings 2018 Chinese Automation Congress: CAC 2018., 8623495, Institute of Electrical and Electronics Engineers Inc., pp. 1034-1039, 2018 Chinese Automation Congress, Xi'an, China, 30/11/18. https://doi.org/10.1109/CAC.2018.8623495

Data Prediction Compensation for Dynamic Target Tracking System Based on BP Neural Network. / Xu, Shuqing; Qin, Yongrui; Zhou, Haiyin; Sun, Bowen; Wang, Jiongqi.

Proceedings 2018 Chinese Automation Congress: CAC 2018. Institute of Electrical and Electronics Engineers Inc., 2019. p. 1034-1039 8623495.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Data Prediction Compensation for Dynamic Target Tracking System Based on BP Neural Network

AU - Xu, Shuqing

AU - Qin, Yongrui

AU - Zhou, Haiyin

AU - Sun, Bowen

AU - Wang, Jiongqi

PY - 2019/1/24

Y1 - 2019/1/24

N2 - During the target tracking process, some observation data may be missing due to the equipment problems or the operation errors, which may affect the filtering process of the target state and the position determination accuracy. Therefore, the missing data needs to be effectively compensated. This paper provides a method to compensate the missing data by using the characteristics of BP neural network learning system aiming at the dynamic target tracking system. The neural network is trained by using the complete data of the dynamic system, and then the missing data is predicted by the trained neural network. The simulation results for both of the linear system and the nonlinear system show that the method is indeed effective, compared to the traditional time update prediction, the prediction accuracy is much higher.

AB - During the target tracking process, some observation data may be missing due to the equipment problems or the operation errors, which may affect the filtering process of the target state and the position determination accuracy. Therefore, the missing data needs to be effectively compensated. This paper provides a method to compensate the missing data by using the characteristics of BP neural network learning system aiming at the dynamic target tracking system. The neural network is trained by using the complete data of the dynamic system, and then the missing data is predicted by the trained neural network. The simulation results for both of the linear system and the nonlinear system show that the method is indeed effective, compared to the traditional time update prediction, the prediction accuracy is much higher.

KW - Accuracy Analysis

KW - BP Neural Network

KW - Dynamic System

KW - Extended Kalman Filter

KW - Prediction Compensation

KW - Target Tracking

UR - http://www.scopus.com/inward/record.url?scp=85062796345&partnerID=8YFLogxK

U2 - 10.1109/CAC.2018.8623495

DO - 10.1109/CAC.2018.8623495

M3 - Conference contribution

SN - 9781728113135

SP - 1034

EP - 1039

BT - Proceedings 2018 Chinese Automation Congress

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Xu S, Qin Y, Zhou H, Sun B, Wang J. Data Prediction Compensation for Dynamic Target Tracking System Based on BP Neural Network. In Proceedings 2018 Chinese Automation Congress: CAC 2018. Institute of Electrical and Electronics Engineers Inc. 2019. p. 1034-1039. 8623495 https://doi.org/10.1109/CAC.2018.8623495