TY - JOUR
T1 - Long short-term memory-based deep recurrent neural networks for target tracking
AU - Gao, Chang
AU - Yan, Junkun
AU - Zhou, Shenghua
AU - Varshney, Pramod K.
AU - Liu, Hongwei
N1 - Funding Information:
This work was supported by the National Science Fund for Distinguished Young Scholars (61525105), the National Natural Science Foundation of China ( 61601340 ), the Fundamental Research Funds for the Central Universities ( JB180215 ), the fund for Foreign Scholars in University Research and Teaching Programs (the 111 Project No.B18039) and AFOSR Grant FA9550-16-1-0077 under the DDDAS program of USA.
Publisher Copyright:
© 2019 Elsevier Inc.
PY - 2019/10
Y1 - 2019/10
N2 - Target tracking is a difficult estimation problem due to target motion uncertainty and measurement origin uncertainty. In this paper, we consider the target tracking problem in the presence of only target motion uncertainty. The traditional approaches to address this uncertainty, such as multiple model approaches, can suffer performance degradation when there is a model mismatch. The statistical accuracy of conventional model-based methods is also usually limited because of the measurement errors and insufficient data for the estimation. In this paper, deep neural network-based methods are proposed to handle target motion uncertainty due to their strong capability of fitting any mapping as long as there are sufficient training data. Specifically, a recurrent neural network-based structure is proposed to estimate the true states that is consistent with the sequential manner of target tracking. In addition, it is expected that better performance will be achieved due to access to true states during the training of the networks. We propose two networks that are based on different principles and are capable of real-time tracking. An approach to further reduce the computational load is also introduced. Simulation results show that the proposed methods can handle the target motion uncertainty well and provide better estimation accuracy.
AB - Target tracking is a difficult estimation problem due to target motion uncertainty and measurement origin uncertainty. In this paper, we consider the target tracking problem in the presence of only target motion uncertainty. The traditional approaches to address this uncertainty, such as multiple model approaches, can suffer performance degradation when there is a model mismatch. The statistical accuracy of conventional model-based methods is also usually limited because of the measurement errors and insufficient data for the estimation. In this paper, deep neural network-based methods are proposed to handle target motion uncertainty due to their strong capability of fitting any mapping as long as there are sufficient training data. Specifically, a recurrent neural network-based structure is proposed to estimate the true states that is consistent with the sequential manner of target tracking. In addition, it is expected that better performance will be achieved due to access to true states during the training of the networks. We propose two networks that are based on different principles and are capable of real-time tracking. An approach to further reduce the computational load is also introduced. Simulation results show that the proposed methods can handle the target motion uncertainty well and provide better estimation accuracy.
KW - Deep neural network
KW - Long short-term memory
KW - Recurrent neural network
KW - Target tracking
UR - http://www.scopus.com/inward/record.url?scp=85067524229&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85067524229&partnerID=8YFLogxK
U2 - 10.1016/j.ins.2019.06.039
DO - 10.1016/j.ins.2019.06.039
M3 - Article
AN - SCOPUS:85067524229
SN - 0020-0255
VL - 502
SP - 279
EP - 296
JO - Information sciences
JF - Information sciences
ER -