TY - JOUR
T1 - Aerial Target Threat Assessment Based on Gated Recurrent Unit and Self-Attention Mechanism
AU - Chen, Chen
AU - Quan, Wei
AU - Shao, Zhuang
N1 - Publisher Copyright:
© 1990-2011 Beijing Institute of Aerospace Information.
PY - 2024/4/1
Y1 - 2024/4/1
N2 - Aerial threat assessment is a crucial link in modern air combat, whose result counts a great deal for commanders to make decisions. With the consideration that the existing threat assessment methods have difficulties in dealing with high dimensional time series target data, a threat assessment method based on self-attention mechanism and gated recurrent unit (SAGRU) is proposed. Firstly, a threat feature system including air combat situations and capability features is established. Moreover, a data augmentation process based on fractional Fourier transform (FRFT) is applied to extract more valuable information from time series situation features. Furthermore, aiming to capture key characteristics of battlefield evolution, a bidirectional GRU and SA mechanisms are designed for enhanced features. Subsequently, after the concatenation of the processed air combat situation and capability features, the target threat level will be predicted by fully connected neural layers and the softmax classifier. Finally, in order to validate this model, an air combat dataset generated by a combat simulation system is introduced for model training and testing. The comparison experiments show the proposed model has structural rationality and can perform threat assessment faster and more accurately than the other existing models based on deep learning.
AB - Aerial threat assessment is a crucial link in modern air combat, whose result counts a great deal for commanders to make decisions. With the consideration that the existing threat assessment methods have difficulties in dealing with high dimensional time series target data, a threat assessment method based on self-attention mechanism and gated recurrent unit (SAGRU) is proposed. Firstly, a threat feature system including air combat situations and capability features is established. Moreover, a data augmentation process based on fractional Fourier transform (FRFT) is applied to extract more valuable information from time series situation features. Furthermore, aiming to capture key characteristics of battlefield evolution, a bidirectional GRU and SA mechanisms are designed for enhanced features. Subsequently, after the concatenation of the processed air combat situation and capability features, the target threat level will be predicted by fully connected neural layers and the softmax classifier. Finally, in order to validate this model, an air combat dataset generated by a combat simulation system is introduced for model training and testing. The comparison experiments show the proposed model has structural rationality and can perform threat assessment faster and more accurately than the other existing models based on deep learning.
KW - fractional Fourier transform (FRFT)
KW - gated recurrent unit (GRU)
KW - self-attention (SA)
KW - target threat assessment
UR - http://www.scopus.com/inward/record.url?scp=85193735166&partnerID=8YFLogxK
U2 - 10.23919/JSEE.2023.000116
DO - 10.23919/JSEE.2023.000116
M3 - Article
AN - SCOPUS:85193735166
SN - 1671-1793
VL - 35
SP - 361
EP - 373
JO - Journal of Systems Engineering and Electronics
JF - Journal of Systems Engineering and Electronics
IS - 2
ER -