KGTLIR: An Air Target Intention Recognition Model Based on Knowledge Graph and Deep Learning

被引:0
作者
Cao, Bo [1 ]
Xing, Qinghua [2 ]
Li, Longyue [2 ]
Xing, Huaixi [1 ]
Song, Zhanfu [1 ]
机构
[1] Air Force Engn Univ, Grad Sch, Xian 710051, Peoples R China
[2] Air Force Engn Univ, Air Def & Antimissile Sch, Xian 710051, Peoples R China
来源
CMC-COMPUTERS MATERIALS & CONTINUA | 2024年 / 80卷 / 01期
关键词
Dilated causal convolution; graph attention mechanism; intention recognition; air targets; knowledge graph;
D O I
10.32604/cmc.2024.052842
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
As a core part of battlefield situational awareness, air target intention recognition plays an important role in modern air operations. Aiming at the problems of insufficient feature extraction and misclassification in intention recognition, this paper designs an air target intention recognition method (KGTLIR) based on Knowledge Graph and Deep Learning. Firstly, the intention recognition model based on Deep Learning is constructed to mine the temporal relationship of intention features using dilated causal convolution and the spatial relationship of intention features using a graph attention mechanism. Meanwhile, the accuracy, recall, and F1-score after iteration are introduced to dynamically adjust the sample weights to reduce the probability of misclassification. After that, an intention recognition model based on Knowledge Graph is constructed to predict the probability of the occurrence of different intentions of the target. Finally, the results of the two models are fused by evidence theory to obtain the target's operational intention. Experiments show that the intention recognition accuracy of the KGTLIR model can reach 98.48%, which is not only better than most of the air target intention recognition methods, but also demonstrates better interpretability and trustworthiness.
引用
收藏
页码:1251 / 1275
页数:25
相关论文
共 25 条
[1]   A Stochastic Gradient Descent Approach for Stochastic Optimal Control [J].
Archibald, Richard ;
Bao, Feng ;
Yong, Jiongmin .
EAST ASIAN JOURNAL ON APPLIED MATHEMATICS, 2020, 10 (04) :635-658
[2]   Causal augmented ConvNet: A temporal memory dilated convolution model for long-sequence time series prediction [J].
Ayodeji, Abiodun ;
Wang, Zhiyu ;
Wang, Wenhai ;
Qin, Weizhong ;
Yang, Chunhua ;
Xu, Shenghu ;
Liu, Xinggao .
ISA TRANSACTIONS, 2022, 123 :200-217
[3]  
Bai SJ, 2018, Arxiv, DOI arXiv:1803.01271
[4]  
Chen YM., 2019, Comput. Simul, V36, P1
[5]  
Fusano A., 2011, 2011 UkSim 13th International Conference on Computer Modelling and Simulation (UKSim 2011), P249, DOI 10.1109/UKSIM.2011.54
[6]  
Jin Q, 2017, 2017 2ND IEEE INTERNATIONAL CONFERENCE ON INTELLIGENT TRANSPORTATION ENGINEERING (ICITE), P356, DOI 10.1109/ICITE.2017.8056938
[7]   Target Tactical Intention Recognition in Multiaircraft Cooperative Air Combat [J].
Meng Guanglei ;
Zhao Runnan ;
Wang Biao ;
Zhou Mingzhe ;
Wang Yu ;
Liang Xiao .
INTERNATIONAL JOURNAL OF AEROSPACE ENGINEERING, 2021, 2021
[8]   Intention recognition of aerial target based on deep learning [J].
Qu, Chongxiao ;
Guo, Zichang ;
Xia, Shaojie ;
Zhu, Liaoyuan .
EVOLUTIONARY INTELLIGENCE, 2024, 17 (01) :303-311
[9]  
Sun Y.L., 2012, Ship Electron.Eng., V32, P48, DOI 10.3969/j.issn.1627-9730.2012.05.017
[10]   Attention-TCN-BiGRU: An Air Target Combat Intention Recognition Model [J].
Teng, Fei ;
Song, Yafei ;
Guo, Xinpeng .
MATHEMATICS, 2021, 9 (19)