论文:2023,Vol:41,Issue(2):400-408
引用本文:
李颖, 武君胜, 李伟刚, 董玮, 房爱青. 一种识别作战意图的层次聚合模型[J]. 西北工业大学学报
LI Ying, WU Junsheng, LI Weigang, DONG Wei, FANG Aiqing. A hierarchical aggregation model for combat intention recognition[J]. Journal of Northwestern Polytechnical University

一种识别作战意图的层次聚合模型
李颖1, 武君胜1, 李伟刚2, 董玮1, 房爱青1
1. 西北工业大学 计算机学院, 陕西 西安 710072;
2. 西北工业大学 软件学院, 陕西 西安 710072
摘要:
作战意图识别是指对敌方目标的状态信息进行分析,从而解释和判断敌方想要达到的目的。随着作战平台信息化程度的不断提高,这些具有时序性的敌方状态信息呈现多维、海量的特点。面对这样的特点,提出基于神经网络的方法学习敌方状态信息。由于作战意图具有层次性,并且意图行为之间具有依赖关系,设计了一种层次聚合模型,模型底层基于卷积神经网络感知行为特征,中间层基于双向长短时记忆网络聚合子意图之间的长时依赖信息,表达意图内部关系。顶层通过注意力机制将特征聚焦于对识别意图有更高贡献的高级特征,最终感知全局信息以识别目标作战意图。实验数据表明,相比其他网络结构,提出的模型可以表达意图的层次性以及意图之间的长时依赖关系,识别准确率可以达到88.83%,适用于现代战场空中目标意图的识别问题。
关键词:    意图识别    卷积神经网络    双向长短时记忆网络    注意力机制    层次聚合   
A hierarchical aggregation model for combat intention recognition
LI Ying1, WU Junsheng1, LI Weigang2, DONG Wei1, FANG Aiqing1
1. School of Computer Science, Northwestern Polytechnical University, Xi'an 710072, China;
2. School of Software, Northwestern Polytechnical University, Xi'an 710072, China
Abstract:
Combat intent recognition refers to analyzing the enemy target's state information to interpret and judge the purpose of the enemy. With the increased knowledge of combat platforms, these time-series enemy state presents multi-dimensional and massive characteristics. Using neural networks to learn enemy state information has become a research trend in the face of such traits. To address these challenges, we propose a hierarchical aggregation model to recognize the intention of the target. The bottom layer of our model is based on convolutional neural network(CNN) to perceive behavior features, and the middle layer is based on Bi-LSTM(Bi-directional long short-term memory) to aggregate the long-time interdependence information between sub-intentions. The top layer focuses on higher-level features that contribute more to the recognition of intent through the attention mechanism and finally combines the global information to recognize the intention. Extensive experimental results show the superiority of our model in that the recognition accuracy achieves 88.83%, which can solve the problem of identifying air target intent on the modern battlefield.
Key words:    intention recognition    convolutional neural network    bi-directional long short-term memory network    attention mechanism    hierarchy aggregation   
收稿日期: 2022-06-10     修回日期:
DOI: 10.1051/jnwpu/20234120400
基金项目: 国家自然科学基金(71701208)与陕西省重点研发计划(2023-YBGY-201,2023-YBGY-228)资助
通讯作者: 李伟刚(1972-),西北工业大学副教授,主要从事智能决策及云原生软件运维方法研究。e-mail:liweigang@nwpu.edu.cn     Email:liweigang@nwpu.edu.cn
作者简介: 李颖(1991-),西北工业大学博士研究生,主要从事智能决策与神经网络研究。
相关功能
PDF(2989KB) Free
打印本文
把本文推荐给朋友
作者相关文章
李颖  在本刊中的所有文章
武君胜  在本刊中的所有文章
李伟刚  在本刊中的所有文章
董玮  在本刊中的所有文章
房爱青  在本刊中的所有文章

参考文献:
[1] NOBLE D F. Schema-based knowledge elicitation for planning and situation assessment aids[J]. IEEE Trans on Systems, Man, and Cybernetics, 1989, 19(3):473-482
[2] 黄长强. 未来空战过程智能化关键技术研究[J]. 航空兵器, 2019, 26(1):11-19 HUANG Changqiang. Research on key technology of future air combat process intelligentization[J]. Aero Weaponry, 2019, 26(1):11-19 (in Chinese)
[3] 赵福均, 周志杰, 胡昌华, 等. 基于置信规则库和证据推理的空中目标意图识别方法[J]. 电光与控制, 2017, 24(8):15-19 ZHAO Fujun, ZHOU Zhijie, HU Changhua, et al. Aerial target intention recognition approach based on belief-rule-base and evidential reasoning[J]. Electronics Optics & Control, 2017, 24(8):15-19 (in Chinese)
[4] JIANG W, HAN D, FAN X, et al. Research on threat assessment based on Dempster-Shafer evidence theory[J]. Lecture Notes in Electrical Engineering, 2012, 113:975-984
[5] BASIR O, YUAN X. Engine fault diagnosis based on multi-sensor information fusion using Dempster-Shafer evidence theory[J]. Information Fusion, 2007, 8(4):379-386
[6] 谢泓, 蒲金龙. 基于D-S证据理论多模复合探测器信息融合算法研究[J]. 光电技术应用, 2017, 32(2):41-43 XIE Hong, PU Jinlong. Research on information fusion method of multi-sensor based on Dempster-Shafer evidence theory[J]. Electro-Optic Technology Application, 2017, 32(2):41-43 (in Chinese)
[7] 葛顺, 夏学知. 用于战术意图识别的动态序列贝叶斯网络[J]. 系统工程与电子技术, 2014, 36(1):76-81 GE Shun, XIA Xuezhi. DSBN used for recognition of tactical intention[J]. Systems Engineering and Electronics, 2014, 36(1):76-81 (in Chinese)
[8] QING J, XIANTAI G, WEIDONG J, et al. Intention recognition of aerial targets based on Bayesian optimization algorithm[C]//2nd IEEE International Conference on Intelligent Transportation Engineering, 2017:356-359
[9] 李战武, 李双庆, 彭明毓, 等. 基于注意力机制改进的LSTM空战目标意图识别方法[J]. 电光与控制:2023, 30(3):1-7 LI Zhanwu, LI Shuangqing, PENG Mingyu, et al. Air combat intention recognition method of target based on LSTM improved by attention mechanism[J]. Electronics Optics & Control, 2023, 30(3):1-7 (in Chinese)
[10] ABDULGHANI Ali Ahmed, MOHAMMED Falah. SAIRF:a similarity approach for attack intention recognition using fuzzy min-max neural network[J]. Journal of Computational Science, 2018, 25:76-81
[11] 陈浩, 任卿龙, 滑艺, 等. 基于模糊神经网络的海面目标战术意图识别[J]. 系统工程与电子技术, 2016, 38(8):1847-1853 CHEN Hao, REN Qinglong, HUA Yi, et al. Fuzzy neural network based tactical intention recognition for sea targets[J]. Systems Engineering and Electronics, 2016, 38(8):1847-1853 (in Chinese)
[12] ZHAO Kexin, HUANG Changqiang. The Hierarchical recognition method of autonomous air tactical operation of unmanned combat aircraft[C]//Proceedings of the 7th International Conference on Informatics, Environment, Energy and Applications, 2018:129-133
[13] 周旺旺, 姚佩阳, 张杰勇, 等. 基于深度神经网络的空中目标作战意图识别[J]. 航空学报, 2018, 39(11):195-203 ZHOU Wangwang, YAO Peiyang, ZHANG Jieyong, et al. Combat intention recognition for aerial targets based on deep neural network[J]. Acta Aeronautica et Astronautica Sinica, 2018, 39(11):195-203 (in Chinese)
[14] ZAREMBA W, SUTSKEVER I, VINYALS O. Recurrent neural network regularization[C]//International Conference on Learning Representations, 2015
[15] 赵佳欢, 杨海明, 邱令存. 基于循环神经网络的空中目标类型识别[J]. 航天控制, 2020, 38(3):47-53 ZHAO Jiahuan, YANG Haiming, QIU Lingcun. Recognition of aerial target types based on recurrent neural network[J]. Aerospace Control, 2020, 38(3):47-53 (in Chinese)
[16] ZHANG H, ZHU T. Aircraft hard landing prediction using LSTM neural network[C]//2nd International Symposium on Computer Science and Intelligent Control, 2018:1-5
[17] 王志刚, 王业光, 杨宁, 等. 基于LSTM的飞行数据挖掘模型构建方法[J]. 航空学报, 2021, 42(8):262-271 WANG Zhigang, WANG Yeguang, YANG Ning, et al. Construction method of flight data mining model based on LSTM[J]. Acta Aeronautica et Astronautica Sinica, 2021, 42(8):262-271 (in Chinese)
[18] 欧微, 柳少军, 贺筱媛, 等. 基于时序特征编码的目标战术意图识别算法[J]. 指挥控制与仿真, 2016, 38(6):36-41 OU Wei, LIU Shaojun, HE Xiaoyuan, et al. Tactical intention recognition algorithm based on encoded temporal features[J]. Command Control & Simulation, 2016, 38(6):36-41 (in Chinese)
[19] SCHUSTER M, PALIWAL K. Bidirectional recurrent neural networks[J]. IEEE Trans on Signal Processing, 1997, 45(11):2673-2681
[20] KINGMA D P, BA J. Adam:a method for stochastic optimization[C]//International Conference on Learning Representations, 2015
[21] DENG J, GUO J, XUE N, et al. ArcFace:additive angular margin loss for deep face recognition[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019:4685-4694
[22] KIM Y. Convolutional neural networks for sentence classification[C]//Conference on Empirical Methods in Natural Language Processing, 2014:1746-1751
[23] CHO K, MERRIENBOER B V, GULCEHRE C, et al. Learning phrase representations using RNN encoder-decoder for statistical machine translation[C]//Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing, 2014:1724-1734
[24] VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need[C]//Proceedings of the 31st International Conference on Neural Information Processing Systems, 2017:5998-6008