Based on the state feature of the target, traditional methods of inferring aerial targets’ combat intention, require a large amount of domain expert knowledge to quantify the weight of feature, prior probability and clear correspondence between state characteristics and intention. However, the neural network method can train itself to obtain the rules between state features and intentions in the absence of domain expert knowledge. The Back Propagation (BP) algorithm has slow convergence rate and can easily fall into local optimum when updating the network node weights. Through the introduction of the Rectified Linear Unit (ReLU) activation function and the Adaptive moment estimation (Adam) optimization algorithm, a combat intention recognition model based on deep neural network is designed to improve the convergence speed of the model and effectively prevent the algorithm from falling into a local optimum. The simulation results show that the proposed method can effectively recognise the aerial targets’ combat intention and obtain a higher recognition rate.
ZHOU Wangwang
,
YAO Peiyang
,
ZHANG Jieyong
,
WANG Xun
,
WEI Shuai
. Combat intention recognition for aerial targets based on deep neural network[J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2018
, 39(11)
: 322468
-322476
.
DOI: 10.7527/S1000-6893.2018.22468
[1] NOBLE D F. Schema-based knowledge elicitation for planning and situation assessment aids[J]. IEEE Transactions on Systems Man & Cybernetics, 1989, 19(3): 473-482.
[2] 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.
[3] 李曼, 冯新喜, 张薇. 基于模板的态势估计推理模型与算法[J]. 火力与指挥控制, 2010, 35(6): 64-66. LI M, FENG X X, ZHANG W. Template-based inference model and algorithm for situation assessment in information fusion[J]. Fire Control & Command Control, 2010, 35(6): 64-66 (in Chinese).
[4] BEN-BASSAT M, FREEDY E. Knowledge requirements and management in expert decision support systems for (military) situation assessment[J]. Systems Man & Cybernetics IEEE Transactions on, 1982, 12(4): 479-490.
[5] 伍之前, 李登峰. 基于推理和多属性决策的空中目标攻击意图判断模型[J]. 电光与控制, 2010, 17(5): 10-13. WU Z Q, LI D F. A model for aerial target attacking intention judgment based on reasoning and multi-attribute decision making[J]. Electronics Optics & Control, 2010, 17(5): 10-13 (in Chinese).
[6] CARLING R. Naval situation assessment using a real-time knowledge-based system[J]. Naval Engineers Journal, 2010, 111(5): 108-113.
[7] JIN Q, GOU X, JIN W, et al. Intention recognition of aerial targets based on Bayesian optimization algorithm[C]//IEEE International Conference on Intelligent Transportation Engineering. Piscataway, NJ: IEEE Press, 2017: 356-359.
[8] DAHLBOM A. A comparison of two approaches for situation detection in an air-to-air combat scenario[C]//Modeling Decisions for Artificial Intelligence. Berlin: Springer, 2013: 70-81.
[9] CHEN Z G, WU X F. A novel multi-timescales layered intention recognition method[J]. Applied Mechanics & Materials, 2014, 644-650: 4607-4611.
[10] 贾苏元, 徐金钰, 王钰. 基于自适应神经网络模糊系统(ANFIS)的空中目标意图分类[J]. 电子测量技术, 2016, 39(12): 62-66. JIA S Y, XU J Y, WANG Y. Classification of air target intention based on adaptive neural network fuzzy system(ANFIS)[J]. Electronic Measurement Technology, 2016, 39(12): 62-66 (in Chinese).
[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 H, REN Q L, HUA Y, 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] AHMED A A, MOHAMMED F M. SAIRF: A similarity approach for attack intention recognition using fuzzy min-max neural network[J]. Journal of Computational Science, 2018, 25: 467-473.
[13] 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 W, LIU S J, HE X Y, et al. Tactical intention recognition algorithm based on encoded temporal features[J]. Command Control & Simulation, 2016, 38(6): 36-41 (in Chinese).
[14] HINTON G E, SALAKHUTDINOV R R. Reducing the dimensionality of data with neural networks[J]. Science, 2006, 313(5786): 504-507.
[15] GLOROT X, BORDES A, BENGIO Y. Deep sparse rectifier neural networks[C]//International Conference on Artificial Intelligence and Statistics. 2011: 315-323.
[16] KINGMA D P, BA J. Adam: A method for stochastic optimization[J]. Computer Science, 2014: 1-5.
[17] WANG L, ZHANG J, LIU P, et al. Spectral-spatial multi-feature-based deep learning for hyperspectral remote sensing image classification[J]. Soft Computing, 2017, 21(1): 213-221: 1-15.
[18] CHANG P, ZHANG J, HU J, et al. A deep neural network based on ELM for semi-supervised learning of image classification[J]. Neural Processing Letters, 2017, 48(1): 375-388.
[19] ANSARI Z, SEYYEDSALEHI S A. Toward growing modular deep neural networks for continuous speech recognition[J]. Neural Computing & Applications, 2017, 28(S1): 1177-1196.
[20] WEN Z, LI K, HUANG Z, et al. Improving deep neural network based speech synthesis through contextual feature parametrization and multi-task learning[J]. Journal of Signal Processing Systems, 2018, 90(7): 1025-1037.
[21] CHEN K, DING G G. Attribute-based supervised deep learning model for action recognition[J]. Frontiers of Computer Science, 2017, 11(2): 219-229.
[22] LI Q, QIU Z, YAO T, et al. Learning hierarchical video representation for action recognition[J]. International Journal of Multimedia Information Retrieval, 2017, 6(1): 85-98.
CJA