一种基于CNN的样本不足战场包围态势认知方法

doi:10.16182/j.issn1004731x.joss.201710009

系统仿真学报 ›› 2017, Vol. 29 ›› Issue (10): 2291-2300.doi: 10.16182/j.issn1004731x.joss.201710009

一种基于CNN的样本不足战场包围态势认知方法

朱丰^1,2, 胡晓峰¹, 贺筱媛¹, 孔亦思¹, 杨璐^3,4

1.中国人民解放军国防大学信息作战与指挥训练教研部,北京,100091;
2.中国人民解放军93682部队,北京,101300;
3.中国人民解放军91053部队,北京,100070;
4.空军工程大学防空反导学院,陕西西安,710051

收稿日期:2017-04-30 发布日期:2020-06-04
作者简介:朱丰(1983-), 男, 北京, 博士后, 工程师, 研究方向为战场态势评估与辅助决策分析、体系效能评估、深度学习理论与方法、雷达信号与信息处理。
基金资助:
国家自然科学基金(61374179),国家自然科学基金青年科学基金(61703412),军民共用重大研究计划联合基金(U1435218),中国博士后科学基金(2016M602996)

A CNN Based Cognitive Method to Battlefields Encompassing Situation with Insufficient Samples

Zhu Feng^1,2, Hu Xiaofeng¹, He Xiaoyuan¹, Kong Yisi¹, Yang Lu^3,4

1. The Department of Information Operation and Command Training, National Defense University, Beijing 100091, China;
2. No. 93682 Unit of PLA, Beijing 101300, China;
3. No. 91053 Unit of PLA, Beijing 100070, China;
4. Air and Missile Defense College, Air Force Engineering University, Xi'an 710051, China

Received:2017-04-30 Published:2020-06-04

摘要/Abstract

摘要： 为研究面对战场视图如何捕捉到指挥员认知经验的问题,深度学习中CNN可提供有力支持。但CNN的训练需要足够的样本数据,目前难以获得。针对战争中常见的战场包围态势认知及样本不足问题进行了剖析,提出一种基于CNN的样本不足包围态势认知新方法,该方法利用CNN的非线性拟合功能及包围态势图像的对称特性,可在一定程度上获得指挥员对包围态势的认知经验。仿真实验结果证明了方法的有效性和鲁棒性。

关键词: 战场包围态势认知, 指挥员, 建模方法, 卷积神经网络, 样本不足, 深度学习

Abstract: To research the issue of how to grasp the commander's cognitive experience successfully and effectively facing to battlefields sight map, Convolution Neural Network (CNN) as a kind of the typical algorithm in deep learning can provide the key ways. However, CNN needs the enough samples for running. These samples are hardly to achieve for the time being. Aimed at these problems, some exploring researches were carried out. The issues of battlefields encompassing situation cognition met generally in the warfare and lacking enough samples were discussed. On the basis of analyzing the image characteristics of battlefields encompassing situation and the operational principles of CNN, a new method of battlefields encompassing situation cognition based on CNN without enough samples was proposed. In the method, the non-linear fitting function of CNN and the symmetry characteristics of the battlefields encompassing situation images were utilized to catch the commander's experience for cognizing the battlefields encompassing situation at a certain extent. Simulation results validate the effectiveness and the robustness of the proposed method.

Key words: battlefields encompassing situation cognition, commanders, method of establishing models, CNN, insufficient samples, deep learning

中图分类号:

TP183

朱丰, 胡晓峰, 贺筱媛, 孔亦思, 杨璐. 一种基于CNN的样本不足战场包围态势认知方法[J]. 系统仿真学报, 2017, 29(10): 2291-2300.

Zhu Feng, Hu Xiaofeng, He Xiaoyuan, Kong Yisi, Yang Lu. A CNN Based Cognitive Method to Battlefields Encompassing Situation with Insufficient Samples[J]. Journal of System Simulation, 2017, 29(10): 2291-2300.

参考文献

[1] 胡晓峰, 贺筱媛, 徐旭林. 大数据时代对建模仿真的挑战与思考-中国科协第81期新观点新学说学术沙龙综述[J]. 中国科学: 信息科学, 2014, 44(5): 676-692.
(Hu Xiaofeng, He Xiaoyuan, Xu Xulin.Simulation in the Big Data Era Review of New Ideas and New Theories in the 81st Academic Salon of China Association for Science and Technology[J]. Science China: Information Science, 2014, 44(5): 676-692.)
[2] Zhu Feng, Hu Xiaofeng, Wu Lin, et al.Inspiration for Battlefield Situation Cognition from AI Military Programs Launched by DARPA of USA and Development of AI Technology[C]// 2016 International Simulation Multi-Conference (S1865-0929), Beijing, China, Springer Nature, 2016: 566-577.
[3] Alan N Steinberg, Christopher L Bowman, Franklin E White.Revisions to the JDL Data Fusion Model[C]// The Joint NATO/IRIS Conference, Quebec, Canda, October, 1998.
[4] Marvin S Cohen, Leonard Adelman, Martin A Tolcott, et al.A Cognitive Framework for Battlefield Commanders' Situation Assessment [R]. Arlington, VA, USA: Cognitive Technologies, Inc, 1993.
[5] Octavio Juarez-Espinosa, Cleotilde Gonzalez. Situation Awareness of Commanders: A Cognitive Model [C]//2004 Conference on Proceedings of Behavior Representation in Modeling and Simulation.
[6] 郭丽丽, 丁世飞. 深度学习研究进展[J]. 计算机科学, 2015, 42(5): 28-33.
(Guo Lili, Ding Shifei.Research Progress on Deep Learning[J]. Computer Science, 2015, 42(5): 28-33.)
[7] Hinton G, Salakhutdinov R.Reducing the dimensionality of data with neural networks[J]. Science, 2006, 313(5786): 504-507.
[8] 李卫. 深度学习在图像识别中的研究及应用 [D]. 武汉: 武汉理工大学, 2014.
(Li Wei.Research and Application of Deep Learning in Image Recognition [D]. Wuhan, China: Wuhan University of Technology, 2014.)
[9] 杨斌, 钟金英. 卷积神经网络的研究进展综述[J]. 南华大学学报(自然科学版), 2016, 30(3): 66-72.
(Yang Bin, Zhong Jinying.Review of Convolution Neural Network[J]. Journal of University of South China (Science and Technology), 2016, 30(3): 66-72.)
[10] 惠国保. 基于深度学习的自动目标识别技术 [C]// 第四届指挥控制大会报告, 北京. 中国指挥与控制学会, 电子工业出版社, 2016: 319-324.
(Hui Guobao.Auto Target Recognition Technology Based on Deep Learn [C]// 4th China Command and Control Conference, Beijing, China, Chinese Institute of Command and Control, Publishing House of Electronics Industry, 2016: 319-324.)
[11] 高惠琳. 基于卷积神经网络的军事图像分类 [J]. 计算机应用研究, 2017, 34(10): 优先出版.
(Gao Huilin. Military Image Classification Based on Convolutional Neural Network [J]. Application Research of Computers, 2017, 34(10): First Published.)
[12] Elpiniki I Papageorgiou, Jose L Salmeron.A Review of Fuzzy Cognitive Maps Research during the Last Decade[J]. IEEE Transactions on Fuzzy Systems (S1063-6706), 2013, 21(1): 66-79.
[13] 张玉叶, 周胜明, 赵育良, 等. 高速运动目标的运动模糊图像复原研究[J]. 红外与激光工程, 2017, 46(4): 0128001.
(Zhang Yuye, Zhou Shengming, Zhao Yuliang, et al. Motion-Blurred Image Deblurring of Fast Moving Target [J]. Infrared and Laser Engineering, 2017, 46(4): 0128001.)
[14] 王坤峰, 苟超, 段艳杰, 等. 生成式对抗网络GAN的研究进展与展望[J]. 自动化学报, 2017, 43(3): 321-332.
(Wang Kunfeng, Gou Chao, Duan Yanjie, et al.Generative Adversarial Networks: The State of the Art and Beyond[J]. Acta Automatica Sinica, 2017, 43(3): 321-332.)
[15] 计算机视觉战队. 深度压缩网络较大程度减少了网络参数存储问题 [R]. 微信文章. (2017-07-09) [2017-07-15].
(Computer Vision Team. Issue of Saved Network Parameters are Reduced by Deep Compress Network at a Large Extent [R]. Weixin Paper. (2017-07-09) [2017-07-15].)
[16] Brenden M Lake, Ruslan Salakhutdinov, Joshua B Tenenbaum.Human-Level Concept Learning through Probabilistic Program Induction[J]. Science (S0036-8075), 2015, 350(6266): 1332-1338.

一种基于CNN的样本不足战场包围态势认知方法

A CNN Based Cognitive Method to Battlefields Encompassing Situation with Insufficient Samples

PDF (PC)

可视化

被引次数

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	张立峰, 王会忍. 基于卷积神经网络及有限元仿真的电容层析成像图像重建[J]. 系统仿真学报, 2022, 34(4): 712-718.
[2]	康旭, 张晓峰. 基于生成对抗神经网络的雷达遥感数据增广方法[J]. 系统仿真学报, 2022, 34(4): 920-927.
[3]	敖邦乾, 杨莎, 令狐金卿, 叶振环. 基于级联神经网络疲劳驾驶检测系统设计[J]. 系统仿真学报, 2022, 34(2): 323-333.
[4]	聂凯, 曾科军, 孟庆海. 基于深度贝叶斯网络学习的不确定性建模方法[J]. 系统仿真学报, 2022, 34(1): 79-85.
[5]	林硕, 安磊, 高治军, 单丹, 尚文利. 结合栈式自编码及长短时记忆的入侵检测研究[J]. 系统仿真学报, 2021, 33(6): 1288-1296.
[6]	程文聪, 史小康, 王志刚. 基于生成对抗网络的仿真卫星云图生成方法[J]. 系统仿真学报, 2021, 33(6): 1297-1306.
[7]	赵瑛, 陆耀, 张健, 梁启弟, 龙炜. 基于深度神经网络的多视角人体动作识别[J]. 系统仿真学报, 2021, 33(5): 1019-1030.
[8]	仝卫国, 庞雪纯, 朱赓宏. 基于卷积神经网络的气液两相流流型识别方法[J]. 系统仿真学报, 2021, 33(4): 883-891.
[9]	董书琴, 张斌. 面向不平衡数据的网络流量异常检测方法[J]. 系统仿真学报, 2021, 33(3): 679-689.
[10]	王霄汉, 张霖, 任磊, 谢堃钰, 王昆玉, 叶飞, 陈真. 基于强化学习的车间调度问题研究简述[J]. 系统仿真学报, 2021, 33(12): 2782-2791.
[11]	王步维, 王敏, 范谦, 王雅男, 章涵文, 乐云亮. 基于深度学习的晶体性质预测研究[J]. 系统仿真学报, 2021, 33(12): 2854-2863.
[12]	冯晓, 张辉, 周蕊, 乔璐, 魏东, 李丹丹, 张玉尧, 郑国清. 基于深度学习和籽粒双面特征的玉米品种识别[J]. 系统仿真学报, 2021, 33(12): 2983-2991.
[13]	马榕, 陈秋瑞, 张晗, 梅铮, 王锐, 魏伟. 基于单目深度估计的低功耗视觉里程计[J]. 系统仿真学报, 2021, 33(12): 3001-3011.
[14]	杜金莲, 李淑飞, 金雪云. 三维烟雾流场超分辨率数据生成网络模型的研究[J]. 系统仿真学报, 2021, 33(10): 2381-2389.
[15]	刘瑞军, 王向上, 张晨, 章博华. 基于深度学习的视觉SLAM综述[J]. 系统仿真学报, 2020, 32(7): 1244-1256.