期刊文献+

基于深度学习的战场态势高级理解模拟方法 被引量:27

Simulation Method of Battlefields Situation Senior Comprehension Based on Deep Learning
下载PDF
导出
摘要 当今军事领域问题的研究已步入了信息化主导的大数据时代,传统的智能辅助指挥员完成战场态势理解已遇到了瓶颈,亟需探索突破。认知智能中深度学习的提出可为该问题的突破提供契机。通常,指挥员进行战场态势理解是分层次的。其中的高级理解则需要深度学习来模拟。就此,展开了探索性研究。概述了战场态势评估的相关概念,分析了指挥员理解战场态势的思维模式,掌握了指挥员理解战场态势时的主要步骤,并结合深度学习运行原理,提出了一种基于深度学习的指挥员战场态势高级理解思维过程(以判断敌方对我方可能的主攻方向为例)模拟方法,该方法利用认知智能中的深度学习(以CNN为例)对指挥员战场态势高级理解过程进行非线性拟合处理,从而达到探索性模拟的目的,仿真实验结果验证了该方法的有效性。 Nowadays,the research of military field has entered into the era of Big Data dominated by information technology.The traditional intelligent assistant commander has been confronted with the bottleneck of the battlefield situation comprehension,needing to explore to breakthrough.Deep Learning within cognitive intelligence can provide an opportunity for the breakthrough.Usually,battlefield situation comprehension by commanders is hierarchical.However,the period of senior comprehension needs Deep Learning to simulate.Aimed at the issue of senior comprehension simulation,some exploring researches are carried out in the paper.The relative concepts of the battlefield situation assessment are generalized.The battlefield situation comprehension mode of thinking is analyzed,and the main steps of the battlefield situation comprehension by commanders are grasped.And combined with the operation principle of Deep Learning,an intelligent simulation method of the thinking process(example as judging the main offensive direction of enemy)of senior compre原hension of the commanders based on Deep Learning is put forward.In the method,Deep Learning(ex原ample as CNN)within cognitive intelligence is utilized to carry on the non-linear fitting for process of the commanders’battlefield situation senior comprehension,so as to achieve the purpose of simulation.The simulation results verify the effectiveness of the proposed method
作者 朱丰 胡晓峰 吴琳 贺筱媛 杨璐 ZHU Feng;HU Xiao-feng;WU Lin;HE Xiao-yuan;YANG Lu(National Defense University,Beijing 100091,China;Academy of Military Sciences,Beijing 100091,China;Unit 91053 of PLA,Beijing 100070,China;Air and Missile Defense College,Air Force Engineering University,Xi’an 710051,China)
出处 《火力与指挥控制》 CSCD 北大核心 2018年第8期25-30,共6页 Fire Control & Command Control
基金 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资助项目(2016M602996)
关键词 战场态势高级理解 指挥员思维过程 主攻方向判断 深度学习 CNN 模拟方法 battlefields situation senior comprehension thinking process of commanders judgment of main offensive direction deep learning CNN simulation method
  • 相关文献

参考文献4

二级参考文献67

  • 1史忠值.神经网络[M].北京:高等教育出版社,2009.
  • 2李彦宏.2012百度年会主题报告:相信技术的力量[R].北京:百度,2013.
  • 3Rumelhart D,Hinton G,Williams R.Learning representationsby back-propagating errors[J].Nature,1986,323(6088):533-536.
  • 4Hinton G,Salakhutdinov R.Reducing the dimensionality of data with neural networks[J].Science,2006,313(5786):504-507.
  • 5Ding Shi-fei,Zhang Yan-an,Chen Jin-rong,et al.Research onUsing Genetic Algorithms to Optimize Elman Neural Networks[J].Neural Computing and Applications,2013,23(2):293-297.
  • 6Ding Shi-fei,Jia Wei-kuan,Su Chun-yang,et al.Research ofNeural Network Algorithm Based on Factor Analysis and Cluster Analysis[J].Neural Computing and Applications,2011,20(2):297-302.
  • 7Lee T S,Mumford D.Hierarchical Bayesian inference in the vi-sual cortex[J].Optical Society of America,2003,20(7):1434-1448.
  • 8Serre T,Wolf L,Bileschi S,et al.Robust object recognition with cortex-like mechanisms[J].IEEE Trans on Pattern Analysis and Machine Intelligence,2007,29(3):411-426.
  • 9Lee T S,Mumford D,Romero R,et al.The role of the primary visual cortex in higher level vision[J].Vision Research,1998,38 (15):2429-2454.
  • 10Bengio Y.Learning deep architectures for AI[J].Foundations and Trends in Machine Learning,2009,2(1):1-127.

共引文献237

同被引文献241

引证文献27

二级引证文献185

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部