A cost-sensitive method for aerial target intention recognition

被引：0
|
作者：
Ding P. [1 ]
Song Y. [1 ]
机构：
[1] Air and Missile Defense College, Air Force Engineering University, Xi’an
来源：
Hangkong Xuebao/Acta Aeronautica et Astronautica Sinica | 2023年 / 44卷 / 24期
基金：
中国国家自然科学基金;
关键词：
aerial target; cost sensitive; deep learning; Fully Convolutional Networks (FCN); Gated Recurrent Unit (GRU); intention recognition;
D O I：
10.7527/S1000-6893.2023.28551
中图分类号：
学科分类号：
摘要：
Air intention recognition is the key to the transition from the information domain to the cognitive domain，serving as the basis for command and decision making in air defense operations，as well as the prerequisite and foun⁃ dation for battlefield cognition and intelligent decision making. It has always been considered the core content of battle⁃ field situational awareness. However，existing research mostly focuses solely on the accuracy of intention recognition，without considering whether the misjudgment costs of intention recognition are equivalent. Air target intention recogni⁃ tion should consider both accuracy and cost sensitivity. To solve the problem of different misjudgments that may cause different losses to our side，a new deep learning model（GRU-FCN）for cost sensitive aerial target intention recogni⁃ tion is designed based on gated cyclic units and fully convolutional networks，and a cost sensitive improvement strat⁃ egy is also proposed. Experimental analysis shows that the accuracy of the GRU-FCN model reaches 98. 57%，sur⁃ passing other aerial target intention recognition models in the comparative experiment by 2. 24%. After incorporating the cost sensitive improvement strategy，the overall misjudgment cost has been reduced from 0. 346 7 to 0. 175 7，en⁃ suring that the accuracy meets the requirements while also possessing the ability to recognize cost sensitive intentions. © 2023 AAAS Press of Chinese Society of Aeronautics and Astronautics. All rights reserved.
引用
收藏
相关论文
共 38 条
  • [1] YAO Q K, LIU S J，, HE X Y，, Et al., Research and pros⁃ pect of battlefield target operational intention recognition ［J］, Journal of Command and Control, 3, 2, pp. 127-131, (2017)
  • [2] XIA P C，, CHEN M, Et al., Prediction of air tar⁃ get intention utilizing incomplete information［C］∥Chi⁃ nese Intelligent Systems Conference, pp. 395-403, (2016)
  • [3] CHEN Y M, LI C Y., Simulation of target tactical inten⁃ tion recognition based on knowledge map［J］, Computer Simulation, 36, 8, pp. 1-4, (2019)
  • [4] YIN X, ZHANG M, CHEN M Q., Combat intention rec⁃ ognition of the target in the air based on discriminant analysis［J］, Journal of Projectiles， Rockets， Missiles and Guidance, 38, 3, pp. 46-50, (2018)
  • [5] CHENG S Y，, ZHANG H B，, Et al., Air target combat intention identification based on IE-DSBN［C］∥ 2020 International Workshop on Electronic Communica⁃ tion and Artificial Intelligence（IWECAI）, pp. 36-40, (2020)
  • [6] YANG R N，, FU Y., Situation assessment for air combat based on novel semi-supervised naive Bayes ［J］, Journal of Systems Engineering and Electronics, 29, 4, pp. 768-779, (2018)
  • [7] ZHOU W W, YAO P Y, ZHANG J Y，, Et al., Combat in⁃ tention recognition for aerial targets based on deep neural network［J］, Acta Aeronautica et Astronautica Sinica, 39, 11, (2018)
  • [8] ZHAI X Y, YANG F B, JI L N，, Et al., Air combat tar⁃ gets threat assessment based on standardized fully con⁃ nected network and residual network［J］, Fire Control & Command Control, 45, 6, pp. 39-44, (2020)
  • [9] QIAN Z, LU Y，, Et al., Identification of target’s combat intention based on long short term memory net⁃ work［J］, Journal of Terahertz Science and Electronic In⁃ formation Technology, 20, 11, pp. 1156-1162, (2022)
  • [10] HU Z Y, LIU H L, GONG S J，, Et al., Target intention recognition based on random forest［J］, Modern Electron⁃ ics Technique, 45, 19, pp. 1-8, (2022)
1234