Air Combat Intention Recognition with Incomplete Information Based on Decision Tree and GRU Network
Battlefield information is generally incomplete, uncertain, or deceptive. To realize enemy intention recognition in an uncertain and incomplete air combat information environment, a novel intention recognition method is proposed. After repairing the missing state data of an enemy fighter, the gated...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-04-01
|
Series: | Entropy |
Subjects: | |
Online Access: | https://www.mdpi.com/1099-4300/25/4/671 |
_version_ | 1797605559875141632 |
---|---|
author | Jingyang Xia Mengqi Chen Weiguo Fang |
author_facet | Jingyang Xia Mengqi Chen Weiguo Fang |
author_sort | Jingyang Xia |
collection | DOAJ |
description | Battlefield information is generally incomplete, uncertain, or deceptive. To realize enemy intention recognition in an uncertain and incomplete air combat information environment, a novel intention recognition method is proposed. After repairing the missing state data of an enemy fighter, the gated recurrent unit (GRU) network, supplemented by the highest frequency method (HFM), is used to predict the future state of enemy fighter. An intention decision tree is constructed to extract the intention classification rules from the incomplete a priori knowledge, where the decision support degree of attributes is introduced to determine the node-splitting sequence according to the information entropy of partitioning (IEP). Subsequently, the enemy fighter intention is recognized based on the established intention decision tree and the predicted state data. Furthermore, a target maneuver tendency function is proposed to screen out the possible deceptive attack intention. The one-to-one air combat simulation shows that the proposed method has advantages in both accuracy and efficiency of state prediction and intention recognition, and is suitable for enemy fighter intention recognition in small air combat situations. |
first_indexed | 2024-03-11T05:02:49Z |
format | Article |
id | doaj.art-242a5f1f93974c558676606b42ad6219 |
institution | Directory Open Access Journal |
issn | 1099-4300 |
language | English |
last_indexed | 2024-03-11T05:02:49Z |
publishDate | 2023-04-01 |
publisher | MDPI AG |
record_format | Article |
series | Entropy |
spelling | doaj.art-242a5f1f93974c558676606b42ad62192023-11-17T19:09:26ZengMDPI AGEntropy1099-43002023-04-0125467110.3390/e25040671Air Combat Intention Recognition with Incomplete Information Based on Decision Tree and GRU NetworkJingyang Xia0Mengqi Chen1Weiguo Fang2School of Management, Wuhan University of Science and Technology, Wuhan 430081, ChinaSchool of Advanced Interdisciplinary Studies, Hunan University of Technology and Business, Changsha 410205, ChinaSchool of Economics and Management, Beihang University, Beijing 100191, ChinaBattlefield information is generally incomplete, uncertain, or deceptive. To realize enemy intention recognition in an uncertain and incomplete air combat information environment, a novel intention recognition method is proposed. After repairing the missing state data of an enemy fighter, the gated recurrent unit (GRU) network, supplemented by the highest frequency method (HFM), is used to predict the future state of enemy fighter. An intention decision tree is constructed to extract the intention classification rules from the incomplete a priori knowledge, where the decision support degree of attributes is introduced to determine the node-splitting sequence according to the information entropy of partitioning (IEP). Subsequently, the enemy fighter intention is recognized based on the established intention decision tree and the predicted state data. Furthermore, a target maneuver tendency function is proposed to screen out the possible deceptive attack intention. The one-to-one air combat simulation shows that the proposed method has advantages in both accuracy and efficiency of state prediction and intention recognition, and is suitable for enemy fighter intention recognition in small air combat situations.https://www.mdpi.com/1099-4300/25/4/671air combatGRU networkintention recognitiondecision treeincomplete information |
spellingShingle | Jingyang Xia Mengqi Chen Weiguo Fang Air Combat Intention Recognition with Incomplete Information Based on Decision Tree and GRU Network Entropy air combat GRU network intention recognition decision tree incomplete information |
title | Air Combat Intention Recognition with Incomplete Information Based on Decision Tree and GRU Network |
title_full | Air Combat Intention Recognition with Incomplete Information Based on Decision Tree and GRU Network |
title_fullStr | Air Combat Intention Recognition with Incomplete Information Based on Decision Tree and GRU Network |
title_full_unstemmed | Air Combat Intention Recognition with Incomplete Information Based on Decision Tree and GRU Network |
title_short | Air Combat Intention Recognition with Incomplete Information Based on Decision Tree and GRU Network |
title_sort | air combat intention recognition with incomplete information based on decision tree and gru network |
topic | air combat GRU network intention recognition decision tree incomplete information |
url | https://www.mdpi.com/1099-4300/25/4/671 |
work_keys_str_mv | AT jingyangxia aircombatintentionrecognitionwithincompleteinformationbasedondecisiontreeandgrunetwork AT mengqichen aircombatintentionrecognitionwithincompleteinformationbasedondecisiontreeandgrunetwork AT weiguofang aircombatintentionrecognitionwithincompleteinformationbasedondecisiontreeandgrunetwork |