An interpretable real-time maneuver identification algorithm based on early time series classification

Computer Engineering & Science ›› 2024, Vol. 46 ›› Issue (02): 353-362.

• Artificial Intelligence and Data Mining • Previous Articles Next Articles

An interpretable real-time maneuver identification algorithm based on early time series classification

PANG Nuo-yan，GUAN Dong-hai，YUAN Wei-wei

The maneuver identification of fighter aircraft is the basis for judging their tactical intentions, but the existing maneuver identification methods have weak real-time performance and lack interpretability, which cannot meet the real-time requirements in air combat and are not conducive to human-machine trust. This paper designs a real-time maneuver identification algorithm based on early time- series classification, which divides the complete maneuver into maneuver units and uses ensemble learning algorithm to recognize and monitor the maneuver units in real-time, in order to achieve real-time requirements and obtain high recognition accuracy. The algorithm uses interpretable models and explains the model through feature contribution, making the model more transparent and reducing the decision risk for air combat decision-makers. Nine different maneuvers, such as hovering and jackknifing, are selected for simulation experiments, which proves that the algorithm can complete the identification with only the first 20% of the sample data of the time series observed, and the identification accuracy can reach 93%.

Received:2022-10-28 Revised:2023-03-12 Accepted:2024-02-25 Online:2024-01-25 Published:2024-02-26

Abstract

PANG Nuo-yan, GUAN Dong-hai, YUAN Wei-wei. An interpretable real-time maneuver identification algorithm based on early time series classification[J]. Computer Engineering & Science, 2024, 46(02): 353-362.

References ［19］

［1］	Samuel K,Gadepally V,Jacobs D,et al.Maneuver identification challenge［C］∥Proc of 2021 IEEE High Performance Extreme Computing Conference,2021:1-7.
［2］	贾镇泽,樊晓光,薛明浩,等.基于机动动作元的敌机战术机动在线识别方法［J］.北京理工大学学报,2018,38(8): 820-827.
	Jia Zhen-ze,Fan Xiao-guang,Xue Ming-hao,et al.Online identification method for tactical maneuver of target based on air combat maneuver element［J］.Transactions of Beijing Institute of Technology,2018,38(8): 820-827.
［3］	Wang Y J,Dong J, Liu X D,et al.Identification and standardization of maneuvers based upon operational flight data［J］.Chinese Journal of Aeronautics,2015,28(1):133-140.
［4］	李鸿利,单征,郭浩然.基于MDTW的飞行动作识别算法［J］.计算机工程与应用,2015,51(9): 267-270.
	Li Hong-li,Shan Zheng,Guo Hao-ran.Flight action recognition algorithm based on MDTW［J］.Computer Engineering and Applications,2015,51(9): 267-270.
［5］	王志刚,杨宁,米禹丰.基于动态时间规划和支持向量机的飞机机动动作识别方法［J］.飞机设计,2020,40(4): 35-40.
	Wang Zhi-gang,Yang Ning,Mi Yu-feng.Method on aircraft maneuver motion recognition based on dynamic time warping and support vector machine［J］.Aircraft Design,2020,40(4):35-40.
［6］	徐西蒙,杨任农,于洋,等.基于运动分解和H-SVM的空战目标机动识别［J］.控制与决策,2020,35(5): 1265-1272.
	Xu Xi-meng,Yang Ren-nong,Yu Yang,et al.Target maneuver recognition in air combat based on motion decomposition and H-SVM［J］.Control and Decision,2020,35(5):1265-1272.
［7］	魏政磊,董康生,岑飞,等.一种在线飞机机动轨迹识别方法［C］∥第五届中国航空科学技术大会论文集,2021:733-740.
	Wei Zheng-lei,Dong Kang-sheng,Cen Fei,et al.An online aircraft maneuver trajectory recognition method［C］∥Proc of the 5th Chinese Aeronautics Science and Technology Confe- rence,2021:733-740.
［8］	沈一超,倪世宏,张鹏.基于贝叶斯网络的飞行动作识别方法［J］.计算机工程与应用,2017,53(24): 161-167.
	Shen Yi-chao,Ni Shi-hong,Zhang Peng.Flight action recognition method based on Bayesian network［J］.Computer Engineering and Applications,2017,53(24): 161-167.
［9］	刘浩,王昊,孟光磊,等.基于动态贝叶斯网络和模糊灰度理论的飞行训练评估［J］.航空学报,2021,42(8):525838.
	Liu Hao,Wang Hao,Meng Guang-lei,et al.Flight training evaluation based on dynamic Bayesian network and fuzzy gray theory［J］.Acta Aeronautica ET Astronautica Sinica,2021,42(8): 525838.
［10］	彭章友,陈琳妍,刘洋.基于BPNN的机动识别方法［J］.电子测量技术,2019,42(15): 12-17.
	Peng Zhang-you,Chen Lin-yan,Liu Yang.A novel maneuver recognition algorithm based on back propagation neural network［J］.Electronic Measurement Technology,2019,42(15):12-17.
［11］	周亚楠,聂帅.基于循环神经网络的飞行机动识别方法及仿真研究［J］.中国电子科学研究院学报,2020,15(6):539-546.
	Zhou Ya-nan,Nie Shuai.A flight maneuver recognition approach and simulation study based on recurrent neural network［J］.Journal of CAEIT,2020,15(6):539-546.
［12］	杨梦晨,陈旭栋,蔡鹏,等.早期时间序列分类方法研究综述［J］.华东师范大学学报(自然科学版),2021,2021(5): 115-133.
	Yang Meng-chen,Chen Xu-dong,Cai Peng,et al.Survey of early time series classification methods［J］.Journal of East China Normal University(Natural Science),2021,2021(5): 115-133.
［13］	Xing Z Z, Pei J,Yu P S.Early classification on time series［J］.Knowledge and Information Systems,2012,31(1):105-127.
［14］	Xing Z Z,Pei J,Yu P S,et al.Extracting interpretable features for early classification on time series［C］∥Proc of the 11th SIAM International Conference on Data Mining,2011:28-30.
［15］	Schfer P,Leser U.TEASER: Early and accurate time series classification［J］.Data Mining and Knowledge Discovery,2020,34(9):1336-1362.
［16］	Prokhorenkova L, Gusev G,Vorobev A,et al.CatBoost: Unbiased boosting with categorical features［C］∥Proc of the 32nd International Conference on Neural Information Processing Systems,2018: 6639-6649.
［17］	Lundberg S, Lee S I. A unified approach to interpreting model predictions［C］∥Proc of the 31st International Conference on Neural Information Processing Systems,2017:4768-4777.
［18］	Liu W R,Deng K Y,Zhang X Y,et al.A semi-supervised Tri-CatBoost method for driving style recognition［J］.Symmetry,2020,12(3):336.
［19］	张芸.基于复合CatBoost的银行客户流失预测模型［D］.兰州:兰州大学,2021.
	Zhang Yun.Prediction model of bank customer churn based on hybrid CatBoost［D］.Lanzhou:Lanzhou University,2021.

An interpretable real-time maneuver identification algorithm based on early time series classification

PDF

Knowledge

Abstract

Cite this article

share this article

References ［19］

Related Articles 0

Recommended Articles

Metrics

Comments