UAV abnormal behavior detection based on improved iForest algorithm

TANG Li; HAO Peng; REN Peige; ZHANG Zuyao; HE Xiang; ZHANG Xuejun

doi:10.7527/S1000-6893.2022.26789

ACTA AERONAUTICAET ASTRONAUTICA SINICA >

2022 , Vol. 43 >Issue 8: 326789 - 326789

DOI: https://doi.org/10.7527/S1000-6893.2022.26789

Electronics and Electrical Engineering and Control

UAV abnormal behavior detection based on improved iForest algorithm

TANG Li ,
HAO Peng ,
REN Peige ,
ZHANG Zuyao ,
HE Xiang ,
ZHANG Xuejun

Expand

1. Intelligent Air-Ground Fusion Vehicle and Control Engineering Research Center of the Ministry of Education, Xihua University, Chengdu 610039, China;
2. National Airspace Management Center, Beijing 100094, China;
3. School of Automobile and Transportation, Xihua University, Chengdu 610039, China;
4. School of Aeronautics and Astronautics, Xihua University, Chengdu 610039, China

Received date: 2021-12-09

Revised date: 2022-03-23

Online published: 2022-03-22

Supported by

National Natural Science Foundation of China (5210120621);Horizontal Scientific Research Fund (RH1900010872)

Fold

Abstract

To further improve the control ability of low altitude UAV and break through the key technologies of accurate monitoring of cooperative UAV operation state and rapid judgment of the type of non-cooperative UAV task, a method for UAV abnormal behavior detection is studied. Firstly, the abnormal behaviors in the operation of cooperative and non-cooperative UAVs are defined. The operation parameters of the two types of UAVs are analyzed, and the extraction methods of various operation characteristics and judgment parameters are determined. Then, a UAV type determination method is proposed based on the Sobel Operator-CNN algorithm. Finally, the improved isolated Forest (iForest) algorithm based on the method of dynamic maximum growth height is proposed to distinguish the abnormal behavior of cooperative and non-cooperative UAVs. The task characteristics and abnormal types of UAVs are determined according to data nodes. The results of test based on the ardupilot-airsim experimental platform show that the improved iForest algorithm has the characteristics of fast convergence speed and high accuracy, and abnormal-behavior recognition accuracy of the algorithm is 96.4%, which is 3.2% higher than that of the traditional algorithm.

Key words： UAV monitoring technology; UAV identification and classification; abnormal behavior detection; Sobel Operator-CNN algorithm; improved isolated Forest (iForest) algorithm

Cite this article

TANG Li , HAO Peng , REN Peige , ZHANG Zuyao , HE Xiang , ZHANG Xuejun . UAV abnormal behavior detection based on improved iForest algorithm[J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2022 , 43(8) : 326789 -326789 . DOI: 10.7527/S1000-6893.2022.26789

References

[1] 张东军, 陈世伟. 无人机的发展及在交通管理领域应用的综述[J]. 科技广场, 2019(4): 84-90. ZHANG D J, CHEN S W. Overview of UAV development and its application in traffic management[J]. Science Mosaic, 2019(4): 84-90 (in Chinese).
[2] 白玉. 四旋翼无人机的应用与发展综述[J]. 广西农业机械化, 2020(2): 7, 9. BAI Y. Overview of application and development of four-rotor UAV[J]. Guang Xi Agricultural Mechanization, 2020(2): 7, 9 (in Chinese).
[3] 覃洪战. 对无人机反制系统干扰的排查及思考[J]. 中国无线电, 2021(8): 61-63. QIN H Z. Investigation and study on radio anti-drone systems[J]. China Radio, 2021(8): 61-63 (in Chinese).
[4] 程擎, 伍瀚宇, 吉鹏, 等. 民用无人机反制技术及应用场景分析[J]. 电讯技术, 2022, 62(3): 389-398. CHENG Q, WU H Y, JI P, et al. Civilian UAV countermeasures and application scene analysis[J]. Telecommunication Engineering, 2022, 62(3): 389-398 (in Chinese).
[5] XIAO K, ZHAO J Y, HE Y H, et al. Abnormal behavior detection scheme of UAV using recurrent neural networks[J]. IEEE Access, 2019, 7: 110293-110305.
[6] 吴奇, 储银雪. 基于深度学习的航空器异常飞行状态识别[J]. 民用飞机设计与研究, 2017(3): 68-78, 4. WU Q, CHU Y X. Abnormal flight states of aircraft identification based on deep learning method[J]. Civil Aircraft Design & Research, 2017(3): 68-78, 4 (in Chinese).
[7] 张余, 葛飞. 基于航迹数据的飞行状态识别方法研究[J]. 航空计算技术, 2017, 47(6): 45-48, 51. ZHANG Y, GE F. Research on flight state recognition method based on track data[J]. Aeronautical Computing Technique, 2017, 47(6): 45-48, 51 (in Chinese).
[8] 潘新龙, 王海鹏, 何友, 等. 基于多维航迹特征的异常行为检测方法[J]. 航空学报, 2017, 38(4): 320442. PAN X L, WANG H P, HE Y, et al. Anomalous behavior detection method based on multidimensional trajectory characteristics[J]. Acta Aeronautica et Astronautica Sinica, 2017, 38(4): 320442 (in Chinese).
[9] MEDEL J R, SAVAKIS A. Anomaly detection in video using predictive convolutional long short-term memory networks[DB/OL]. arXiv preprint: 1612.00390, 2016.
[10] 祝彦森. 基于改进iForest的学生异常行为检测及分析系统研究[D]. 南京: 南京信息工程大学, 2019. ZHU Y S. Research on student anomaly behavior detection and analysis system based on improved iForest[D]. Nanjing: Nanjing University of Information Science & Technology, 2019 (in Chinese).
[11] 任家东, 刘新倩, 王倩, 等. 基于KNN离群点检测和随机森林的多层入侵检测方法[J]. 计算机研究与发展, 2019, 56(3): 566-575. REN J D, LIU X Q, WANG Q, et al. An multi-level intrusion detection method based on KNN outlier detection and random forests[J]. Journal of Computer Research and Development, 2019, 56(3): 566-575 (in Chinese).
[12] 王诚, 狄萱. 孤立森林算法研究及并行化实现[J]. 计算机技术与发展, 2021, 31(6): 13-18. WANG C, DI X. Research and parallelization of isolation forest algorithm[J]. Computer Technology and Development, 2021, 31(6): 13-18 (in Chinese).
[13] MADHUKAR RAO G, RAMESH D. A hybrid and improved isolation forest algorithm for anomaly detection[C]//Proceedings of International Conference on Recent Trends in Machine Learning, IoT, Smart Cities and Applications, 2021.
[14] 陈婧, 徐佳琦, 李心玥, 等. 无监督机器学习异常检测技术在智能监控领域的应用展望[J]. 中国金融电脑, 2021(2): 81-86. CHEN J, XU J Q, LI X Y, et al. Application and prospect of unsupervised machine learning anomaly detection technology in intelligent monitoring field[J]. Financial Computer of China, 2021(2): 81-86 (in Chinese).
[15] TANG B, HE H B. A local density-based approach for outlier detection[J]. Neurocomputing, 2017, 241:171-180.
[16] 刘伟博, 白鲲. 基于神经网络的运动视频图像分类和识别研究[J]. 现代电子技术, 2021, 44(20): 163-167. LIU W B, BAI K. Research on motion video image classification and recognition based on neural network[J]. Modern Electronics Technique, 2021, 44(20): 163-167 (in Chinese).
[17] 陈波冯, 李靖东, 卢兴见, 等. 基于深度学习的图异常检测技术综述[J]. 计算机研究与发展, 2021, 58(7):1436-1455. CHEN B F, LI J D, LU X J, et al. Survey of deep learning based graph anomaly detection methods[J]. Journal of Computer Research and Development, 2021,58(7): 1436-1455 (in Chinese).
[18] LI Y C, ZHOU R G, XU R Q, et al. A quantum deep convolutional neural network for image recognition[J]. Quantum Science and Technology, 2020, 5(4): 044003.
[19] 季长清, 高志勇, 秦静, 等. 基于卷积神经网络的图像分类算法综述[J]. 计算机应用, 2022, 42(4): 1044-1049. JI C Q, GAO Z Y, QIN J, et al. Review of image classification algorithms based on convolutional neural network[J]. Journal of Computer Applications, 2022, 42(4): 1044-1049 (in Chinese).
[20] 王泽伟, 高丙朋. 基于时空融合卷积神经网络的异常行为识别[J]. 计算机工程与设计, 2020, 41(7): 2052-2056. WANG Z W, GAO B P. Spatio-temporal fusion convolutional neural network for abnormal behavior recognition[J]. Computer Engineering and Design, 2020, 41(7): 2052-2056 (in Chinese).
[21] 陈兴蜀, 金逸灵, 王玉龙, 等. 基于长短期记忆神经网络的容器内进程异常行为检测[J]. 电子学报, 2021, 49(1): 149-156. CHEN X S, JIN Y L, WANG Y L, et al. Anomaly detection of processes behavior in container based on LSTM neural network[J]. Acta Electronica Sinica, 2021, 49(1): 149-156 (in Chinese).
[22] 薛宏伟, 刘赢, 庄伟超, 等. 车联网环境下基于Stacking集成学习的车辆异常行为检测方法[J]. 汽车工程, 2021, 43(4): 501-508, 536. XUE H W, LIU Y, ZHUANG W C, et al. A detection method of vehicular abnormal behaviors in V2X environment based on stacking ensemble learning[J]. Automotive Engineering, 2021, 43(4): 501-508, 536 (in Chinese).
[23] 王鹏宇, 程郁凡, 徐昊, 等. 基于卷积神经网络联合多域特征提取的干扰识别算法[J/OL]. 信号处理,2021:1-12[2021-10-31]. WANG P Y, CHENG Y F, XU H, et al. Jamming classification using convolutional neural network based joint multi-domain feature extraction[J/OL]. Journal of Signal Processing,2021:1-12[2021-10-31](in Chinese).

Options

Outlines

模态框（Modal）标题

Abstract

Cite this article

References