ACTA AERONAUTICAET ASTRONAUTICA SINICA >
Trajectory classification and anomaly detection based on stochastic depth ResNet
Received date: 2024-07-01
Revised date: 2024-08-14
Accepted date: 2024-10-08
Online published: 2024-10-23
Supported by
National Natural Science Foundation of China(U2333209);Civil Aviation Administration of China Safety Capacity Building Fund(MHAQ2022008)
In traditional trajectory similarity research, clustering algorithms have the problems of indistinct trajectory identification results, imprecise clustering, and larger time cost under the condition of high-dimensional data, especially under the condition of complex trajectory. To address these issues, we present a trajectory classification and anomaly detection model based on the improved stochastic depth network. Firstly, we optimize the attention mechanism Squeezed-and-Excitation (SE) module and Global Average Pool (GAP) module based on the ResNet model, and construct a trajectory classification network model. Secondly, in the data processing stage, the continuous spatiotemporal trajectory model is used to convert the discrete trajectory data into continuous data of the trajectory function of time for graph neural network processing. Then, nominal trajectory data is introduced into the training set to realize trajectory classification, with nominal trajectories as the reference. Finally, an improved twin neural network is developed based on the trajectory classification results, and is utilized for abnormal trajectory detection. Comprehensive experiments show that the proposed algorithm can efficiently complete the task of track classification according to nominal trajectories and detect abnormal trajectories accurately, compared with traditional track clustering algorithms.
Ge SONG , Pengfei HAN , Yuxiang LUO , Weijun PAN . Trajectory classification and anomaly detection based on stochastic depth ResNet[J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2025 , 46(4) : 330883 -330883 . DOI: 10.7527/S1000-6893.2024.30883
1 | WANG D, MIWA T, MORIKAWA T. Big trajectory data mining: A survey of methods, applications, and services[J]. Sensors, 2020, 20(16): 4571. |
2 | LIU Y, NG K K H, CHU N N, et al. Spatiotemporal image-based flight trajectory clustering model with deep convolutional autoencoder network[J]. Journal of Aerospace Information Systems, 2023, 20(9): 575-587. |
3 | DENG W, LI K P, ZHAO H M. A flight arrival time prediction method based on cluster clustering-based modular with deep neural network[J]. IEEE Transactions on Intelligent Transportation Systems, 2024, 25(6): 6238-6247. |
4 | 刘继新, 董欣放, 徐晨, 等. 基于密度峰值的终端区航迹聚类与异常识别[J]. 交通运输工程学报, 2021, 21(5): 214-226. |
LIU J X, DONG X F, XU C, et al. Aircraft trajectory clustering in terminal area and anomaly recognition based on density peak[J]. Journal of Traffic and Transportation Engineering, 2021, 21(5): 214-226 (in Chinese). | |
5 | WANG C, HUANG J H, WANG Y H, et al. A deep spatiotemporal trajectory representation learning framework for clustering[J]. IEEE Transactions on Intelligent Transportation Systems, 2024, 25(7): 7687-7700. |
6 | REDDY B S T, VALARMATHI J. Machine Learning Based Track Classification and Estimation using Kalman Filter[J]. International Journal of Recent Technology and Engineering (IJRTE), 2020, 9(1): 1700-1704. |
7 | 王增福, 潘泉, 陈丽平, 等. 基于航路-航迹关联的天波超视距雷达航迹分类[J]. 系统工程与电子技术, 2012, 34(10): 2018-2022. |
WANG Z F, PAN Q, CHEN L P, et al. Tracks classification based on airway-track association for over-the-horizon radar[J]. Systems Engineering and Electronics, 2012, 34(10): 2018-2022 (in Chinese). | |
8 | 刘莉. 基于语义分析的航迹优化和分类[D]. 苏州: 苏州大学, 2020. |
LIU L. Route optimization and classification based on semantic analysis[D]. Suzhou: Soochow University, 2020 (in Chinese). | |
9 | 王超, 王明明, 王飞. 基于改进的模糊C-Means航迹聚类方法研究[J]. 中国民航大学学报, 2013, 31(3): 14-18. |
WANG C, WANG M M, WANG F. Trajectory clustering method research based on improved Fuzzy C-Means[J]. Journal of Civil Aviation University of China, 2013, 31(3): 14-18 (in Chinese). | |
10 | 杨翠芳, 刘硕, 李宏博, 等. 一种基于随机森林的航迹起始算法[J]. 信息化研究, 2018, 44(6): 16-20. |
YANG C F, LIU S, LI H B, et al. A new track initiation algorithm based on random forest[J]. Informatization Research, 2018, 44(6): 16-20 (in Chinese). | |
11 | GUI X H, ZHANG J F, PENG Z H. Trajectory clustering for arrival aircraft via new trajectory representation[J]. Journal of Systems Engineering and Electronics, 2021, 32(2): 473-486. |
12 | OLIVE X, MORIO J. Trajectory clustering of air traffic flows around airports[J]. Aerospace Science and Technology, 2019, 84: 776-781. |
13 | 申正义, 李平, 王洪林, 等. 基于航迹数据的改进DBSCAN聚类算法研究[J]. 空天预警研究学报, 2024, 38(02): 128-131. |
SHEN Z Y, LI P, WANG H L,et al. Research on improved DBSCAN clustering algorithm based on trajectory data[J]. Journal of Air and Space Warning Research,2024,38(02):128-131 (in Chinese). | |
14 | ZENG W L, XU Z F, CAI Z P, et al. Aircraft trajectory clustering in terminal airspace based on deep autoencoder and Gaussian mixture model[J]. Aerospace, 2021, 8(9): 266. |
15 | 王超, 李昊昱, 陈含露. 基于形态特征的终端区进场中心航迹识别方法[J]. 科学技术与工程, 2023, 23(26): 11445-11451. |
WANG C, LI H Y, CHEN H L. Center trajectory extraction in terminal area based on one way distance and density-peak clustering[J]. Science Technology and Engineering, 2023, 23(26): 11445-11451 (in Chinese). | |
16 | KRIZHEVSKY A, SUTSKEVER I, HINTON G E. ImageNet classification with deep convolutional neural networks[J]. Communications of the ACM, 2017, 60(6): 84-90. |
17 | SIMONYAN K, ZISSERMAN A. Very deep convolutional networks for large-scale image recognition[DB/OL]. arXiv preprint: 1409.1556;2014. |
18 | SZEGEDY C, LIU W, JIA Y Q, et al. Going deeper with convolutions[C]∥2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway: IEEE Press, 2015: 1-9. |
19 | HE K M, ZHANG X Y, REN S Q, et al. Deep residual learning for image recognition[C]∥2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway: IEEE Press, 2016: 770-778. |
20 | 李超能, 冯冠文, 姚航, 等. 轨迹异常检测研究综述[J]. 软件学报, 2024, 35(2): 927-974. |
LI C N, FENG G W, YAO H, et al. Survey on trajectory anomaly detection[J]. Journal of Software, 2024, 35(2): 927-974 (in Chinese). | |
21 | 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). | |
22 | KUMAR D, BEZDEK J C, RAJASEGARAR S, et al. A visual-numeric approach to clustering and anomaly detection for trajectory data[J]. The Visual Computer, 2017, 33(3): 265-281. |
23 | SALARPOUR A, KHOTANLOU H. Direction-based similarity measure to trajectory clustering[J]. IET Signal Processing, 2019, 13(1): 70-76. |
24 | 饶丹, 时宏伟. 基于深度聚类的航空交通流识别与异常检测研究[J]. 计算机科学, 2023, 50(3): 121-128. |
RAO D, SHI H W. Study on air traffic flow recognition and anomaly detection based on deep clustering[J]. Computer Science, 2023, 50(3): 121-128 (in Chinese). | |
25 | 王志森, 张召悦, 冯朝辉, 等. 终端区飞行轨迹聚类分析及异常轨迹识别[J]. 科学技术与工程, 2022, 22(9): 3807-3814. |
WANG Z S, ZHANG Z Y, FENG Z H, et al. Cluster analysis of flight trajectories in terminal area and identification of abnormal trajectories[J]. Science, Technology and Engineering, 2022, 22(9): 3807-3814 (in Chinese). | |
26 | 王华溢, 黄要诚, 蔡波. 基于传统方法与深度学习方法的图片相似度算法比较[J]. 计算机系统应用, 2024, 33(2): 253-264. |
WANG H Y, HUANG Y C, CAI B. Comparison of image similarity algorithms based on traditional methods and deep learning methods[J]. Computer Systems & Applications, 2024, 33(2): 253-264 (in Chinese). | |
27 | HUANG G, SUN Y, LIU Z, et al. Deep networks with stochastic depth[M]∥LEIBE B, MATAS J, SEBE N, et al, eds. Lecture Notes in Computer Science. Cham: Springer Cham, 2016: 646-661. |
28 | LAXHAMMAR R, FALKMAN G. Online learning and sequential anomaly detection in trajectories[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2014, 36(6): 1158-1173. |
29 | TAHA A A, HANBURY A. An efficient algorithm for calculating the exact Hausdorff distance[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 37(11): 2153-2163. |
/
〈 |
|
〉 |