Hurricane Trajectory Outlier Detection Method Based on Variational Auto-encode

doi:10.16182/j.issn1004731x.joss.20-0369

Abstract

Abstract: Hurricanes often cause incalculable human and economic losses, and the trajectory outlier detection can provide the auxiliary information or abnormal warning of the disaster. On deep learning, a method of hurricane trajectory outlier detection based on variable auto encoder (VAEOD) is proposed in this paper. The trajectory is divided into equal sequence sub trajectories based on the sliding window as the input of VAE. The trajectory reconstruction model is trained by the VAE. The parallel, vertical and angle distance of reconstructed trajectory and the input trajectory are compared to find out the outlier trajectory segments. The simulation experiment on real hurricane data shows that the VAEOD method is more rational and practical than the classical TRAOD method.

Key words: variational auto-encoder, space distance, sliding window, outlier detection

CLC Number:

TP391.9

Qin Wanting, Lao Songyang, Tang Jun, Lu Cong. Hurricane Trajectory Outlier Detection Method Based on Variational Auto-encode[J]. Journal of System Simulation, 2021, 33(9): 2191-2201.

References

[1] Meuel T, Prado G, Seychelles F, et al. Hurricane Track Forecast Cones from Fluctuations[J]. Scientific Reports (S2045-2322), 2012, 2: No.446.
[2] Mann M E, Woodruff J D, Donnelly J P, et al.Atlantic Hurricanes and Climate Over the Past 1,500 Years[J]. Nature (S0028-0836), 2009, 460(7257): 880-883.
[3] Zheng Y.Trajectory Data Mining: An Overview[J]. ACM Transactions on Intelligent Systems and Technology (S2157-6904), 2015, 6(3): 1-41.
[4] Tang J.Conflict Detection and Resolution for Civil Aviation: A Literature Survey[J]. IEEE Aerospace and Electronic Systems Magazine (S0018-9251), 2019, 34(10): 20-35.
[5] Meng F, Yuan G, Lv S, et al.An Overview on Trajectory Outlier Detection[J]. Artificial Intelligence Review (S0269-2821), 2019, 52(4): 2473-2456.
[6] Tang J, Piera M A, Guasch T.Coloured Petri Net-based Traffic Collision Avoidance System Encounter Model for the Analysis of Potential Induced Collisions[J]. Transportation Research Part C: Emerging Technologies (S0968-090X), 2016, 67: 357-377.
[7] Tang J, Zhu F, Piera M A.A Causal Encounter Model of Traffic Collision Avoidance System Operations for Safety Assessment and Advisory Optimization in High-density Airspace[J]. Transportation Research Part C: Emerging Technologies (S0968-090X), 2018, 96: 347-365.
[8] Lee J G, Han J, Li X.Trajectory outlier detection: A partition-and-detect framework[C]//2008 IEEE 24th International Conference on Data Engineering. Cancun, Mexico: IEEE, 2008: 140-149.
[9] Lee J G, Han J W, Whang K Y.Trajectory Clustering: A Partition-and-group Framework[C]//2007 ACM SIGMOD International Conference on Management of Data. Beijing: ACM, 2007: 593-604.
[10] Liu Z, Pi D, Jiang J.Density-based Trajectory Outlier Detection Algorithm[J]. Journal of Systems Engineering & Electronics (S1004-4132), 2013, 24(2): 335-340.
[11] Ge Y, Xiong H, Zhou Z H, et al.Top-Eye: Top-k Evolving Trajectory Outlier Detection[C]//19th ACM Conference on Information and Knowledge Management. Toronto: ACM, 2010: 1733-1736.
[12] Pang L X, Chawla S, Liu W, et al.On Mining Anomalous Patterns in Road Traffic Streams[C]//Advanced Data Mining and Applications - 7th International Conference. Beijing: Springer-Verlag, 2011: 237-251.
[13] Pang L X, Chawla S, Liu W, et al.On Detection of Emerging Anomalous Traffic Patterns Using GPS Data[J]. Data & Knowledge Engineering (S0169-023X), 2013, 87(9): 357-373.
[14] Li X, Han J, Kim S, et al.ROAM: Rule and Motif-based Anomaly Detection in Massive Moving Object Data Sets[C]//7th SIAM International Conference on Data Mining. New Orleans: SIAM, 2007: 296-307.
[15] Piciarelli C, Foresti G L.Anomalous Trajectory Detection Using Support Vector Machines[C]//2007 IEEE Conference on Advanced Video and Signal Based Surveillance. London: IEEE, 2007: 153-158.
[16] Alahi A, Goel K, Ramanathan V, et al.Social LSTM: Human Trajectory Prediction in Crowded Spaces[C]// IEEE conference on computer vision and pattern recognition. Las Vegas: IEEE, 2016: 961-971.
[17] Hinton G E.Reducing the Dimensionality of Data with Neural Networks[J]. Science (S0036-8075), 2006, 313(5786): 504-507.
[18] Kingma D P, Welling M. Auto-Encoding Variational Bayes[EB/OL]. (2013-12-20) [2020-05-24]. https://arxiv. org/abs/1312.6114.
[19] Rezende D J, Mohamed S, Wierstra D. Stochastic Backpropagation and Approximate Inference in Deep Generative Models[EB/OL]. (2014-02-16) [2020-05-24]. https://arxiv. org/abs/1401.4082.
[20] 方华强, 颜寒祺, 陈波, 等. 基于自编码网络的移动轨迹异常检测[J]. 地理信息世界, 2019, 26(5): 41-44.
Fang Huaqiang, Yan Hanqi, Chen Bo, et al.Anomaly Detection in Mobile Trajectory Using Auto-encoder Network[J]. Geomatics World, 2019, 26(5): 41-44.
[21] 霍纬纲, 王慧芳. 基于自编码器和隐马尔可夫模型的时间序列异常检测方法[J]. 计算机应用, 2020, 40(5):1329-1334.
Huo Weigang, Wang Huifang.Time Series Anomaly Detection Method Based on Autoencoder and HMM[J]. Journal of Computer Applications, 2020, 40(5): 1329-1334.
[22] Vincent P, Larochelle H, Bengio Y, et al.Extracting and Composing Robust Features with Denoising Autoencoders[C]//25^th International Conference on Machine Learning. Helsinki, Finland: ACM, 2008: 1096-1103.