DOI:10.19850/j.cnki.2096-4706.2021.02.018

基金项目：国家自然科学基金资助项目（61872230，61572311）

中图分类号：TP39                                    文献标识码：A                                 文章编号：2096-4706（2021）02-0070-06

Traffic Flow Anomaly Detection Algorithm Based on Spatiotemporal Convolution Neural Network GL-GCN

XU Hongfei，LI Jing

（School of Computer Science and Technology，Shanghai University of Electric Power，Shanghai 200090，China）

Abstract：Traffic flow anomaly detection usually considers time information，spatial information and others，which makes traffic flow anomaly detection challenging. This paper focuses on the non-recurrent traffic anomaly inspection caused by traffic accidents or short-term events. The new algorithm（GL-GCN）uses the spatiotemporal data of traffic，the spatial information is captured by graph convolution network，and the time dependence is modeled by DeepGLO neural network. This algorithm captures spatiotemporal characteristics at the same time and establishes the traffic flow prediction model，and the traffic flow anomaly is judged by the anomaly score. The model is proved to be effective and superior by using the real traffic flow data.

Keywords：traffic flow；anomaly detection；deep neural network；graph convolutional network；spatiotemporal characteristics

参考文献：

[1] 陈珂，邹权. 融入时间关联因子曲线拟合的交通流异常挖掘方法 [J]. 计算机工程与设计，2013，34（7）：2561-2565.

[2] 黎维，陶蔚，周星宇，等. 时空序列预测方法综述 [J]. 计算机应用研究，2020，37（10）：2881-2888.

[3] WU X D，KUMAR V，QUINLAN J R. Top 10 algorithms in data mining [J].Knowledge and Information Systems，2018，14：1-37.

[4] GIANNAKERIS P，KALTSA V，AVGERINAKIS K. Speed Estimation and Abnormality Detection from Surveillance Cameras [C]//2018IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops （CVPRW）.Salt Lake City：IEEE，2018：93-936.

[5] HOCHREITER S，SCHMIDHUBER J. Long Short-Term Memory [J].Neural Computation，1997，9（8）：1735-1780.

[6] KING D P，WELLING M. Auto-Encoding Variational Bayes [J/OL].arXiv：1312.6114v10 [stat.ML].（2014-05-01）.https://arxiv.org/abs/1312.6114v10.

[7] PHILIP L，WANG L L，NGAN H Y T. Outlier Detection In Large-scale Traffic Data By Naitve Bayes Method and Gaussian Mixture Model Method [C]//Electronic Imaging，Intelligent Robotics and Industrial Applications using Computer Vision 2017.Society for Imaging Science and Technology，2017：73-78.

[8] TUROCHY R E，SMITH B L. Applying quality control to traffic condition monitoring [C]//ITSC2000. 2000 IEEE Intelligent Transportation Systems. Proceedings（Cat.No.00TH8493）.Dearborn，IEEE，2000：15-20.

[9] DANG T T，NGAN H Y T，LIU W. Distance-based k-nearest neighbors outlier detection method in large-scale traffic data [C]//2015 IEEE International Conference on Digital Signal Processing（DSP）.Singapore ：IEEE，2015：507-510.

[10] MA M X，NGAN H Y T，LIU W. Density-based Outlier Detection by Local Outlier Factor on Largescale Traffic Data [C]//Electronic Imaging，Image Processing：Machine Vision Applications IX.San Francisco：Society for Imaging Science and Technology：2016：1-4.

[11] MARKUS M，BREUNIG M M，KRIEGEL H P，et al.LOF：Identifying Density-Based Local Outliers [C]//Proceedings of the 2000 ACM SIGMOD international conference on management of data.Dallas：Association for Computing Machinery，2000：93-97.

[ 1 2 ] M U N O Z - O R G A N E R O M，R U I Z - B L A Q U E Z R，SÁNCHEZ-FERNÁNDEZ L. Automatic detection of traffic lights，

street crossings and urban roundabouts combining outlier detection and deep learning classification techniques based on GPS traces while driving[J].Computers，Environment and Urban Systems，2018，68：1-8.

[13] SHI Y，DENG M，YANG X X，et al. Detecting anomalies in spatio-temporal flow data by constructing dynamic neighbourhoods [J].Computers，Environment and Urban Systems，2018，67：80-96.

[14] WEN H Y，LUO J. Traffic Incident Detection for Urban Arterial Road Based on Data Fusion and Learning Vector Quantization[C]//First International Conference on Transportation Information and Safety（ICTIS）.Wuhan：American Society of Civil Engineers，2011.

[15] HSU D. Anomaly Detection on Graph Time Series [J/OL].arXiv：1708.02975v2 [cs.LG].（2017-11-01）.https://arxiv.org/abs/1708.02975v2.

[16] DEFFERRARD M，BRESSON X，VANDERGHEYNST P.Convolutional neural networks on graphs with fast localized spectral filtering [C]//NIPS’16：Proceedings of the 30th International

Conference on Neural Information Processing Systems.Red Hook：Curran Associates Inc.，2016：3844-3852.

[17] SEN R，YU H F，DHILLON I.Think Globally，Act Locally：A Deep Neural Network Approach to High-Dimensional Time Series Forecasting [J/OL].arXiv：1905.03806v2 [stat.ML]（. 2019-10-27）.https://arxiv.org/abs/1905.03806v2.

[18] BAI S J，KOLTER Z，KOLTUN V. An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling [J/OL].arXiv：1803.01271v2 [cs.LG].（2018-04-19）.https://arxiv.org/abs/1803.01271v2.

[ 1 9 ] L I Y G，Y U R，S H A H A B I C，e t a l . D i f f u s i o n Convolutional Recurrent Neural Network：Data-Driven Traffic

Forecasting [J/OL].arXiv：1707.01926v3 [cs.LG].（2018-01-22）.https://arxiv.org/abs/1707.01926v3.

[20] AHMED M S，COOK A R. Analysis of freeway traffic time series data by using Box-Jenkins techniques [J].Transportation Research Record Journal of the Transportation Research Board，1979，773（722）：1-9.

[21] SMOLA A J，SCHÖLKOPF B. A tutorial on support vector regression [J].Statistics and Computing，2004，14：199-222.

[22] OORD A V D，DIELEMAN S，ZEN H，et al. WaveNet：A Generative Model for Raw Audio [J/OL].arXiv：1609.03499v2 [cs.SD].（2016-08-19）.https://arxiv.org/abs/1609.03499v2.

[23] YU B，YIN H T，ZHU Z X.Spatio-Temporal Graph Convolutional Networks：A Deep Learning Framework for Traffic Forecasting [J/OL].arXiv：1709.04875v4 [cs.LG].（2018-07-12）.https://arxiv.org/abs/1709.04875v4.

[24] LIU F T，TING K M，ZHOU Z H. Isolation Forest [C]//2008Eighth IEEE International Conference on Data Mining.Pisa：IEEE，2008：413-422.

[25] KHANSARI-ZADEH S M，BILLARD A. Learning Stable Nonlinear Dynamical Systems With Gaussian Mixture Models [J].

IEEE，2011,27（5）：943-957.

作者简介：

徐红飞（1995—），男，汉族，江苏宿迁人，硕士研究生在读，主要研究方向：大数据挖掘，智能运维等；

李婧（1980—），女，汉族，上海，副教授，硕士研究生导师，博士研究生，主要研究方向：计算机网络通信算法、智能电网、无线传感器网络等。