Traffic Incident Detection Based on Dynamic Graph Embedding in Vehicular Edge Computing

With a large of time series dataset from the Internet of Things in Ambient Intelligence-enabled smart environments, many supervised learning-based anomaly detection methods have been investigated but ignored the correlation among the time series. To address this issue, we present a new idea for anomaly detection based on dynamic graph embedding, in which the dynamic graph comprises the multiple time series and their correlation in each time interval. We propose an entropy for measuring a graph’s information injunction with a correlation matrix to define similarity between graphs. A dynamic graph embedding model based on the graph similarity is proposed to cluster the graphs for anomaly detection. We implement the proposed model in vehicular edge computing for traffic incident detection. The experiments are carried out using traffic data produced by the Simulation of Urban Mobility framework. The experimental findings reveal that the proposed method achieves better results than the baselines by 14.5% and 18.1% on average with respect to F1-score and accuracy, respectively.

[1]  Krishna Jagannathan,et al.  A Framework for End-to-End Deep Learning-Based Anomaly Detection in Transportation Networks , 2019, Transportation Research Interdisciplinary Perspectives.

[2]  Vicente Julián,et al.  Advances and trends for the development of ambient‐assisted living platforms , 2017, Expert Syst. J. Knowl. Eng..

[3]  John Murphy,et al.  A SUMO based evaluation of road incidents' impact on traffic congestion level in smart cities , 2014, 39th Annual IEEE Conference on Local Computer Networks Workshops.

[4]  Feng Xia,et al.  Deep Reinforcement Learning for Vehicular Edge Computing , 2019, ACM Trans. Intell. Syst. Technol..

[5]  Sunghwan Moon,et al.  ReLU Network with Bounded Width Is a Universal Approximator in View of an Approximate Identity , 2021, Applied Sciences.

[6]  Yan Liu,et al.  DynGEM: Deep Embedding Method for Dynamic Graphs , 2018, ArXiv.

[7]  C.-C. Jay Kuo,et al.  Graph representation learning: a survey , 2019, APSIPA Transactions on Signal and Information Processing.

[8]  U. Rajendra Acharya,et al.  Classification of myocardial infarction with multi-lead ECG signals and deep CNN , 2019, Pattern Recognit. Lett..

[9]  Fei-Fei Li,et al.  Illuminating the dark spaces of healthcare with ambient intelligence , 2020, Nature.

[10]  Tamás F. Móri,et al.  On relationships between the Pearson and the distance correlation coefficients , 2021 .

[11]  Jason J. Jung,et al.  Dynamic graph embedding for outlier detection on multiple meteorological time series , 2021, PloS one.

[12]  Jason J. Jung,et al.  Swarm intelligence-based green optimization framework for sustainable transportation , 2021, Sustainable Cities and Society.

[13]  Zhong Fan,et al.  Anomaly Detection for IoT Time-Series Data: A Survey , 2020, IEEE Internet of Things Journal.

[14]  Shangguang Wang,et al.  A Survey on Vehicular Edge Computing: Architecture, Applications, Technical Issues, and Future Directions , 2019, Wirel. Commun. Mob. Comput..

[15]  P. Ziehl,et al.  Implementation of Information Entropy, b-Value, and Regression Analyses for Temporal Evaluation of Acoustic Emission Data Recorded during ASR Cracking , 2021 .

[16]  Jason J. Jung,et al.  Internet of agents framework for connected vehicles: A case study on distributed traffic control system , 2017, J. Parallel Distributed Comput..

[17]  Palash Goyal,et al.  dyngraph2vec: Capturing Network Dynamics using Dynamic Graph Representation Learning , 2018, Knowl. Based Syst..

[18]  Diane J. Cook,et al.  Author's Personal Copy Pervasive and Mobile Computing Ambient Intelligence: Technologies, Applications, and Opportunities , 2022 .

[19]  Tomoaki Ohtsuki,et al.  A Smart City Based on Ambient Intelligence , 2017, IEICE Trans. Commun..

[20]  Lei Liu,et al.  Vehicular Edge Computing and Networking: A Survey , 2019, Mobile Networks and Applications.

[21]  Jaouad Boumhidi,et al.  Fuzzy deep learning based urban traffic incident detection , 2017, Cognitive Systems Research.

[22]  Richard Millham,et al.  Bio-Inspired Approaches for Smart Energy Management: State of the Art and Challenges , 2020, Sustainability.

[23]  Jason J. Jung,et al.  Multiple ACO-based method for solving dynamic MSMD traffic routing problem in connected vehicles , 2020, Neural Computing and Applications.

[24]  Simon Harper,et al.  A Survey of Ambient Intelligence , 2021, ACM Comput. Surv..

[25]  Maytham Safar,et al.  Ambient Technology in Vehicles: The Benefits and Risks , 2016, ANT/SEIT.

[26]  Xiang Li,et al.  S-GCN-GRU-NN: A novel hybrid model by combining a Spatiotemporal Graph Convolutional Network and a Gated Recurrent Units Neural Network for short-term traffic speed forecasting , 2021, Journal of Data, Information and Management.

[27]  Bin Ran,et al.  Automated traffic incident detection with a smaller dataset based on generative adversarial networks. , 2020, Accident; analysis and prevention.

[28]  Antonio Iera,et al.  The Internet of Things: A survey , 2010, Comput. Networks.

[29]  Nita Yodo,et al.  A Survey of Road Traffic Congestion Measures towards a Sustainable and Resilient Transportation System , 2020, Sustainability.

[30]  Myounggyu Won Intelligent Traffic Monitoring Systems for Vehicle Classification: A Survey , 2020, IEEE Access.

[31]  Wenwu Zhu,et al.  Structural Deep Network Embedding , 2016, KDD.

[32]  Yun-Pang Flötteröd,et al.  Microscopic Traffic Simulation using SUMO , 2018, 2018 21st International Conference on Intelligent Transportation Systems (ITSC).

[33]  Jing Gao,et al.  A deep learning approach for detecting traffic accidents from social media data , 2018, ArXiv.

[34]  Yunlu Jiang,et al.  Outlier detection and robust variable selection via the penalized weighted LAD-LASSO method , 2020, Journal of applied statistics.

[35]  Sherali Zeadally,et al.  Integration challenges of intelligent transportation systems with connected vehicle, cloud computing, and internet of things technologies , 2015, IEEE Wireless Communications.