Lv Z, Zhang S, Xiu W (2021) Solving the security problem of intelligent transportation system with deep learning. Zhou J, Dai H-N, Wang H, Wang T (2021) Wide-attention and deep-composite model for traffic flow prediction in transportation cyber-physical systems. Lu Y, Ding H, Ji S, Sze N, He Z (2021) Dual attentive graph neural network for metro passenger flow prediction. Li L, Qin L, Qu X, Zhang J, Wang Y, Ran B (2019) Day-ahead traffic flow forecasting based on a deep belief network optimized by the multi-objective particle swarm algorithm. Paule JDG, Sun Y, Moshfeghi Y (2019) On fine-grained geolocalisation of tweets and real-time traffic incident detection. Lu Y, Wang W, Hu X, Xu P, Zhou S, Cai M (2022) Vehicle trajectory prediction in connected environments via heterogeneous context-aware graph convolutional networks. Lin Y, Li L, Jing H, Ran B, Sun D (2020) Automated traffic incident detection with a smaller dataset based on generative adversarial networks. Zhao C, Chang X, Xie T, Fujita H, Wu J (2022) Unsupervised anomaly detection based method of risk evaluation for road traffic accident. Iqbal Z, Khan MI (2018) Automatic incident detection in smart city using multiple traffic flow parameters via v2x communication. Kumar N, Acharya D, Lohani D (2020) An iot-based vehicle accident detection and classification system using sensor fusion. IEEE Trans Intell Transp Syst 21(8):3152–3168ĭing H, Sze N, Li H, Guo Y (2020) Roles of infrastructure and land use in bicycle crash exposure and frequency: a case study using greater london bike sharing data. Veres M, Moussa M (2020) Deep learning for intelligent transportation systems: a survey of emerging trends. Furthermore, the proposed paradigm is more efficient in respondence compared with traditional centralized computing, realizing 8x processing speed for the same detection task. The experimental results revealed the proposed model outperforms state-of-the-art models in terms of detection accuracy, achieving 26.3% improvement over the best-performing baseline. To testify the proposed paradigm and model, real-world datasets were applied. Finally, the above-concerned contexts are integrated and fed into a model decoder to measure the likelihood of incidents. Similarly, the second module is deployed in a central server to capture the spatio-temporal global contexts from historical traffic flows. The dynamic traffic flows will be projected into a spatio-temporal digraph, and in turn addressed by a graph convolutional network for extraction of the deep-seated features. The first module, deployed in an edge server, is designed to extract the local contexts from the real-time traffic flow. To be specific, the model encoder includes two components. In particular, a Spatio-Temporal Variational Digraph Auto-Encoder model is developed to distinguish the incidents in dynamic traffic flows. To fill the above gaps, this study proposes a novel automatic incident detection paradigm using an edge-cloud collaboration mechanism. Also, issues related to network delays and privacy leakage of centralized computing are prevalent. Although the emerging information technologies and artificial intelligence approaches are paving the way for high-precision incident detection, existing incident detection methods fail to handle the unbalanced incident data with excessive zero observations. Automatic incident detection not only plays an important role in traffic safety management, but also contributes to the operation of intelligent transportation systems.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |