GACNet: A Generative Adversarial Capsule Network for Regional Epitaxial Traffic Flow Prediction

With continuous urbanization,cities are undergoing a sharp expansion within the regional space.Due to the high cost,the prediction of regional traffic flow is more difficult to extend to entire urban areas.To address this challenging problem,we present a new deep learning architecture for regional epitaxial traffic flow prediction called GACNet,which predicts traffic flow of surrounding areas based on inflow and outflow information in central area.The method is data-driven,and the spatial relationship of traffic flow is characterized by dynamically transforming traffic information into images through a two-dimensional matrix.We introduce adversarial training to improve performance of prediction and enhance the robustness.The generator mainly consists of two parts:abstract traffic feature extraction in the central region and traffic prediction in the extended region.In particular,the feature extraction part captures nonlinear spatial dependence using gated convolution,and replaces the maximum pooling operation with dynamic routing,finally aggregates multidimensional information in capsule form.The effectiveness of the method is evaluated using traffic flow datasets for two real traffic networks:Beijing and New York.Experiments on highly challenging datasets show that our method performs well for this task.

Road traffic anomaly monitoring and warning based on DeepWalk algorithm

In the complex urban road traffic network,a sudden accident leads to rapid congestion in the nearby traffic region,which even makes the local traffic network capacity quickly reduce.Therefore,an efficient monitoring system for abnormal conditions of the urban road network plays a crucial role in the tolerance of the urban road network.The traditional traffic monitoring system not only costs a lot in construction and maintenance,but also may not cover the road network comprehensively,which could not meet the basic needs of traffic management.Only a more comprehensive and intelligent monitoring method is able to identify traffic anomalies more effectively and quickly,so that it can provide more effective support for traffic management decisions.The extensive use of positioning equipment made us able to obtain accurate trajectory data.This paper presents a traffic anomaly monitoring and prediction method based on vehicle trajectory data.This model uses deep learning to detect abnormal trajectory on the traffic road network.The method effectively analyses the abnormal source and potential anomaly to judge the abnormal region,which provides an important reference for the traffic department to take effective traffic control measures.Finally,the paper uses Internet vehicle trajectory data from Chengdu(China)to test and obtains an accurate result.