GPS-based citywide traffic congestion forecasting using CNN-RNN and C3D hybrid model

Traffic congestion prediction in citywide road networks is a challenging research field in metropolitan transportation operation and management. Recent advances in GPS technology offer great opportunities to improve upon the limitations on the availability and quality of traffic data. Motivated by the success of deep neural networks and considering the spatial dependencies and temporal evolutions of network traffic, we propose an innovative deep learning-based mapping to cube architecture for network-wide urban traffic forecasting. Experiments using real Taxi GPS vehicle trajectory data confirm the accuracy and effectiveness of the proposed approach combining 3-Dimensional Convolutional Networks (C3D) with Convolutional Neuron Networks (CNNs) and Recurrent Neuron Networks (RNNs), called CRC3D as a hybrid method integrating CNN-RNNs and C3Ds. We also compared a variety of recurrent neural network architectures. Results show that CRC3D succeeds in inheriting the advantages of C3D and CNN-RNN, and show its consistent and satisfactory results in urban complex system.

[1]  Zuduo Zheng,et al.  Traffic state estimation through compressed sensing and Markov random field , 2016 .

[2]  Ming Yang,et al.  3D Convolutional Neural Networks for Human Action Recognition , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[3]  Ming C. Lin,et al.  Citywide Estimation of Traffic Dynamics via Sparse GPS Traces , 2017, IEEE Intelligent Transportation Systems Magazine.

[4]  Alexander Mendiburu,et al.  A Review of Travel Time Estimation and Forecasting for Advanced Traveler Information Systems , 2012 .

[5]  Licia Capra,et al.  Urban Computing: Concepts, Methodologies, and Applications , 2014, TIST.

[6]  Azzedine Boukerche,et al.  A performance evaluation of an efficient traffic congestion detection protocol (ECODE) for intelligent transportation systems , 2015, Ad Hoc Networks.

[7]  Xiangjie Kong,et al.  Urban traffic congestion estimation and prediction based on floating car trajectory data , 2016, Future Gener. Comput. Syst..

[8]  Chin-Teng Lin,et al.  Jointly dampening traffic oscillations and improving energy consumption with electric, connected and automated vehicles: A reinforcement learning based approach , 2020 .

[9]  Zhengbing He,et al.  Mapping to Cells: A Simple Method to Extract Traffic Dynamics from Probe Vehicle Data , 2017, Comput. Aided Civ. Infrastructure Eng..

[10]  Yang Liu,et al.  Grid Mapping for Spatial Pattern Analyses of Recurrent Urban Traffic Congestion Based on Taxi GPS Sensing Data , 2017 .

[11]  Nikolaos Geroliminis,et al.  Experienced travel time prediction for congested freeways , 2013 .

[12]  Xiaobo Qu,et al.  Connected infrastructure location design under additive service utilities , 2019, Transportation Research Part B: Methodological.

[13]  Jiannong Cao,et al.  Exploring traffic congestion correlation from multiple data sources , 2017, Pervasive Mob. Comput..

[14]  Yunpeng Wang,et al.  Understanding commuting patterns using transit smart card data , 2017 .

[15]  Jian Wang,et al.  Congestion analysis of traffic networks with direction-dependant heterogeneity , 2013 .

[16]  Bin Ran,et al.  A hybrid deep learning based traffic flow prediction method and its understanding , 2018 .

[17]  Fei-Yue Wang,et al.  Traffic Flow Prediction With Big Data: A Deep Learning Approach , 2015, IEEE Transactions on Intelligent Transportation Systems.

[18]  Yunpeng Wang,et al.  Spatiotemporal Recurrent Convolutional Networks for Traffic Prediction in Transportation Networks , 2017, Sensors.

[19]  Yun Yang,et al.  Improved Deep Hybrid Networks for Urban Traffic Flow Prediction Using Trajectory Data , 2018, IEEE Access.

[20]  Francesco Marcelloni,et al.  Detection of traffic congestion and incidents from GPS trace analysis , 2017, Expert Syst. Appl..

[21]  Ronald J. Williams,et al.  A Learning Algorithm for Continually Running Fully Recurrent Neural Networks , 1989, Neural Computation.

[22]  Y. Nie.  How can the taxi industry survive the tide of ridesourcing? Evidence from Shenzhen, China , 2017 .

[23]  Eleni I. Vlahogianni,et al.  Short-term traffic forecasting: Where we are and where we’re going , 2014 .

[24]  Muhammad Tayyab Asif,et al.  Spatiotemporal Patterns in Large-Scale Traffic Speed Prediction , 2014, IEEE Transactions on Intelligent Transportation Systems.

[25]  Yang Yu,et al.  Development of an Efficient Driving Strategy for Connected and Automated Vehicles at Signalized Intersections: A Reinforcement Learning Approach , 2020, IEEE Transactions on Intelligent Transportation Systems.

[26]  Wenhao Huang,et al.  Deep Architecture for Traffic Flow Prediction: Deep Belief Networks With Multitask Learning , 2014, IEEE Transactions on Intelligent Transportation Systems.

[27]  Tianrui Li,et al.  Predicting Citywide Crowd Flows Using Deep Spatio-Temporal Residual Networks , 2017, Artif. Intell..

[28]  Yingfeng Cai,et al.  Traffic State Spatial-Temporal Characteristic Analysis and Short-Term Forecasting Based on Manifold Similarity , 2018, IEEE Access.

[29]  Yibing Wang,et al.  Driving Behaviour Style Study with a Hybrid Deep Learning Framework Based on GPS Data , 2018, Sustainability.

[30]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[31]  David Watling,et al.  A statistical method for estimating predictable differences between daily traffic flow profiles , 2017 .