A hybrid deep learning model with 1DCNN-LSTM-Attention networks for short-term traffic flow prediction

Abstract With the rapid development of social economy, the traffic volume of urban roads has raised significantly, which has led to increasingly serious urban traffic congestion problems, and has caused much inconvenience to people’s travel. By focusing on the complexity and long-term dependence of traffic flow sequences on urban road, this paper considered the traffic flow data and weather conditions of the road section comprehensively, and proposed a short-term traffic flow prediction model based on the attention mechanism and the 1DCNN-LSTM network. The model combined the time expansion of the CNN and the advantages of the long-term memory of the LSTM. First, the model employs 1DCNN network to extract the spatial features in the road traffic flow data. Second, the output spatial features are considered as the input of LSTM neural network to extract the time features in road traffic flow data, and the long-term dependence characteristics of LSTM neural network are adopted to improve the prediction accuracy of traffic flow. Next, the spatio-temporal characteristics of road traffic flow were regarded as the input of the regression prediction layer, and the prediction results corresponding to the current input were calculated. Finally, the attention mechanism was introduced on the LSTM side to give enough attention to the key information, so that the model can focus on learning more important data features, and further improve the prediction performance. The experimental results showed that the prediction effect of the 1DCNN-LSTM-Attention model under the weather factor was better than that without considering the weather factor. At the same time, compared with traditional neural network models, the prediction effect of the proposed model revealed faster convergence speed and higher prediction accuracy. It can be found that for short-term traffic flow prediction on urban roads, the 1DCNN-LSTM network structure considering the attention mechanism provides superior features.

[1]  Yong Wang,et al.  Learning Traffic as Images: A Deep Convolutional Neural Network for Large-Scale Transportation Network Speed Prediction , 2017, Sensors.

[2]  Xinqiang Chen,et al.  Sensing Data Supported Traffic Flow Prediction via Denoising Schemes and ANN: A Comparison , 2020, IEEE Sensors Journal.

[3]  Hao Wang,et al.  Traffic Speed Prediction Under Non-Recurrent Congestion: Based on LSTM Method and BeiDou Navigation Satellite System Data , 2019, IEEE Intelligent Transportation Systems Magazine.

[4]  Mascha C. van der Voort,et al.  Combining kohonen maps with arima time series models to forecast traffic flow , 1996 .

[5]  Rita Cucchiara,et al.  Predicting Human Eye Fixations via an LSTM-Based Saliency Attentive Model , 2016, IEEE Transactions on Image Processing.

[6]  Jinde Cao,et al.  An interpretable model for short term traffic flow prediction , 2020, Math. Comput. Simul..

[7]  Di Feng,et al.  A New Method for Short-term Traffic Flow Prediction Based on Multi-segments Features , 2020, ICMLC.

[8]  Billy M. Williams,et al.  Comparison of parametric and nonparametric models for traffic flow forecasting , 2002 .

[9]  Fei-Fei Li,et al.  Deep visual-semantic alignments for generating image descriptions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[10]  Feng Lin,et al.  A Hybrid Deep Learning Model With Attention-Based Conv-LSTM Networks for Short-Term Traffic Flow Prediction , 2021, IEEE Transactions on Intelligent Transportation Systems.

[11]  Dewen Seng,et al.  A combined method for short-term traffic flow prediction based on recurrent neural network , 2020 .

[12]  Yingfeng Cai,et al.  Explanatory prediction of traffic congestion propagation mode: A self-attention based approach , 2021, Physica A: Statistical Mechanics and its Applications.

[13]  Chao Zhang,et al.  Multiple sources and multiple measures based traffic flow prediction using the chaos theory and support vector regression method , 2017 .

[14]  Sha Zhao,et al.  A Fused Method of Machine Learning and Dynamic Time Warping for Road Anomalies Detection , 2022, IEEE Transactions on Intelligent Transportation Systems.

[15]  Yee Whye Teh,et al.  A Fast Learning Algorithm for Deep Belief Nets , 2006, Neural Computation.

[16]  Jing Qin,et al.  A temporal-aware LSTM enhanced by loss-switch mechanism for traffic flow forecasting , 2020, Neurocomputing.

[17]  S. Chien,et al.  Deep Learning Framework for Freeway Speed Prediction in Adverse Weather , 2020 .

[18]  Yanni Peng,et al.  Short-term traffic volume prediction using GA-BP based on wavelet denoising and phase space reconstruction , 2020 .

[19]  Chuang Lin,et al.  An LSTM-Based Method with Attention Mechanism for Travel Time Prediction , 2019, Sensors.

[20]  Biao Jin,et al.  Short-Term Traffic Flow Intensity Prediction Based on CHS-LSTM , 2020, Arabian Journal for Science and Engineering.

[21]  Quoc V. Le,et al.  Sequence to Sequence Learning with Neural Networks , 2014, NIPS.

[22]  Huafeng Wu,et al.  Augmented Ship Tracking Under Occlusion Conditions From Maritime Surveillance Videos , 2020, IEEE Access.

[23]  Ya Wang,et al.  Short-term traffic flow prediction based on 1DCNN-LSTM neural network structure , 2020, Modern Physics Letters B.

[24]  Gary A. Davis,et al.  Using time-series designs to estimate changes in freeway level of service, despite missing data , 1984 .

[25]  A. R. Cook,et al.  ANALYSIS OF FREEWAY TRAFFIC TIME-SERIES DATA BY USING BOX-JENKINS TECHNIQUES , 1979 .

[26]  Feng Shu,et al.  Short-term traffic flow prediction based on spatio-temporal analysis and CNN deep learning , 2019, Transportmetrica A: Transport Science.

[27]  Huafeng Wu,et al.  Traffic flow prediction by an ensemble framework with data denoising and deep learning model , 2021 .

[28]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.