Research on the Prediction of Temporal and Spatial Characteristics of Expressway Traffic Speed Based on Attention-CNN-BiLSTM

At present, prediction values of accurate traffic data by highway traffic control departments are not accurate enough. To provide better traffic guidance for pedestrians, new methods must be used to estimate traffic speed data with less error. This paper proposes an attention-convolution-bidirection...

Full description

Saved in:

Bibliographic Details
Main Authors:	Liu, Yongle, Gu, Yuanli
Format:	Report
Language:	eng
Subjects:	bidirectional long and short-term memory network convolutional neural network expressway spatiotemporal characteristics traffic flow prediction
Online Access:	Request full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	At present, prediction values of accurate traffic data by highway traffic control departments are not accurate enough. To provide better traffic guidance for pedestrians, new methods must be used to estimate traffic speed data with less error. This paper proposes an attention-convolution-bidirectional long short-term memory model that considers both temporal and spatial factors, combining a convolutional neural network with spatial local feature extraction capabilities and a bidirectional long short-term memory that can simultaneously consider long-term information in the forward and backward directions. Then add a layer of attention mechanism at the top to make the network architecture pay more attention to the temporal and spatial factors that contribute more weight to the final prediction, we use it to predict traffic speed that can better reflect the fluctuations of time and space. The paper uses some simple benchmark methods as comparison models and uses three evaluation indicators to train and test on the California highway data set. The results show that the prediction results obtained by Attention-CNN-BiLSTM are more in line with the actual traffic speed trend.
ISSN:	0148-7191 2688-3627