Attention Mechanism With Spatial-Temporal Joint Model for Traffic Flow Speed Prediction

2021 ◽  
pp. 1-10
Author(s):  
Hexuan Hu ◽  
Zhenzhou Lin ◽  
Qiang Hu ◽  
Ye Zhang
Keyword(s):  
Traffic Flow ◽  
Joint Model ◽  
Flow Speed ◽  
Attention Mechanism ◽  
Speed Prediction

scholarly journals Traffic flow speed prediction on transportation graph with convolutional neural networks

2018 ◽  
Vol 10 (3) ◽  
pp. 359-367 ◽  
Author(s):  
Nikolay G. Prokoptsev ◽  
Andrey Evgen'evich Alekseenko ◽  
Yaroslav Aleksandrovich Kholodov
Keyword(s):  
Neural Networks ◽  
Traffic Flow ◽  
Convolutional Neural Networks ◽  
Flow Speed ◽  
Speed Prediction

scholarly journals Highway Traffic Speed Prediction in Rainy Environment Based on APSO-GRU

2021 ◽  
Vol 2021 ◽  
pp. 1-11
Author(s):  
Dongqing Han ◽  
Xin Yang ◽  
Guang Li ◽  
Shuangyin Wang ◽  
Zhen Wang ◽  
...  
Keyword(s):  
Prediction Model ◽  
Traffic Flow ◽  
Prediction Accuracy ◽  
Flow Speed ◽  
Highway Traffic ◽  
Speed Prediction ◽  
Potential Factors ◽  
Adaptive Nonlinear Inertia Weight ◽  
The Impact ◽  
Continuous Rainfall

In order to accurately analyse the impact of the rainy environment on the characteristics of highway traffic flow, a short-term traffic flow speed prediction model based on gate recurrent unit (GRU) and adaptive nonlinear inertia weight particle swarm optimization (APSO) was proposed. Firstly, the rainfall and highway traffic flow data were cleaned, and then they are matched according to the spatiotemporal relationship. Secondly, through the method of multivariate analysis of variance, the significance of the impact of potential factors on traffic flow speed was explored. Then, a GRU-based traffic flow speed prediction model in rainy environment is proposed, and the actual road sections under different rainfall scenarios were verified. After that, in view of the problem that the prediction accuracy of the GRU model was low in the continuous rainfall scenario, the APSO algorithm was used to optimize the parameters of the GRU network, and the APSO-GRU prediction model was constructed and verifications under the same road section and rain scene were carried out. The results show that the APSO-GRU model has significantly improved prediction stability than the GRU model and can better extract rainfall features during continuous rainfall, with an average prediction accuracy rate of 96.74%.

scholarly journals Speed Models for Motorcycle Riders for Two-lane Rural Roads

2021 ◽  
Vol 17 ◽  
pp. 595-603
Author(s):  
Panagiotis Lemonakis ◽  
George Botzoris ◽  
Athanasios Galanis ◽  
Nikolaos Eliou
Keyword(s):  
Prediction Models ◽  
Flow Speed ◽  
Operating Speed ◽  
Rural Roads ◽  
The Road ◽  
Horizontal Curves ◽  
Road Geometry ◽  
Speed Prediction ◽  
The Subject ◽  
On The Road

The development of operating speed models has been the subject of numerous research studies in the past. Most of them present models that aim to predict free-flow speed in conjunction with the road geometry at the curved road sections considering various geometric parameters e.g., radius, length, preceding tangent, deflection angle. The developed models seldomly take into account the operating speed profiles of motorcycle riders and hence no significant efforts have been put so far to associate the geometric characteristics of a road segment with the speed behavior of motorcycle riders. The dominance of 4-wheel vehicles on the road network led the researchers to focus explicitly on the development of speed prediction models for passenger cars, vans, pickups, and trucks. However, although the motorcycle fleet represents only a small proportion of the total traffic volume motorcycle riders are over-represented in traffic accidents especially those that occur on horizontal curves. Since operating speed has been thoroughly documented as the most significant precipitating factor of vehicular accidents, the study of motorcycle rider's speed behavior approaching horizontal curves is of paramount importance. The subject of the present paper is the development of speed prediction models for motorcycle riders traveling on two-lane rural roads. The model was the result of the execution of field measurements under naturalistic conditions with the use of an instrumented motorcycle conducted by experienced motorcycle riders under different lighting conditions. The implemented methodology to determine the most efficient model evaluates a series of road geometry parameters through a comprehensive literature review excluding those with an insignificant impact to the magnitude of the operating speeds in order to establish simple and handy models.

An attention mechanism-based method for predicting traffic flow by GCN

2021 ◽  
Author(s):  
Wenyu Wu ◽  
Xiumei Fan ◽  
Yaqiong Xue ◽  
Yusheng Huang
Keyword(s):  
Traffic Flow ◽  
Attention Mechanism

Impact of Rainfall Condition on Traffic Flow and Speed: A Case Study in Johor and Terengganu

2014 ◽  
Vol 70 (4) ◽  
Author(s):  
Nordiana Mashros ◽  
Johnnie Ben- Edigbe ◽  
Sitti Asmah Hassan ◽  
Norhidayah Abdul Hassan ◽  
Nor Zurairahetty Mohd Yunus
Keyword(s):  
Traffic Flow ◽  
Monsoon Season ◽  
Flow Speed ◽  
Free Flow ◽  
Road User ◽  
Traffic Data ◽  
Average Volume ◽  
Rainfall Condition ◽  
Free Flow Speed ◽  
The Impact

This paper explores the impact of various rainfall conditions on traffic flow and speed at selected location in Terengganu and Johor using data collected on two-lane highway. The study aims to quantify the effect of rainfall on average volume, capacity, mean speed, free-flow speed and speed at capacity. This study is important to come out with recommendation for managing traffic under rainfall condition. Traffic data were generated using automatic traffic counters for about three months during the monsoon season. Rainfall data were obtained from nearest surface rain gauge station. Detailed vehicular information logged by the counters were retrieved and processed into dry and various rainfall conditions. Only daylight traffic data have been used in this paper. The effect of rain on traffic flow and speed for each condition were then analysed separately and compared. The results indicated that average volumes shows no pronounce effect under rainfall condition compared to those under dry condition. Other parameters, however, show a decrease under rainfall condition. Capacity dropped by 2-32%, mean speed, free-flow speed and speed at capacity reduced by 3-14%, 1-14% and 3-17%, respectively. The paper recommends that findings from the study can be incorporated with variable message sign, local radio and television, and variable speed limit sign which should help traffic management to provide safer and more proactive driving experiences to the road user. The paper concluded that rainfall irrespective of their intensities have impact on traffic flow and speed except average volume.

scholarly journals Two-Stream Multi-Channel Convolutional Neural Network for Multi-Lane Traffic Speed Prediction Considering Traffic Volume Impact

2020 ◽  
Vol 2674 (4) ◽  
pp. 459-470 ◽  
Author(s):  
Ruimin Ke ◽  
Wan Li ◽  
Zhiyong Cui ◽  
Yinhai Wang
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Traffic Flow ◽  
Data Science ◽  
Prediction Models ◽  
Rapid Development ◽  
Traffic Volume ◽  
Speed Prediction ◽  
Traffic Speed ◽  
The Impact

Traffic speed prediction is a critically important component of intelligent transportation systems. Recently, with the rapid development of deep learning and transportation data science, a growing body of new traffic speed prediction models have been designed that achieved high accuracy and large-scale prediction. However, existing studies have two major limitations. First, they predict aggregated traffic speed rather than lane-level traffic speed; second, most studies ignore the impact of other traffic flow parameters in speed prediction. To address these issues, the authors propose a two-stream multi-channel convolutional neural network (TM-CNN) model for multi-lane traffic speed prediction considering traffic volume impact. In this model, the authors first introduce a new data conversion method that converts raw traffic speed data and volume data into spatial–temporal multi-channel matrices. Then the authors carefully design a two-stream deep neural network to effectively learn the features and correlations between individual lanes, in the spatial–temporal dimensions, and between speed and volume. Accordingly, a new loss function that considers the volume impact in speed prediction is developed. A case study using 1-year data validates the TM-CNN model and demonstrates its superiority. This paper contributes to two research areas: (1) traffic speed prediction, and (2) multi-lane traffic flow study.

scholarly journals The impact of heavy vehicle’s composition to traffic performance of Jakarta Intra Urban Toll Road (JIUT) in macroscopic level

2019 ◽  
Vol 276 ◽  
pp. 03018
Author(s):  
Nahry Yusuf ◽  
Ismi Dilianda Wulandari
Keyword(s):  
Traffic Flow ◽  
Exponential Model ◽  
Flow Speed ◽  
Heavy Vehicles ◽  
Flow Models ◽  
Toll Road ◽  
Traffic Performance ◽  
Traffic Flow Models ◽  
The One ◽  
The Impact

Freight vehicle access restriction policy in 2011 has had an impact on the performance of Jakarta Intra Urban Toll way (JIUT) system. The statutory segment (Cawang-Tomang) of this toll road system seems to have better performance, but not for the advisory segment (Cawang -Ancol). Basically, heavy vehicles (HV) shift their routes to the advisory segment to avoid the statutory segment at which they are prohibited to access from 05.00 a.m. to 10.00 p.m.. This study aims to investigate the impact of the HV composition on the traffic performance of the advisory segment of JIUT. Data were obtained from 48 hours of traffic recording at a part of Cawang-Ancol segment. It was found that the Underwood Model (exponential model) can represent the relationship between the three main parameters of traffic flow on the advisory segment, i.e. volume, speed, and density. Based on the developed traffic flow models which are classified on the HV composition, it is shown that the free flow speed (uf) for HV composition < 6% (i.e. 144.91 km/h) is higher 35.41% than the one of HV > 6% (i.e. 107.02 km/h). The actual road capacity (qm) in HV composition < 6% (i.e. 4442 pcu/hour) also higher 12.83% than the one of HV > 6% (i.e. 3937 pcu/hour). The results will benefit to the transport authority to justify the truck access restriction implementation.

Sign in / Sign up

Export Citation Format

Share Document