Time series decomposition model for traffic flow forecasting in urban midblock sections

Omkar, G.; Kumar, S. Vasantha

doi:10.1109/smarttechcon.2017.8358465

Cited by 11 publications

(5 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Shuvo et al [8] constructed the ARIMA, ETS, SNAIVE, and PROPHET time-series models to predict traffic volumes in congested areas of Bangladesh. To predict traffic volumes for data that lack a sufficient number of locations to apply the ARIMA model, which is frequently used for traffic volume predictions, Omkar and Kumar [9] proposed a method for decomposing and estimating fluctuating components using multiplicative decomposition. These studies emphasize the importance of considering temporal similarities (periodicity) while estimating the traffic volume.…”

Section: ) Models For Temporal Similarities In Traffic Fluctuationsmentioning

confidence: 99%

Development of a Method for Estimating Traffic Volume Fluctuations That Considers Calendar Information and Road Network Geometry

Kobayashi,

Tanishita

2024

IEEE Access

View full text Add to dashboard Cite

This study aims to develop a method for estimating the traffic volume at locations and time periods where past data are unavailable. To achieve this, we constructed a model based on seven years of traffic volume observations on 22 main roads in Tokyo. The estimation method comprises two components: a traffic volume fluctuation pattern model that explains pre-clustered patterns and an annual average daily traffic model. Through our analysis, we made three key observations. First, the distance to the city center is a significant explanatory factor for monthly fluctuations, the month number for weekly fluctuations, the dayto-night population ratio for daily fluctuations, and the city center direction angle for hourly fluctuations. These calendar and road geometry variables account for 70-90% of the traffic volume fluctuation. Second, when estimating traffic volume for specific time periods using the traffic volume fluctuation pattern model, we explained approximately 60% of routes where no traffic volume observations were conducted and approximately 80% of routes where observations were made infrequently. Finally, the optimal number of clusters for the traffic volume fluctuation pattern, which maximized the coefficient of determination of the traffic volume model, was 8 for monthly fluctuations, 4 for weekly fluctuations, 6 for daily fluctuations, and 11 for hourly fluctuations. These findings made it possible to estimate traffic volumes on routes where traffic volume observations are not conducted and to interpolate traffic volumes for any given month or date using the results of periodic surveys conducted every few years.

show abstract

Section: ) Models For Temporal Similarities In Traffic Fluctuationsmentioning

confidence: 99%

Development of a Method for Estimating Traffic Volume Fluctuations That Considers Calendar Information and Road Network Geometry

Kobayashi,

Tanishita

2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Statistical models include the historical trend models [3], nonparametric regression models [4][5][6], and time-series models [6][7][8][9][10][11].…”

Section: Literature Reviewmentioning

confidence: 99%

Short-Term Intersection Traffic Flow Forecasting

Lan

et al. 2020

Sustainability

View full text Add to dashboard Cite

The intersection is a bottleneck in an urban roadway network. As traffic demand increases, there is a growing congestion problem at urban intersections. Short-term traffic flow forecasting is crucial for advanced trip planning and traffic management. However, there are only a handful of existing models for forecasting intersection traffic flow. In addition, previous short-term traffic flow forecasting models usually were for predicting roadway conditions in a very short period, such as one minute or five minutes, which is often too late given that a driver may well be approaching the bottleneck already. Being able to accurately predict traffic congestions in about half-hour advance is very critical for advanced trip planning and traffic management. To fill this gap, this research develops a two-layer stacking model for intersection short-term traffic flow forecasting by integrating the K-nearest neighbor (KNN) and Elman Neural Network modeling methods. It was developed using the 24-h cycle by cycle traffic data collected at a signalized intersection in Jinan, China. The developed model is evaluated by applying it to the same intersection for forecasting the short-term traffic conditions in a different set of days. The prediction performance of this model was compared with four other models developed using some existing non-parametric modeling and machine learning methods, including clustering, backpropagation (BP) neural network, KNN, and Elman Neural Network. The results of this study indicate that the proposed model outperforms other existing models in terms of its prediction accuracy.

show abstract

“…Based on these advances, it makes sense to build a system that predicts traffic conditions and driver behaviors and provides effective information to help drivers reach their destination and park vehicles faster, safer, and more comfortable. 8,9 Vast amounts of data can be generated from almost anywhere, and our universe has become data driven. Without the right data decisions, the prevention and mitigation of risk and systematic assessment will not achieve the desired results.…”

Section: Introductionmentioning

confidence: 99%

“…Driver behavior data can be obtained using existing or innovative machine learning technologies. Based on these advances, it makes sense to build a system that predicts traffic conditions and driver behaviors and provides effective information to help drivers reach their destination and park vehicles faster, safer, and more comfortable 8,9 …”

Section: Introductionmentioning

confidence: 99%

New method of traffic flow forecasting based on quantum particle swarm optimization strategy for intelligent transportation system

Zhang

Wang

Fan

et al. 2020

Int J Communication

View full text Add to dashboard Cite

SummaryTraffic flow forecasting is one of the essential means to realize smart cities and smart transportation. The accurate and effective prediction will provide an important basis for decision‐making in smart transportation systems. This paper proposes a new method of traffic flow forecasting based on quantum particle swarm optimization (QPSO) strategy for intelligent transportation system (ITS). We establish a corresponding model based on the characteristics of the traffic flow data. The genetic simulated annealing algorithm is applied to the quantum particle swarm algorithm to obtain the optimized initial cluster center, and is applied to the parameter optimization of the radial basis neural network prediction model. The function approximation of radial basis neural network is used to obtain the required data. In addition, in order to compare the performance of the algorithms, a comparison study with other related algorithms such as QPSO radial basis function (QPSO‐RBF) is also performed. Simulation results show that compared with other algorithms, the proposed algorithm can reduce prediction errors and get better and more stable prediction results.

show abstract

Time series decomposition model for traffic flow forecasting in urban midblock sections

Cited by 11 publications

References 12 publications

Development of a Method for Estimating Traffic Volume Fluctuations That Considers Calendar Information and Road Network Geometry

Development of a Method for Estimating Traffic Volume Fluctuations That Considers Calendar Information and Road Network Geometry

Short-Term Intersection Traffic Flow Forecasting

New method of traffic flow forecasting based on quantum particle swarm optimization strategy for intelligent transportation system

Contact Info

Product

Resources

About