Accurate and timely traffic flow information is important for the successful deployment of intelligent transportation systems. Over the last few years, traffic data have been exploding, and we have truly entered the era of big data for transportation. Existing traffic flow prediction methods mainly use shallow traffic prediction models and are still unsatisfying for many real-world applications. This situation inspires us to rethink the traffic flow prediction problem based on deep architecture models with big traffic data. In this paper, a novel deep-learning-based traffic flow prediction method is proposed, which considers the spatial and temporal correlations inherently. A stacked autoencoder model is used to learn generic traffic flow features, and it is trained in a greedy layerwise fashion. To the best of our knowledge, this is the first time that a deep architecture model is applied using autoencoders as building blocks to represent traffic flow features for prediction. Moreover, experiments demonstrate that the proposed method for traffic flow prediction has superior performance.

Traffic Flow Prediction With Big Data: A Deep Learning Approach

Short-term traffic forecast is one of the essential issues in intelligent transportation system. Accurate forecast result enables commuters make appropriate travel modes, travel routes, and departure time, which is meaningful in traffic management. To promote the forecast accuracy, a feasible way is to develop a more effective approach for traffic data analysis. The availability of abundant traffic data and computation power emerge in recent years, which motivates us to improve the accuracy of short-term traffic forecast via deep learning approaches. A novel traffic forecast model based on long short-term memory (LSTM) network is proposed. Different from conventional forecast models, the proposed LSTM network considers temporal-spatial correlation in traffic system via a two-dimensional network which is composed of many memory units. A comparison with other representative forecast models validates that the proposed LSTM network can achieve a better performance.

https://ietresearch.onlinelibrary.wiley.com/doi/epdf/10.1049/iet-its.2016.0208

LSTM network: a deep learning approach for short-term traffic forecast

Accurate and real-time traffic forecasting plays an important role in the intelligent traffic system and is of great significance for urban traffic planning, traffic management, and traffic control. However, traffic forecasting has always been considered an “open” scientific issue, owing to the constraints of urban road network topological structure and the law of dynamic change with time. To capture the spatial and temporal dependences simultaneously, we propose a novel neural network-based traffic forecasting method, the temporal graph convolutional network (T-GCN) model, which is combined with the graph convolutional network (GCN) and the gated recurrent unit (GRU). Specifically, the GCN is used to learn complex topological structures for capturing spatial dependence and the gated recurrent unit is used to learn dynamic changes of traffic data for capturing temporal dependence. Then, the T-GCN model is employed to traffic forecasting based on the urban road network. Experiments demonstrate that our T-GCN model can obtain the spatio-temporal correlation from traffic data and the predictions outperform state-of-art baselines on real-world traffic datasets. Our tensorflow implementation of the T-GCN is available at https://www.github.com/lehaifeng/T-GCN .

T-GCN: A Temporal Graph Convolutional Network for Traffic Prediction

Accurate and real-time traffic flow prediction is important in Intelligent Transportation System (ITS), especially for traffic control. Existing models such as ARMA, ARIMA are mainly linear models and cannot describe the stochastic and nonlinear nature of traffic flow. In recent years, deep-learning-based methods have been applied as novel alternatives for traffic flow prediction. However, which kind of deep neural networks is the most appropriate model for traffic flow prediction remains unsolved. In this paper, we use Long Short Term Memory (LSTM) and Gated Recurrent Units (GRU) neural network (NN) methods to predict short-term traffic flow, and experiments demonstrate that Recurrent Neural Network (RNN) based deep learning methods such as LSTM and GRU perform better than auto regressive integrated moving average (ARIMA) model. To the best of our knowledge, this is the first time that GRU is applied to traffic flow prediction.

Using LSTM and GRU neural network methods for traffic flow prediction

A new approach based on Bayesian networks for traffic flow forecasting is proposed. In this paper, traffic flows among adjacent road links in a transportation network are modeled as a Bayesian network. The joint probability distribution between the cause nodes (data utilized for forecasting) and the effect node (data to be forecasted) in a constructed Bayesian network is described as a Gaussian mixture model (GMM) whose parameters are estimated via the competitive expectation maximization (CEM) algorithm. Finally, traffic flow forecasting is performed under the criterion of minimum mean square error (mmse). The approach departs from many existing traffic flow forecasting models in that it explicitly includes information from adjacent road links to analyze the trends of the current link statistically. Furthermore, it also encompasses the issue of traffic flow forecasting when incomplete data exist. Comprehensive experiments on urban vehicular traffic flow data of Beijing and comparisons with several other methods show that the Bayesian network is a very promising and effective approach for traffic flow modeling and forecasting, both for complete data and incomplete data

A bayesian network approach to traffic flow forecasting

Traffic volume is one of the fundamental types of data that have been used for the traffic control and planning process. Forecasting needs and efforts for various applications will be increased with the deployment of advanced traffic management systems. With the importance of the short-term traffic forecasting task, numerous techniques have been utilized to improve its accuracy. The use of the subset autoregressive integrated moving average (ARIMA) model for short-term traffic volume forecasting is investigated. A typical time-series modeling procedure was employed for this study. Model identification was carried out with Akaike's information criterion. The conditional maximum likelihood method was used for the parameter estimation process. Two white noise tests were applied for model verification. From the analysis results, four time-series models in different categories were identified and used for the one-step-ahead forecasting task. The performance of each model was evaluated using two statistical error estimates. Results showed that all time-series models performed well with reasonable accuracy. However, it was observed that the subset ARIMA model gave more stable and accurate results than other time-series models, especially a full ARIMA model. It is believed that the use of a subset ARIMA model could increase the accuracy of the short-term forecasting task within time-series models.

Application of Subset Autoregressive Integrated Moving Average Model for Short-Term Freeway Traffic Volume Forecasting

This report describes the development of recommended revisions to the stopping sight distance (SSD) design policy that appears in portions of Chapters II and III of the 1994 American Association of State Highway and Transportation Officials (AASHTO) publication, "A Policy on Geometric Design of Highways and Streets" (referred to as the Green Book). It also proposes modifications to other sections of the Green Book that currently reference stopping sight distance. The contents of this report are, therefore, of immediate interest to highway designers; highway operations, capacity, and traffic control personnel; and others concerned with highway safety. The report's conclusions are derived from field observations of driver performance, driver visual capacity, driver eye heights, and vehicle heights, as well as safety and operational studies.

Determination of stopping sight distances

Prediction and estimation of speeds on two-lane rural highways are of enormous significance to planners and designers. Estimation of speeds on curves may be easier than prediction of speeds on tangent sections because of the strong correlation of speeds with a few defined and limiting variables, such as curvature, superelevation, and the side-friction coefficients between road surface and tires. On tangent sections, however, the speed of vehicles is dependent on a wide array of roadway characteristics, such as the length of the tangent section, the radius of the curve before and after the section, cross-section elements, vertical alignment, general terrain, and available sight distance. Few studies have dealt with this issue because a considerable database is necessary to identify any significant trends and substantial modeling effort is required. Research analyzed the variability of the operating speeds on 162 tangent sections of two-lane rural highways, and models were developed for prediction of operat...

Predicting Operating Speeds on Tangent Sections of Two-Lane Rural Highways:

Transit service is being viewed increasingly as a reliable travel demand measure. Various means of attracting the motorist to move from the car to transit are being attempted all over the country. It has been found that delay at intersections is the primary cause of bus delay. Reducing delay at intersections can reduce overall trip time, improve schedule reliability, and reduce overall congestion. Providing priority for buses at signalized intersections is one way to reduce delay at intersections. Numerous organizations have developed priority strategies to do the same. But most of them cannot be operational for a long time for various reasons. Improved technology has prompted traffic engineers to renew efforts to develop newer bus priority strategies. This paper discusses the development of a model to evaluate the impacts of implementing a priority strategy at signalized intersections. The model uses the delay equation for signalized intersections in the 1985 Highway Capacity Manual. A priority strategy was developed and implemented in the field. Data were collected, and delay in the field was measured. The model seems to be predicting delay reasonably accurately. In some cases, however, the model was overestimating delay. The model can be a useful tool to traffic engineers to evaluate the impacts and the feasibility of implementing a priority strategy.

Model to evaluate the impacts of bus priority on signalized intersections

One of the most important requirements in highway design is the provision of adequate stopping sight distance at every point along the roadway. At a minimum, this sight distance should be long enough to enable a vehicle traveling at or near the design speed to stop before reaching a stationary object in its path. Stopping sight distance is the sum of two components—brake reaction distance and braking distance. Brake reaction distance is based on the vehicle's speed and the driver's perception-brake reaction time (PBRT). Four separate, but coordinated, driver braking performance studies measured driver perception—brake response to several different stopping sight distance situations. The results from the driver braking performance studies suggest that the mean perception-brake response time to an unexpected object scenario under controlled and open road conditions is about 1.1 s. The 95th percentile perception-brake response times for these same conditions was 2.0 s. The findings from these studies are con...

Daniel B. Fambro

Papers

Application of Subset Autoregressive Integrated Moving Average Model for Short-Term Freeway Traffic Volume Forecasting

Determination of stopping sight distances

Predicting Operating Speeds on Tangent Sections of Two-Lane Rural Highways:

Model to evaluate the impacts of bus priority on signalized intersections

Driver Perception-Brake Response in Stopping Sight Distance Situations