Using Deep Learning to Predict Short Term Traffic Flow: A Systematic Literature Review

Ali, Usman; Mahmood, Tariq

doi:10.1007/978-3-319-93710-6_11

Cited by 11 publications

(9 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Such data explosion introduces a problem well-known as the curse of dimensionality, which cannot be handled efficiently by traditional approaches [48,49]. To gain insight from big traffic data, deep neural networks have become popular in recent years to learn deep correlations inherent in data with little or no prior knowledge and need for manual feature engineering [13,50]. Stacked autoencoder models have been used to exploit temporal and spatiotemporal information on real-world or simulated datasets to predict traffic flow [5,51].…”

Section: Related Workmentioning

confidence: 99%

“…Various kinds and amounts of traffic data have been used by researchers in recent years for traffic condition prediction and related research of intelligent transportation systems. Most of these works use data sources such as road sensors, induction loops, automatic vehicle identification systems, remote traffic microwave sensors, in-road reflectors, floating car data, and simulation [3,4,10,11,12,13]. Images from cameras installed on roads, aerial photographs and remote sensing images as another kind of data source have also been used [14,15].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Deep Autoencoder Neural Networks for Short-Term Traffic Congestion Prediction of Transportation Networks

Zhang

Yao

et al. 2019

Sensors

View full text Add to dashboard Cite

Traffic congestion prediction is critical for implementing intelligent transportation systems for improving the efficiency and capacity of transportation networks. However, despite its importance, traffic congestion prediction is severely less investigated compared to traffic flow prediction, which is partially due to the severe lack of large-scale high-quality traffic congestion data and advanced algorithms. This paper proposes an accessible and general workflow to acquire large-scale traffic congestion data and to create traffic congestion datasets based on image analysis. With this workflow we create a dataset named Seattle Area Traffic Congestion Status (SATCS) based on traffic congestion map snapshots from a publicly available online traffic service provider Washington State Department of Transportation. We then propose a deep autoencoder-based neural network model with symmetrical layers for the encoder and the decoder to learn temporal correlations of a transportation network and predicting traffic congestion. Our experimental results on the SATCS dataset show that the proposed DCPN model can efficiently and effectively learn temporal relationships of congestion levels of the transportation network for traffic congestion forecasting. Our method outperforms two other state-of-the-art neural network models in prediction performance, generalization capability, and computation efficiency.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Deep Autoencoder Neural Networks for Short-Term Traffic Congestion Prediction of Transportation Networks

Zhang

Yao

et al. 2019

Sensors

View full text Add to dashboard Cite

show abstract

“…Then, a series of enhanced ARIMA models such as fractional-ARIMA, SOM/ARIMA, and switching ARIMA also were applied to forecast traffic flow [17], [18], [19]. In recent years, with the rapid development of neural networks, data-driven approaches have a series breakthrough for travel-time and short-term traffic flow prediction with complex data [14], [20], for example k-nearest neighbor (KNN) [21], support vector machine (SVM) and its hybrid models [22], [23], radial basis function (RBF) [24], deep neural network (DNN) [25], staked autoencoder (SAE) [15], [26], [27]. Further than that, many of hybrid models were proposed for traffic flow prediction, for example, long short-term memory (LSTM) combined with SAE [28], convolution neural network (CNN) combined with GRU.…”

Section: B Predicting Traffic Flowmentioning

confidence: 99%

Quantitative Assessment on Truck-Related Road Risk for the Safety Control via Truck Flow Estimation of Various Types

et al. 2019

View full text Add to dashboard Cite

Traffic conditions of truck flow is one of the critical factors influencing transportation safety and efficiency, which is directly related to traffic accidents, maintenance scheduling, traffic flow interruption, risk control, and management. The estimation of the truck flow of various types could be better to identify the irregular flow variation introduced by various trucks and quantitatively assessed the corresponding road risks. In this paper, the dynamics of truck flow are estimated first. The stochastic and uncertain trucks flow data are obtained in terms of small, medium, heavy, and the oversize truck type and regulated corresponding flow in the time series within five minutes. In order to dig the spatial-temporal correlations behind those data, the deep learning-based method is improved on the basis of the gated recurrent unit (GRU) to estimate the truck flow for various types. To quantitatively assess the truck-related effect for road risk, a multiple logistic regression method is further proposed to classify into safe, risky, and dangerous road risks levels. Different risk level could guide the traffic control and management and traffic information that broadcast drivers to help them to choose travel route. The proposed prediction of the road risk is tested in the randomly selected road segment and shows superior compared to other methods. This could promote road safety in the development of intelligent transport system (ITS).INDEX TERMS Truck flow prediction, road risk assessment, various types of truck, remote traffic microwave sensor (RTMS), gated recurrent unit (GRU).

show abstract

“…Deep learning is a recent non-parametric neural-network-based approach to short-term speed prediction, which attempts to model the complex nature of traffic data. Traffic flow prediction has been performed using a variety of deep learning architectures (see Ali and Mahmood ( 18 ) for a review). The variety of architectures applied, such as autoencoders and deep belief networks ( 19 – 21 ), reflects the different information that can be included in the input data, as well as different approaches to help the artificial neural network learn the desired mapping from input to output.…”

Section: Related Workmentioning

confidence: 99%

“…RNNs were designed to learn temporal correlations from sequences of data and have been applied to traffic flow prediction in several studies ( 23 – 27 ). Long short-term memory (LSTM) units are a widely applied ( 18 ) element of RNNs that help in training a network to learn correlations across many timesteps ( 28 ).…”

Section: Related Workmentioning

confidence: 99%

Deep Learning System for Travel Speed Predictions on Multiple Arterial Road Segments

Nguyên

Bentley

Kieu

et al. 2019

Transportation Research Record

View full text Add to dashboard Cite

Accurate travel speed prediction is a critical tool for incidence response management. The complex dynamics of transport systems render model-based prediction extremely challenging. However, the large amounts of available vehicle speed data contain the complex interdependencies of the target travel speed; the data itself can be used to generate accurate predictions using deep learning methods. In this work, a deep learning methodology involving feature generation, model development, and model deployment is presented. The authors demonstrate the high performance of deep learning methods (relative to more traditional benchmarks) in predicting travel speeds from 5–30 min in advance, for a challenging arterial road network. In this study, different deep learning architectures that exploit both spatial and temporal information for several time frames are compared and analyzed. Finally, the authors demonstrate the integration of their deep learning method into a visualization system that can be directly applied for vehicle speed prediction in real time. The model-selection analysis and data-to-visualization framework in this manuscript provide a step towards decision support for incident management; for practical implementation, the predictive power of deep learning models under incident conditions should continue to be investigated and improved.

show abstract

Using Deep Learning to Predict Short Term Traffic Flow: A Systematic Literature Review

Cited by 11 publications

References 26 publications

Deep Autoencoder Neural Networks for Short-Term Traffic Congestion Prediction of Transportation Networks

Deep Autoencoder Neural Networks for Short-Term Traffic Congestion Prediction of Transportation Networks

Quantitative Assessment on Truck-Related Road Risk for the Safety Control via Truck Flow Estimation of Various Types

Deep Learning System for Travel Speed Predictions on Multiple Arterial Road Segments

Contact Info

Product

Resources

About