Deep Learning for Road Traffic Forecasting: Does it Make a Difference?

  title={Deep Learning for Road Traffic Forecasting: Does it Make a Difference?},
  author={Eric L. Manibardo and Ibai La{\~n}a and Javier Del Ser},
Deep Learning methods have been proven to be flexible to model complex phenomena. This has also been the case of Intelligent Transportation Systems (ITS), in which several areas such as vehicular perception and traffic analysis have widely embraced Deep Learning as a core modeling technology. Particularly in short-term traffic forecasting, the capability of Deep Learning to deliver good results has generated a prevalent inertia towards using Deep Learning models, without examining in depth… Expand

Figures and Tables from this paper

Graph Neural Network for Traffic Forecasting: A Survey
This survey is the first comprehensive survey that explores the application of graph neural networks for traffic forecasting problems and reviews the rapidly growing body of recent research using different GNNs, e.g., graph convolutional and graph attention networks, in various traffic forecast problems. Expand


A simple yet accurate short-term urban traffic forecasting solution applying supervised window-based regression analysis using Deep Learning algorithm is proposed and experimental results show that is it possible to forecast the intensity of traffic with good accuracy just monitoring its intensity in the last few minutes. Expand
Deep Learning: A Generic Approach for Extreme Condition Traffic Forecasting
This work builds a deep neural network based on long short term memory (LSTM) units and applies Deep LSTM to forecast peak-hour traffic and manages to identify unique characteristics of the traffic data. Expand
Machine Learning and Deep Learning Models for Traffic Flow Prediction: A Survey
Various models for Traffic flow prediction on the basis machine learning and deep learning approaches are studied, factors affecting the performance of traffic flow prediction intensity are studied and Benchmark performance evaluation metrics are reviewed. Expand
Geospatial data to images: A deep-learning framework for traffic forecasting
A deep-learning framework is proposed, which transforms geospatial data to images, and then utilizes the state-of-the-art deep- learning methodologies such as Convolutional Neural Network (CNN) and residual networks, and significantly outperforms traditional methods. Expand
Deep learning methods in transportation domain: a review
This study reviews recent studies of deep learning for popular topics in processing traffic data including transportation network representation, traffic flow forecasting, traffic signal control, automatic vehicle detection, traffic incident processing, travel demand prediction, autonomous driving and driver behaviours. Expand
A Survey on Modern Deep Neural Network for Traffic Prediction: Trends, Methods and Challenges
This work provides a detailed explanation of popular deep neural network architectures commonly used in the traffic flow prediction literatures, categorize and describe the literatures themselves, and presents an overview of the commonalities and differences between the different work. Expand
DeepSTCL: A Deep Spatio-temporal ConvLSTM for Travel Demand Prediction
A novel deep learning traffic demand forecasting framework which based on Deep Spatio-Temporal ConvLSTM is proposed in this paper, and the experimental results demonstrate that the method outperforms traditional models with accuracy and speed. Expand
Transfer Learning and Online Learning for Traffic Forecasting under Different Data Availability Conditions: Alternatives and Pitfalls
The potential of Transfer Learning (TL) for developing a traffic flow forecasting model in scenarios of absent data is unveiled and traditional batch learning is compared against TL based models using real traffic flow data collected by deployed loops managed by the City Council of Madrid (Spain). Expand
Traffic Flow Prediction With Big Data: A Deep Learning Approach
A novel deep-learning-based traffic flow prediction method is proposed, which considers the spatial and temporal correlations inherently and is applied for the first time that a deep architecture model is applied using autoencoders as building blocks to represent traffic flow features for prediction. Expand
Traffic speed prediction using deep learning method
  • Y. Jia, Jianping Wu, Yiman Du
  • Engineering, Computer Science
  • 2016 IEEE 19th International Conference on Intelligent Transportation Systems (ITSC)
  • 2016
A deep learning method, the Deep Belief Network (DBN) model, is proposed for short-term traffic speed information prediction and it is concluded that the DBN can outperform Back Propagation Neural Network (BPNN) and Auto-Regressive Integrated Moving Average (ARIMA) for all time horizons. Expand