Spatio-Temporal Traffic Flow Prediction in Madrid: An Application of Residual Convolutional Neural Networks

Vélez-Serrano, Daniel; Álvaro-Meca, Alejandro; Sebastián-Huerta, Fernando; Velez-Serrano, Jose F.

doi:10.3390/math9091068

Cited by 9 publications

(4 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some authors have used other approaches. For example, Zhou et al (2021) combined RNNs and convolutional neural networks (CNNs) by sliding windows over a map, while Vélez-Serrano et al (2021) proposed CNNs for the spatio-temporal structure of a set of sensors. In their work, Zhang & Kabuka (2018) used RNN to predict traffic flow on the basis of weather conditions such as temperature, smoke or wind speed.…”

Section: Related Workmentioning

confidence: 99%

Design of a pollution ontology-based event generation framework for the dynamic application of traffic restrictions

Ruiz de Gauna,

Sánchez,

Ruiz-Iniesta

2023

PeerJ Computer Science

View full text Add to dashboard Cite

The environmental damage caused by air pollution has recently become the focus of city council policies. The concept of the green city has emerged as an urban solution by which to confront environmental challenges worldwide and is founded on air pollution levels that have increased meaningfully as a result of traffic in urban areas. Local governments are attempting to meet environmental challenges by developing public traffic policies such as air pollution protocols. However, several problems must still be solved, such as the need to link smart cars to these pollution protocols in order to find more optimal routes. We have, therefore, attempted to address this problem by conducting a study of local policies in the city of Madrid (Spain) with the aim of determining the importance of the vehicle routing problem (VRP), and the need to optimise a set of routes for a fleet. The results of this study have allowed us to propose a framework with which to dynamically implement traffic constraints. This framework consists of three main layers: the data layer, the prediction layer and the event generation layer. With regard to the data layer, a dataset has been generated from traffic data concerning the city of Madrid, and deep learning techniques have then been applied to this data. The results obtained show that there are interdependencies between several factors, such as weather conditions, air quality and the local event calendar, which have an impact on drivers’ behaviour. These interdependencies have allowed the development of an ontological model, together with an event generation system that can anticipate changes and dynamically restructure traffic restrictions in order to obtain a more efficient traffic system. This system has been validated using real data from the city of Madrid.

show abstract

Section: Related Workmentioning

confidence: 99%

Design of a pollution ontology-based event generation framework for the dynamic application of traffic restrictions

Ruiz de Gauna,

Sánchez,

Ruiz-Iniesta

2023

PeerJ Computer Science

View full text Add to dashboard Cite

show abstract

“…Wang Jun et al [ 12 ] (2022) developed a method of automatically obtaining spatial dependence in data, which can automatically obtain the spatial state and spatial dependence using a multi graph advantageous neural network to predict traffic flow in time and space. V é lezserrano Daniel et al [ 13 ] (2021) performed a short-term prediction of traffic flow in Madrid, using different types of neural network architectures with a focus on convolutional residual neural networks. Xinyu Chen et al [ 14 ] (2021) obtained better prediction results after a Bayesian decomposition of multidimensional data.…”

Section: Literature Reviewmentioning

confidence: 99%

Multi-Section Traffic Flow Prediction Based on MLR-LSTM Neural Network

Shi

2022

Sensors

View full text Add to dashboard Cite

As the aggravation of road congestion leads to frequent traffic crashes, it is necessary to relieve traffic pressure through traffic flow prediction. As well, the traffic flow of the target road section to be predicted is also closely related to the adjacent road sections. Therefore, in this paper, a prediction method based on the combination of multiple linear regression and Long-Short-Term Memory (MLR-LSTM) is proposed, which uses the incomplete traffic flow data in the past period of time of the target prediction section and the continuous and complete traffic flow data in the past period of time of each adjacent section to jointly predict the traffic flow changes of the target section in a short time. The accurate prediction of future traffic flow changes can be solved based on the model supposed when the traffic flow data of the target road section is partially missing in the past period of time. The accuracy of the prediction results is the same as that of the current mainstream prediction results based on continuous and non-missing target link flow data. Meanwhile, there is a small-scale improvement when the data time interval is short enough. In the case of frequent maintenance of cameras in actual traffic sections, the proposed prediction method is more feasible and can be widely used.

show abstract

“…A number of research works have used convolutional neural networks (CNNs) to extract spatial connections from two-layered geospatial traffic data [49][50][51]. Since it is very difficult to represent the traffic network using 2D grids, few studies in [30,52,53] have attempted to convert the structure of the traffic network into images, which are then used to map spatial similarities between different locations.…”

Section: Related Workmentioning

confidence: 99%

A Hybrid DNN Model for Travel Time Estimation from Spatio-Temporal Features

et al. 2022

View full text Add to dashboard Cite

Due to recent advances in the Vehicular Internet of Things (VIoT), a large volume of traffic trajectory data has been generated. The trajectory data is highly unstructured and pre-processing it is a very cumbersome task, due to the complexity of the traffic data. However, the accuracy of traffic flow learning models depends on the quantity and quality of preprocessed data. Hence, there is a significant gap between the size and quality of benchmarked traffic datasets and the respective learning models. Additionally, generating a custom traffic dataset with required feature points in a constrained environment is very difficult. This research aims to harness the power of the deep learning hybrid model with datasets that have fewer feature points. Therefore, a hybrid deep learning model that extracts the optimal feature points from the existing dataset using a stacked autoencoder is presented. Handcrafted feature points are fed into the hybrid deep neural network to predict the travel path and travel time between two geographic points. The chengdu1 and chengdu2 standard reference datasets are used to realize our hypothesis of the evolution of a hybrid deep neural network with minimal feature points. The hybrid model includes the graph neural networks (GNN) and the residual networks (ResNet) preceded by the stacked autoencoder (SAE). This hybrid model simultaneously learns the temporal and spatial characteristics of the traffic data. Temporal feature points are optimally reduced using Stacked Autoencoder to improve the accuracy of the deep neural network. The proposed GNN + Resnet model performance was compared to models in the literature using root mean square error (RMSE) loss, mean absolute error (MAE) and mean absolute percentile error (MAPE). The proposed model was found to perform better by improving the travel time prediction loss on chengdu1 and chengdu2 datasets. An in-depth comprehension of the proposed GNN + Resnet model for predicting travel time during peak and off-peak periods is also presented. The model’s RMSE loss was improved up to 22.59% for peak hours traffic data and up to 11.05% for off-peak hours traffic data in the chengdu1 dataset.

show abstract

Spatio-Temporal Traffic Flow Prediction in Madrid: An Application of Residual Convolutional Neural Networks

Cited by 9 publications

References 46 publications

Design of a pollution ontology-based event generation framework for the dynamic application of traffic restrictions

Design of a pollution ontology-based event generation framework for the dynamic application of traffic restrictions

Multi-Section Traffic Flow Prediction Based on MLR-LSTM Neural Network

A Hybrid DNN Model for Travel Time Estimation from Spatio-Temporal Features

Contact Info

Product

Resources

About