Traffic State Prediction Using One-Dimensional Convolution Neural Networks and Long Short-Term Memory
Traffic prediction is a vitally important keystone of an intelligent transportation system (ITS). It aims to improve travel route selection, reduce overall carbon emissions, mitigate congestion, and enhance safety. However, efficiently modelling traffic flow is challenging due to its dynamic and non...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-05-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/12/10/5149 |
| _version_ | 1797501794910208000 |
|---|---|
| author | Selim Reza Marta Campos Ferreira José J. M. Machado João Manuel R. S. Tavares |
| author_facet | Selim Reza Marta Campos Ferreira José J. M. Machado João Manuel R. S. Tavares |
| author_sort | Selim Reza |
| collection | DOAJ |
| description | Traffic prediction is a vitally important keystone of an intelligent transportation system (ITS). It aims to improve travel route selection, reduce overall carbon emissions, mitigate congestion, and enhance safety. However, efficiently modelling traffic flow is challenging due to its dynamic and non-linear behaviour. With the availability of a vast number of data samples, deep neural network-based models are best suited to solve these challenges. However, conventional network-based models lack robustness and accuracy because of their incapability to capture traffic’s spatial and temporal correlations. Besides, they usually require data from adjacent roads to achieve accurate predictions. Hence, this article presents a one-dimensional (1D) convolution neural network (CNN) and long short-term memory (LSTM)-based traffic state prediction model, which was evaluated using the Zenodo and PeMS datasets. The model used three stacked layers of 1D CNN, and LSTM with a logarithmic hyperbolic cosine loss function. The 1D CNN layers extract the features from the data, and the goodness of the LSTM is used to remember the past events to leverage them for the learnt features for traffic state prediction. A comparative performance analysis of the proposed model against support vector regression, standard LSTM, gated recurrent units (GRUs), and CNN and GRU-based models under the same conditions is also presented. The results demonstrate very encouraging performance of the proposed model, improving the mean absolute error, root mean squared error, mean percentage absolute error, and coefficient of determination scores by a mean of 16.97%, 52.1%, 54.15%, and 7.87%, respectively, relative to the baselines under comparison. |
| first_indexed | 2024-03-10T03:23:41Z |
| format | Article |
| id | doaj.art-b624e8fe9862454483ac9561e5adf3a0 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T03:23:41Z |
| publishDate | 2022-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-b624e8fe9862454483ac9561e5adf3a02023-11-23T09:58:24ZengMDPI AGApplied Sciences2076-34172022-05-011210514910.3390/app12105149Traffic State Prediction Using One-Dimensional Convolution Neural Networks and Long Short-Term MemorySelim Reza0Marta Campos Ferreira1José J. M. Machado2João Manuel R. S. Tavares3Faculdade de Engenharia, Universidade do Porto, Rua Dr. Roberto Frias, s/n, 4200-465 Porto, PortugalFaculdade de Engenharia, Universidade do Porto, Rua Dr. Roberto Frias, s/n, 4200-465 Porto, PortugalDepartamento de Engenharia Mecânica, Faculdade de Engenharia, Universidade do Porto, Rua Dr. Roberto Frias, s/n, 4200-465 Porto, PortugalDepartamento de Engenharia Mecânica, Faculdade de Engenharia, Universidade do Porto, Rua Dr. Roberto Frias, s/n, 4200-465 Porto, PortugalTraffic prediction is a vitally important keystone of an intelligent transportation system (ITS). It aims to improve travel route selection, reduce overall carbon emissions, mitigate congestion, and enhance safety. However, efficiently modelling traffic flow is challenging due to its dynamic and non-linear behaviour. With the availability of a vast number of data samples, deep neural network-based models are best suited to solve these challenges. However, conventional network-based models lack robustness and accuracy because of their incapability to capture traffic’s spatial and temporal correlations. Besides, they usually require data from adjacent roads to achieve accurate predictions. Hence, this article presents a one-dimensional (1D) convolution neural network (CNN) and long short-term memory (LSTM)-based traffic state prediction model, which was evaluated using the Zenodo and PeMS datasets. The model used three stacked layers of 1D CNN, and LSTM with a logarithmic hyperbolic cosine loss function. The 1D CNN layers extract the features from the data, and the goodness of the LSTM is used to remember the past events to leverage them for the learnt features for traffic state prediction. A comparative performance analysis of the proposed model against support vector regression, standard LSTM, gated recurrent units (GRUs), and CNN and GRU-based models under the same conditions is also presented. The results demonstrate very encouraging performance of the proposed model, improving the mean absolute error, root mean squared error, mean percentage absolute error, and coefficient of determination scores by a mean of 16.97%, 52.1%, 54.15%, and 7.87%, respectively, relative to the baselines under comparison.https://www.mdpi.com/2076-3417/12/10/5149support vector regressionlong short-term memorygated recurrent unitsone-dimensional convolution neural networkZenodo and PeMS datasets |
| spellingShingle | Selim Reza Marta Campos Ferreira José J. M. Machado João Manuel R. S. Tavares Traffic State Prediction Using One-Dimensional Convolution Neural Networks and Long Short-Term Memory Applied Sciences support vector regression long short-term memory gated recurrent units one-dimensional convolution neural network Zenodo and PeMS datasets |
| title | Traffic State Prediction Using One-Dimensional Convolution Neural Networks and Long Short-Term Memory |
| title_full | Traffic State Prediction Using One-Dimensional Convolution Neural Networks and Long Short-Term Memory |
| title_fullStr | Traffic State Prediction Using One-Dimensional Convolution Neural Networks and Long Short-Term Memory |
| title_full_unstemmed | Traffic State Prediction Using One-Dimensional Convolution Neural Networks and Long Short-Term Memory |
| title_short | Traffic State Prediction Using One-Dimensional Convolution Neural Networks and Long Short-Term Memory |
| title_sort | traffic state prediction using one dimensional convolution neural networks and long short term memory |
| topic | support vector regression long short-term memory gated recurrent units one-dimensional convolution neural network Zenodo and PeMS datasets |
| url | https://www.mdpi.com/2076-3417/12/10/5149 |
| work_keys_str_mv | AT selimreza trafficstatepredictionusingonedimensionalconvolutionneuralnetworksandlongshorttermmemory AT martacamposferreira trafficstatepredictionusingonedimensionalconvolutionneuralnetworksandlongshorttermmemory AT josejmmachado trafficstatepredictionusingonedimensionalconvolutionneuralnetworksandlongshorttermmemory AT joaomanuelrstavares trafficstatepredictionusingonedimensionalconvolutionneuralnetworksandlongshorttermmemory |