2018
DOI: 10.1111/mice.12376
|View full text |Cite
|
Sign up to set email alerts
|

End‐to‐End Deep Learning Methodology for Real‐Time Traffic Network Management

Abstract: This article presents a novel real‐time traffic network management system using an end‐to‐end deep learning (E2EDL) methodology. A computational learning model is trained, which allows the system to identify the time‐varying traffic congestion pattern in the network, and recommend integrated traffic management schemes to reduce this congestion. The proposed model structure captures the temporal and spatial congestion pattern correlations exhibited in the network, and associates these patterns with efficient tr… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1

Citation Types

0
32
0

Year Published

2019
2019
2023
2023

Publication Types

Select...
7
3

Relationship

0
10

Authors

Journals

citations
Cited by 51 publications
(32 citation statements)
references
References 52 publications
0
32
0
Order By: Relevance
“…In addition, because the developed adaptive local approximation method in this paper is based on the characteristics of SVM, such as the support hyperplanes, other classification algorithms cannot be directly employed to take place of SVM. Some other popular classification algorithms have been extensively used in practical engineering, such as neural network (Ahmadlou & Adeli, ; Koziarski & Cyganek, ; Molina‐Cabello, Luque‐Baena, López‐Rubio, & Thurnhofer‐Hemsi, ; Wang & Bai, ; Xue & Li, ), neural dynamic classification (Rafiei & Adeli, , ), and deep learning techniques (Gao & Mosalam, ; Hashemi & Abdelghany, ; Rafiei & Adeli, , ; Rafiei, Khushefati, Demirboga, & Adeli, ; Zhang et al., ; Ortega‐Zamorano, Jerez, Gómez, & Franco, ; Torres, Galicia, Troncoso, & Martínez‐Álvarez, ). The applications of these classification algorithms in SRA‐RI can be investigated.…”
Section: Discussionmentioning
confidence: 99%
“…In addition, because the developed adaptive local approximation method in this paper is based on the characteristics of SVM, such as the support hyperplanes, other classification algorithms cannot be directly employed to take place of SVM. Some other popular classification algorithms have been extensively used in practical engineering, such as neural network (Ahmadlou & Adeli, ; Koziarski & Cyganek, ; Molina‐Cabello, Luque‐Baena, López‐Rubio, & Thurnhofer‐Hemsi, ; Wang & Bai, ; Xue & Li, ), neural dynamic classification (Rafiei & Adeli, , ), and deep learning techniques (Gao & Mosalam, ; Hashemi & Abdelghany, ; Rafiei & Adeli, , ; Rafiei, Khushefati, Demirboga, & Adeli, ; Zhang et al., ; Ortega‐Zamorano, Jerez, Gómez, & Franco, ; Torres, Galicia, Troncoso, & Martínez‐Álvarez, ). The applications of these classification algorithms in SRA‐RI can be investigated.…”
Section: Discussionmentioning
confidence: 99%
“…The method was shown here by implementing the ANN and the GA in MATLAB. It is worthwhile mentioning that although there is a growing trend toward deep neural networks and more sophisticated methods in civil engineering (Cha, Choi, Suh, Mahmoudkhani, & Büyüköztürk, 2018;Hashemi and Abdelghany, 2018;Nabian & Meidani, 2018;Rafiei & Adeli, 2018), the conventional backpropagation neural network was used here because the main scope of this study is the formulation of fuzzy Sobol indices and the considered metamodel is proven to be accurate enough to reduce the computational effort of the example. The maximum vertical deflection above the removed column, during 5 s after sudden column removal, was considered as the output of the ANN and was used to find the maximum demand of beam rotations.…”
Section: Ann Metamodelmentioning
confidence: 99%
“…Autonomous crack detection systems aid short‐term and long‐term inspections in terms of decreasing human involvement during their operation, resulting in lower cost, higher reliability, and system efficiency. Concurrent to these developments in computer‐vision techniques, there has been a resurgence of machine learning algorithms in a variety of fields, including image processing and pattern recognition (Hashemi & Abdelghany, ; Koziarski & Cyganek, ; Molina‐Cabello, Luque‐Baena, López‐Rubio, & Thurnhofer‐Hemsi, ; Nabian & Meidani, ; Sonka, Hlavac, & Boyle, ; Torres, Galicia, Troncoso, & Martínez‐Álvarez, ; Wang & Bai, ; Wang et al., ; Wang et al, ; Wu, Zhang, Story, & Rajan, ; Zhang & Zhang, ). Meanwhile, the hardware implementation of training large‐scale neural networks also receives wide attention (Ortega‐Zamorano, Jerez, Gómez, & Franco, ).…”
Section: Introductionmentioning
confidence: 99%