Stochastic Weight Completion for Road Networks Using Graph Convolutional Networks

Hu, Jilin; Guo, Chenjuan; Yang, Bin; Jensen, Christian S.

doi:10.1109/icde.2019.00116

Cited by 77 publications

(40 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Research in GCNs architectures for road networks has thus far focused on extending GCNs architectures to solve specific problems with temporal dependencies [3], [21], [22]. In contrast, our work explores the spatial and structural aspects of GCN architectures and we present a novel GCN architecture that is designed to be generally applicable for machine learning on road networks.…”

Section: E Case Study: Danalienmentioning

confidence: 99%

Relational Fusion Networks: Graph Convolutional Networks for Road Networks

Jepsen

Jensen

Nielsen

2022

IEEE Trans. Intell. Transport. Syst.

Self Cite

View full text Add to dashboard Cite

The application of machine learning techniques in the setting of road networks holds the potential to facilitate many important intelligent transportation applications. Graph Convolutional Networks (GCNs) are neural networks that are capable of leveraging the structure of a network. However, many implicit assumptions of GCNs do not apply to road networks.We introduce the Relational Fusion Network (RFN), a novel type of GCN designed specifically for road networks. In particular, we propose methods that substantially outperform state-ofthe-art GCNs on two machine learning tasks in road networks. Furthermore, we show that state-of-the-art GCNs may fail to effectively leverage road network structure and may not generalize well to other road networks. Manuscript received by ...

show abstract

Section: E Case Study: Danalienmentioning

confidence: 99%

Relational Fusion Networks: Graph Convolutional Networks for Road Networks

Jepsen

Jensen

Nielsen

2022

IEEE Trans. Intell. Transport. Syst.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Researchers have done a lot of research on undirected graph neural networks [31][32][33][34][35][36][37][38], and only a few researchers pay attention to directed graph neural networks [39]. For undirected graph networks, the most representative one was proposed by Bruna and Szlam of New York University [38].…”

Section: Graph Networkmentioning

confidence: 99%

A Deep Graph-Embedded LSTM Neural Network Approach for Airport Delay Prediction

Zeng

Quan

et al. 2021

Journal of Advanced Transportation

View full text Add to dashboard Cite

Due to the strong propagation causality of delays between airports, this paper proposes a delay prediction model based on a deep graph neural network to study delay prediction from the perspective of an airport network. We regard airports as nodes of a graph network and use a directed graph network to construct airports’ relationship. For adjacent airports, weights of edges are measured by the spherical distance between them, while the number of flight pairs between them is utilized for airports connected by flights. On this basis, a diffusion convolution kernel is constructed to capture characteristics of delay propagation between airports, and it is further integrated into the sequence-to-sequence LSTM neural network to establish a deep learning framework for delay prediction. We name this model as deep graph-embedded LSTM (DGLSTM). To verify the model’s effectiveness and superiority, we utilize the historical delay data of 325 airports in the United States from 2015 to 2018 as the model training set and test set. The experimental results suggest that the proposed method is superior to the existing mainstream methods in terms of accuracy and robustness.

show abstract

“…Their approach was efficient to reduce the time consumed for computations when compared to the conventional algorithms that do not move from a place to another. Hu et al in 2019 [6] proposed a generic learning framework called Graph Convolutional Weight Completion (GCWC) that exploited the topology of a road network graph to estimate the weights for all roads. Then, they incorporated contextual information into GCWC to improve accuracy.…”

Section: Literature Reviewmentioning

confidence: 99%

A Network-Based Model for Mitigating Traffic Jams in Road Networks

Hasan¹

2021

Technium

View full text Add to dashboard Cite

Abstract. In recent years, the city of Mosul, which is the capital city of Nineveh province in the North of Iraq, had witnessed an unstable situation (e.g., wars, internal conflicts) that led to destructing most of the infrastructure including city roads. In addition, the population of Mosul is currently concentrated on the east coast of the city. Therefore, this situation has caused a server traffic jam and the roads have become overloaded, which is time-wasting when accessing a particular place in the city. In this analytical study, the roads of the east coast of Mosul city are modeled in the form of a Road Network. The proposed approach is based on concepts inspired from Complex Networks and their measurements such as clustering coefficient, betweenness, degree, and closeness. The dataset of this work was collected from Google Earth with the support of governmental offices and road-experienced individuals. The created network represents the road network of Mosul city. In the results, suggestions and recommendations are provided, which can contribute to alleviating the problem of traffic congestion in the city of Mosul. The provided suggestions do not need a high cost because the proposed approach benefits the current road networks with few modifications. The proposed approach is applicable to any city of interest.

show abstract

Stochastic Weight Completion for Road Networks Using Graph Convolutional Networks

Cited by 77 publications

References 26 publications

Relational Fusion Networks: Graph Convolutional Networks for Road Networks

Relational Fusion Networks: Graph Convolutional Networks for Road Networks

A Deep Graph-Embedded LSTM Neural Network Approach for Airport Delay Prediction

A Network-Based Model for Mitigating Traffic Jams in Road Networks

Contact Info

Product

Resources

About