Graph Sequence Neural Network with an Attention Mechanism for Traffic Speed Prediction

Lu, Zhilong; Liu, Weifeng; Xie, Zhipu; Xiong, Guixi; Sun, Leilei; Wang, Haiquan

doi:10.1145/3470889

Cited by 11 publications

(8 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Each layer in the multi-layer network represents a system or a subsystem, and the connection between the networks is realized based on the relationship between the actual system's layers [34,35]. Each layer in the multi-layer network may exhibit different local and global structural characteristics than those in the single-layer network, which provides an effective method for analyzing the interaction between different systems and the formation mechanism of the network [36][37][38].…”

Section: Multi-layer Networkmentioning

confidence: 99%

Construction and Characteristics Analysis of the Xi’an Public Transport Network Considering Single-Mode and Multi-Mode Transferring

Sun,

Xie,

Huang

et al. 2024

Sustainability

View full text Add to dashboard Cite

The connectivity of the urban public transport network and the convenience of transfers between modes of transit are important factors that affect whether passengers choose public transport. Identifying the key nodes that affect network connectivity, direct access, transfers, and clarifying the main factors that restrict the network efficiency play important roles in improving the efficiency of the public transport network and establishing a “green city”. On this premise, this paper constructs two single-layer networks and a composite network that can reflect the transfer relationship between ‘bus–bus’, ‘metro–metro’, and ‘metro–bus’ based on the method of Space-P. The composite network realizes the integration study of homogeneous and heterogeneous stops, lines, and transfer relationships in the public transport network. At the same time, five kinds of centrality indexes are applied to the transport transfer network, and the significance of these indexes in the network is explained. Through the comprehensive analysis of these five types of indexes, the key nodes affecting the network connectivity, direct access and transfer efficiency, can be identified more accurately. Taking the public transport network of Xi’an as an example, the structural characteristics of the networks, including scale-free and small-world characteristics, were empirically analyzed. The main stops that play important roles in networks were identified based on the integrated centrality, degrees, and weight degrees. The research results showed the following: (1) Xi’an’s metro network, bus network, and metro–bus composite network all have scale-free and small-world characteristics. (2) The influence of the key stops of the metro network is concentrated, while the influence of the key stops of the bus network is scattered. (3) The public transport network in the first ring road area of Xi’an has the highest degree of direct access, and the core areas of the south, west, and north of Xi’an also have high direct access. However, the direct access in the area east of Xi’an is slightly lower. (4) Xi’an’s bus transport network covers a large area, showing the characteristics of a dual-core “central + southern” network. (5) The metro–bus composite network demonstrates a closer connection between stops and a more balanced network. (6) Finally, the degree of direct access to stops in the bus transport network and metro transport network shows the characteristics of “the single core is dominant, and the circle diffusion weakens step by step”.

show abstract

Section: Multi-layer Networkmentioning

confidence: 99%

Construction and Characteristics Analysis of the Xi’an Public Transport Network Considering Single-Mode and Multi-Mode Transferring

Sun,

Xie,

Huang

et al. 2024

Sustainability

View full text Add to dashboard Cite

show abstract

“…Attention mechanisms typically involve a scoring mechanism that calculates the relevance or attention weight for each time step, followed by a weighted combination of the time step representations to produce a context vector that is then used for making predictions or further processing. Attention mechanisms in time series analysis have shown effectiveness in tasks such as sequence classification, forecasting, and anomaly detection, as they enable models to selectively attend to relevant temporal information while disregarding irrelevant or noisy segments of the time series [63][64][65].…”

Section: Attentionmentioning

confidence: 99%

Anomaly Detection in Medical Time Series with Generative Adversarial Networks: A Selective Review

Cekić

2024

Artificial Intelligence

View full text Add to dashboard Cite

Anomaly detection in medical data is often of critical importance, from diagnosing and potentially localizing disease processes such as epilepsy to detecting and preventing fatal events such as cardiac arrhythmias. Generative adversarial networks (GANs) have since their inception shown promise in various applications and have been shown to be effective in cybersecurity, data denoising, and data augmentation, and have more recently found a potentially important place in the detection of anomalies in medical time series. This chapter provides a selective review of this novel use of GANs, in the process highlighting the nature of anomalies in time series, special challenges related to medical time series, and some general issues in approaching time series anomaly detection with deep learning. We cover the most frequently applied GAN models and briefly detail the current landscape of applying GANs to anomaly detection in two commonly used medical time series, electrocardiography (ECG) and electroencephalography (EEG).

show abstract

“…The Graph Neural Network family as a whole includes a broad range of subjects, including as reinforcement learning, unsupervised learning, supervised learning, and semi-supervised learning. For instance, a model proposed by Lu et al [25] based on GNNs has the capability of mapping a graph G, including all its nodes, to an m-dimensional Euclidean space with n ∈ N. On the other hand, Reza et al [26] proposed a model that is an extension of Lu et al's [25], in which the authors used gated recurrent elements for making output GNN sequences. Bogaerts et al [27] proposed a GCNN model by employing CNNs for handling graph data in addition to a variety of alternative GNNs.…”

Section: Graph Neural Network-based Approachesmentioning

confidence: 99%

A Graph Neural Network (GNN)-Based Approach for Real-Time Estimation of Traffic Speed in Sustainable Smart Cities

Sharma

Nikashina

et al. 2023

Sustainability

View full text Add to dashboard Cite

Planning effective routes and monitoring vehicle traffic are essential for creating sustainable smart cities. Accurate speed prediction is a key component of these efforts, as it aids in alleviating traffic congestion. While their physical proximity is important, the interconnection of these road segments is what significantly contributes to the increase of traffic congestion. This interconnectedness poses a significant challenge to increasing prediction accuracy. To address this, we propose a novel approach based on Deep Graph Neural Networks (DGNNs), which represent the connectedness of road sections as a graph using Graph Neural Networks (GNNs). In this study, we implement the proposed approach, called STGGAN, for real-time traffic-speed estimation using two different actual traffic datasets: PeMSD4 and PeMSD8. The experimental results validate the prediction accuracy values of 96.67% and 98.75% for the PeMSD4 and PeMSD8 datasets, respectively. The computation of mean squared error (MSE), root mean squared error (RMSE), mean absolute error (MAE) and mean absolute percentage error (MAPE) also shows a progressive decline in these error values with increasing iteration count, demonstrating the success of the suggested technique. To confirm the feasibility, reliability, and applicability of the suggested STGGAN technique, we also perform a comparison analysis, including several statistical, analytical, and machine-learning- and deep-learning-based approaches. Our work contributes significantly to the field of traffic-speed estimation by considering the structure and characteristics of road networks through the implementation of DGNNs. The proposed technique trains a neural network to accurately predict traffic flow using data from the entire road network. Additionally, we extend DGNNs by incorporating Gated Graph Attention Network (GGAN) blocks, enabling the modification of the input and output to sequential graphs. The prediction accuracy of the proposed model based on DGNNs is thoroughly evaluated through extensive tests on real-world datasets, providing a comprehensive comparison with existing state-of-the-art models for traffic-flow forecasting.

show abstract

Graph Sequence Neural Network with an Attention Mechanism for Traffic Speed Prediction

Cited by 11 publications

References 29 publications

Construction and Characteristics Analysis of the Xi’an Public Transport Network Considering Single-Mode and Multi-Mode Transferring

Construction and Characteristics Analysis of the Xi’an Public Transport Network Considering Single-Mode and Multi-Mode Transferring

Anomaly Detection in Medical Time Series with Generative Adversarial Networks: A Selective Review

A Graph Neural Network (GNN)-Based Approach for Real-Time Estimation of Traffic Speed in Sustainable Smart Cities

Contact Info

Product

Resources

About