Urban short-term traffic speed prediction with complicated information fusion on accidents

Xu, Xing; Hu, Xiaoge; Zhao, Yun; Lü, Xiaoshu; Aapaoja, Aki

doi:10.1016/j.eswa.2023.119887

Cited by 13 publications

(7 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Self-attention in conjunction with other temporal feature extraction methods such as GRU [22], [34], [62] and dilated causal convolution [40], [46], [51], [58] have also been proposed. GMAN [68], and AI-GFACN [71] adopted self-attention for both spatial and temporal feature extractions. In addition, Zheng et al [68] also introduced a transform attention layer that generated spatial-temporal embedding representations for the positional embedding of future time steps.…”

Section: A Temporal Feature Extractionmentioning

confidence: 99%

“…As transportation networks are inherently equipped with graph structures, the GNNs have become the most popular spatial feature extraction method for traffic forecasting. Convolutional GNNs have pioneered GNN-based traffic forecasting research, and have been widely used in concurrent models [15]- [17], [22], [28], [29], [31]- [33], [35], [37], [40], [43], [44], [47], [55]- [60], [62]- [64], [67], [71], [75], [95].…”

Section: B Spatial Feature Extraction With Graph Neural Networkmentioning

confidence: 99%

“…Gupta et al [38] proposed a message-passing GNN-based model with a spatial embedding and attention mechanism based on shortest-paths on graphs. Outside the existing taxonomy of GNNs, graph embedding techniques such as DeepWalk [97], LINE [98], and node2vec [99] have also been adopted to incorporate graph structures [24], [66], [68], [71], [89].…”

Section: B Spatial Feature Extraction With Graph Neural Networkmentioning

confidence: 99%

“…In contrast, GNN takes advantage of the node-link structure to incorporate the underlying transportation network topology. By modeling traffic sensors and road segments as graph nodes, the hidden representation of a target node is learned by aggregating information from the neighboring nodes connected by edges [15]- [17], [21], [22], [24], [26]- [29], [31], [32], [34]- [38], [40], [41], [43]- [47], [51]- [53], [55], [57]- [60], [63], [64], [66]- [68], [71]- [75].…”

mentioning

confidence: 99%

See 3 more Smart Citations

Performance Evaluation of Building Blocks of Spatial-Temporal Deep Learning Models for Traffic Forecasting

Shin,

Yoon

2023

IEEE Access

View full text Add to dashboard Cite

The traffic forecasting problem is a challenging task that requires spatial-temporal modeling and gathers research interests from various domains. In recent years, spatial-temporal deep learning models have improved the accuracy and scale of traffic forecasting. While hundreds of models have been suggested, they share similar modules, or building blocks, which can be categorized into three temporal feature extraction methods of recurrent neural networks, convolution, and self-attention and two spatial feature extraction methods of convolutional graph neural networks (GNN) and attentional GNN. More importantly, the models have been mostly evaluated for their entire architectures with limited efforts to characterize and understand the performance of each category of building blocks. In this study, we conduct an extensive, multifaceted experiment to understand the influence of building block selection on traffic forecasting accuracy, considering environmental characteristics and dataset distributions. Specifically, we implement six traffic forecasting models using three temporal and two spatial building blocks. When we evaluate the models on four datasets with diverse characteristics, the results show each building block demonstrates distinguishable characteristics depending on study sites, prediction horizons, and traffic categories. The convolution models demonstrate higher overall forecasting performance than other models, whereas self-attention models show competitiveness in less frequent traffic categories, transition states, and the presence of outliers. Based on the results, we also suggest an adaptive model evaluation framework for category-wise predictions of test sets based on the performance of the models on validation sets. The results of this evaluation framework demonstrate improved forecasting accuracy at most by 3.7% without further sophistication in existing model architectures. The results enhance the utility of existing models and suggest guidelines for researchers building traffic forecasting model architectures and for practitioners implementing these state-of-the-art techniques in real-world applications.

show abstract

Section: A Temporal Feature Extractionmentioning

confidence: 99%

Section: B Spatial Feature Extraction With Graph Neural Networkmentioning

confidence: 99%

Section: B Spatial Feature Extraction With Graph Neural Networkmentioning

confidence: 99%

mentioning

confidence: 99%

See 2 more Smart Citations

Performance Evaluation of Building Blocks of Spatial-Temporal Deep Learning Models for Traffic Forecasting

Shin,

Yoon

2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…By making informed predictions based on the cyclical nature of ur-ban data, policymakers can anticipate trends, prepare for challenges, and proactively design interventions that align with the city's temporal rhythm. In essence, the emphasis on seasonality within urban data analysis transcends statistical methodologies; it becomes a visionary tool that equips those shaping urban futures with the foresight needed to navigate the complexities of dynamic cityscapes [3,7,[9][10][11][12].…”

Section: Introductionmentioning

confidence: 99%

Temporal Dynamics of Citizen-Reported Urban Challenges: A Comprehensive Time Series Analysis

Gkontzis,

Kotsiantis,

Feretzakis

et al. 2024

BDCC

View full text Add to dashboard Cite

In an epoch characterized by the swift pace of digitalization and urbanization, the essence of community well-being hinges on the efficacy of urban management. As cities burgeon and transform, the need for astute strategies to navigate the complexities of urban life becomes increasingly paramount. This study employs time series analysis to scrutinize citizen interactions with the coordinate-based problem mapping platform in the Municipality of Patras in Greece. The research explores the temporal dynamics of reported urban issues, with a specific focus on identifying recurring patterns through the lens of seasonality. The analysis, employing the seasonal decomposition technique, dissects time series data to expose trends in reported issues and areas of the city that might be obscured in raw big data. It accentuates a distinct seasonal pattern, with concentrations peaking during the summer months. The study extends its approach to forecasting, providing insights into the anticipated evolution of urban issues over time. Projections for the coming years show a consistent upward trend in both overall city issues and those reported in specific areas, with distinct seasonal variations. This comprehensive exploration of time series analysis and seasonality provides valuable insights for city stakeholders, enabling informed decision-making and predictions regarding future urban challenges.

show abstract

Addressing the Privacy and Complexity of Urban Traffic Flow Prediction with Federated Learning and Spatiotemporal Graph Convolutional Networks

Zhou,

Liu

2024

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Urban short-term traffic speed prediction with complicated information fusion on accidents

Cited by 13 publications

References 25 publications

Performance Evaluation of Building Blocks of Spatial-Temporal Deep Learning Models for Traffic Forecasting

Performance Evaluation of Building Blocks of Spatial-Temporal Deep Learning Models for Traffic Forecasting

Temporal Dynamics of Citizen-Reported Urban Challenges: A Comprehensive Time Series Analysis

Addressing the Privacy and Complexity of Urban Traffic Flow Prediction with Federated Learning and Spatiotemporal Graph Convolutional Networks

Contact Info

Product

Resources

About