Probabilistic Traffic State Prediction Based on Vehicle Trajectory Data

Khajeh Hosseini, Mohammadreza; Talebpour, Alireza

doi:10.1007/s42421-023-00085-8

Cited by 2 publications

(1 citation statement)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A significant fraction of recent research on DL-based traffic prediction reports the model performance degradation of DL models with increasing prediction horizon, thereby hinting at the increased underlying complexity of the modelling traffic prediction tasks at longer prediction horizons (Jia et al, 2016;Wu et al, 2018;Li et al, 2023;Kumar and Raubal, 2021;Khajeh Hosseini and Talebpour, 2023). This performance degradation has been observed for a wide range of DL architectures.…”

Section: Evidence From Dl-based Traffic Prediction Literaturementioning

confidence: 99%

Enhancing deep learning-based city-wide traffic prediction pipelines through complexity analysis

Kumar,

Martin,

Raubal

2024

Preprint

View full text Add to dashboard Cite

Deep learning models can effectively capture the non-linear spatiotemporal dynamics of city-wide traffic forecasting. Evidence of varying deep learning model performance between different cities, different prediction horizons, different scales, specific city regions, and during particular hours of the day abounds in the literature on deep learning-based traffic prediction, yet a unified metric to quantify the complexity of different prediction tasks does not exist. This paper proposes two metrics - Model Complexity ($MC$) and Intrinsic Complexity ($IC$). While $MC$ quantifies the complexity of deep learning models for city-wide traffic prediction tasks, the $IC$ quantifies the underlying complexity of the prediction task. Both metrics are validated through systematic experimentation using traffic volume data from three cities. Finally, we demonstrate how these metrics can improve the workflows for deep learning-based data-driven traffic prediction pipelines and deployment by reducing the hyperparameter search scope and comparing the effectiveness of different design pathways.

show abstract

Section: Evidence From Dl-based Traffic Prediction Literaturementioning

confidence: 99%

Enhancing deep learning-based city-wide traffic prediction pipelines through complexity analysis

Kumar,

Martin,

Raubal

2024

Preprint

View full text Add to dashboard Cite

show abstract

Enhancing Deep Learning-Based City-Wide Traffic Prediction Pipelines Through Complexity Analysis

Kumar,

Martin,

Raubal

2024

Data Sci. Transp.

View full text Add to dashboard Cite

Deep learning models can effectively capture the non-linear spatiotemporal dynamics of city-wide traffic forecasting. Evidence of varying deep learning model performance between different cities, different prediction horizons, different scales, specific city regions, and during particular hours of the day abounds in the literature on deep learning-based traffic prediction, yet a unified metric to quantify the complexity of different prediction tasks does not exist. This paper proposes two metrics—model complexity (MC) and intrinsic complexity (IC). While MC quantifies the effective complexity of deep learning models for city-wide traffic prediction tasks, the IC quantifies the underlying complexity of the prediction task. Being an effective complexity metric, MC depends on the model and the data. The IC depends only on the data and is invariant to the model being used. Both metrics are validated through systematic experimentation using traffic volume data from three cities. Finally, we demonstrate how these metrics can improve the workflows for deep learning-based data-driven traffic prediction pipelines and deployment by reducing the hyperparameter search scope and comparing the effectiveness of different design pathways.

show abstract

Probabilistic Traffic State Prediction Based on Vehicle Trajectory Data

Cited by 2 publications

References 41 publications

Enhancing deep learning-based city-wide traffic prediction pipelines through complexity analysis

Enhancing deep learning-based city-wide traffic prediction pipelines through complexity analysis

Enhancing Deep Learning-Based City-Wide Traffic Prediction Pipelines Through Complexity Analysis

Contact Info

Product

Resources

About