Highlights Introduction of a generalizable Bayesian recurrent neural network framework for uncertainty quantification in traffic flow prediction. Utilization of spectral normalization in hidden layers of neural network to enhance generalizability and improve uncertainty estimates. Demonstration of how normalization alters the training process, controlling model complexity and reducing overfitting. Spectral normalization improves generalization performance of deep learning models on out-of-distribution datasets, which is crucial for traffic management applications. Ability of spectral normalization to localize latent feature space under data perturbations, leading to improved generalizability. Significant outperformance of spectral normalization over layer normalization and models without normalization in both single and multistep prediction horizons.
Abstract Deep-learning models for traffic data prediction can have superior performance in modeling complex functions using a multi-layer architecture. However, a major drawback of these approaches is that most of these approaches do not offer forecasts with uncertainty estimates, which are essential for traffic operations and control. Without uncertainty estimates, it is difficult to place any level of confidence in the model predictions, and operational strategies relying on overconfident predictions can lead to worsening traffic conditions. In this study, we propose a Bayesian recurrent neural network framework for uncertainty quantification in traffic prediction with higher generalizability by introducing spectral normalization to its hidden layers. In our paper, we have shown that normalization alters the training process of deep neural networks by controlling the model's complexity and reducing the risk of overfitting the training data. This, in turn, helps improve the generalization performance of the model on out-of-distribution datasets. Results demonstrate that spectral normalization improves uncertainty estimates and significantly outperforms both the layer normalization and model without normalization in both single and multistep prediction horizons. This improved performance can be attributed to the ability of spectral normalization to better localize the latent feature space of the data under perturbations. Our findings are especially relevant to traffic management applications, where predicting traffic conditions across multiple locations is the goal, but the availability of training data from multiple locations is limited. Spectral normalization, therefore, provides a more generalizable approach that can effectively capture the underlying patterns in traffic data without requiring location-specific models.
A Bayesian approach to quantifying uncertainties and improving generalizability in traffic prediction models
2024-03-23
Aufsatz (Zeitschrift)
Elektronische Ressource
Englisch
Quantifying Uncertainties in Measurements of Railway Vibration
Springer Verlag | 2018
|