Physics-Informed Deep Learning for Traffic State Estimation

Abstract: Deep neural networks increasingly use attention to interpret and improve model performance, but little research has examined how attention progresses to complete a task and whether it is reasonable. We propose an Attention with…

Abstract: Conventional deformable registration methods solve an image pair optimization model, which is computationally expensive. Recent deep learning-based methods estimate deformation quickly. These data-driven heuristic network architectures lack geometric constraints needed to generate plausible topology-preserving…

Abstract: Traffic congestion has become a major economic and environmental problem for urban areas worldwide. Traffic prediction is an effective way to reduce congestion. Traffic prediction research has grown since the late 1970s. Early studies…

Abstract: Entity resolution (ER), a classification problem, is difficult on real data due to dirty values. The best ER solutions use learning models like deep neural networks, which need lots of labeled training data. High-quality…

Abstract: Long-term traffic predictions are less dense than short-term ones. City-scale traffic prediction literature is also scarce due to data scarcity. This study examines the scalability of deep learning models for long-term large-scale traffic prediction….

Abstract: Kernel methods have thrived for 20 years. Big data has greatly increased data collection. Existing kernel methods are not scalable for training or predicting. This paper introduces a general sparse kernel learning formulation based…