Search Results for author:
Found 9 papers, 4 papers with code
A Machine Learning Method for Predicting Traffic Signal Timing from Probe Vehicle Data
In this paper, we present a machine learning (ML) method for estimating traffic signal timing information from vehicle probe data.
Attention-based Spatial-Temporal Graph Neural ODE for Traffic Prediction
Traffic forecasting is an important issue in intelligent traffic systems (ITS).
HumanLight: Incentivizing Ridesharing via Human-centric Deep Reinforcement Learning in Traffic Signal Control
Apart from adopting FRAP, a state-of-the-art (SOTA) base model, HumanLight introduces the concept of active vehicles, loosely defined as vehicles in proximity to the intersection within the action interval window.
Explainable Graph Pyramid Autoformer for Long-Term Traffic Forecasting
Moreover, most of the existing deep learning traffic forecasting models are black box, presenting additional challenges related to explainability and interpretability.
Deep-Ensemble-Based Uncertainty Quantification in Spatiotemporal Graph Neural Networks for Traffic Forecasting
Our approach uses a scalable Bayesian optimization method to perform hyperparameter optimization, selects a set of high-performing configurations, fits a generative model to capture the joint distributions of the hyperparameter configurations, and trains an ensemble of models by sampling a new set of hyperparameter configurations from the generative model.
A data-centric weak supervised learning for highway traffic incident detection
To that end, we focus on a data-centric approach to improve the accuracy and reduce the false alarm rate of traffic incident detection on highways.
Socially-Aware Evaluation Framework for Transportation
In this paper, we develop a holistic framework of indicators, called Socially-Aware Evaluation Framework for Transportation (SAEF), that will assist in understanding how traffic routing and the resultant traffic dynamics impact city metrics, with the intent of avoiding unintended consequences and adhering to city objectives.
Transfer Learning with Graph Neural Networks for Short-Term Highway Traffic Forecasting
To that end, we develop a new transfer learning approach for DCRNN, where a single model trained on data-rich regions of the highway network can be used to forecast traffic on unseen regions of the highway network.
Graph-Partitioning-Based Diffusion Convolutional Recurrent Neural Network for Large-Scale Traffic Forecasting
We demonstrate the efficacy of the graph-partitioning-based DCRNN approach to model the traffic on a large California highway network with 11, 160 sensor locations.
