no code implementations • 4 Aug 2023 • Juliette Ugirumurera, Joseph Severino, Erik A. Bensen, Qichao Wang, Jane Macfarlane
In this paper, we present a machine learning (ML) method for estimating traffic signal timing information from vehicle probe data.
no code implementations • 1 May 2023 • Weiheng Zhong, Hadi Meidani, Jane Macfarlane
Traffic forecasting is an important issue in intelligent traffic systems (ITS).
1 code implementation • 5 Apr 2023 • Dimitris M. Vlachogiannis, Hua Wei, Scott Moura, Jane Macfarlane
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.
1 code implementation • 27 Sep 2022 • Weiheng Zhong, Tanwi Mallick, Hadi Meidani, Jane Macfarlane, Prasanna Balaprakash
Moreover, most of the existing deep learning traffic forecasting models are black box, presenting additional challenges related to explainability and interpretability.
no code implementations • 4 Apr 2022 • Tanwi Mallick, Prasanna Balaprakash, Jane Macfarlane
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.
no code implementations • 17 Dec 2021 • Yixuan Sun, Tanwi Mallick, Prasanna Balaprakash, Jane Macfarlane
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.
no code implementations • 11 Nov 2021 • Anu Kuncheria, Joan L. Walker, Jane Macfarlane
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.
2 code implementations • 17 Apr 2020 • Tanwi Mallick, Prasanna Balaprakash, Eric Rask, Jane Macfarlane
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.
2 code implementations • 24 Sep 2019 • Tanwi Mallick, Prasanna Balaprakash, Eric Rask, Jane Macfarlane
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.