Výsledky vyhledávání - "Guler, S. Ilgin"

Report

Evaluating the reliability of automatically generated pedestrian and bicycle crash surrogates

Autor: Sengupta, Agnimitra, Guler, S. Ilgin, Gayah, Vikash V., Warchol, Shannon

Vulnerable road users (VRUs), such as pedestrians and bicyclists, are at a higher risk of being involved in crashes with motor vehicles, and crashes involving VRUs also are more likely to result in severe injuries or fatalities. Signalized intersecti

Externí odkaz: http://arxiv.org/abs/2307.13178

Zobrazit plný text záznamu

Report

Newell's theory based feature transformations for spatio-temporal traffic prediction

Autor: Sengupta, Agnimitra, Guler, S. Ilgin

Deep learning (DL) models for spatio-temporal traffic flow forecasting employ convolutional or graph-convolutional filters along with recurrent neural networks to capture spatial and temporal dependencies in traffic data. These models, such as CNN-LS

Externí odkaz: http://arxiv.org/abs/2307.05949

Zobrazit plný text záznamu

Report

A Bayesian approach to quantifying uncertainties and improving generalizability in traffic prediction models

Autor: Sengupta, Agnimitra, Mondal, Sudeepta, Das, Adway, Guler, S. Ilgin

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

Externí odkaz: http://arxiv.org/abs/2307.05946

Zobrazit plný text záznamu

Report

Hybrid hidden Markov LSTM for short-term traffic flow prediction

Autor: Sengupta, Agnimitra, Das, Adway, Guler, S. Ilgin

Deep learning (DL) methods have outperformed parametric models such as historical average, ARIMA and variants in predicting traffic variables into short and near-short future, that are critical for traffic management. Specifically, recurrent neural n

Externí odkaz: http://arxiv.org/abs/2307.04954

Zobrazit plný text záznamu