bilzinet

AnisoCNN-HighRes-SpeedEstimation

We propose an Anisotropic Deep Convolutional Neural Network model exploiting causaility in human-drivne vehicular traffic flow. We show results for traffic speed field estimation. The key takeaway is that physics-informing deep learning models using domain knowledge can significantly reduce model complexity and improve generalizability.

bilzinet

Config files for my GitHub profile.

cvpinns

Network-Traffic-Signal-Tampering

nyu-latex-templates

Beamer presentation and poster template for New York University / NYU Abu Dhabi / NYU Shanghai

opensource-data

pifno

Physics Informed Fourier Neural Operator

PINNs

Physics Informed Deep Learning: Data-driven Solutions and Discovery of Nonlinear Partial Differential Equations

Traffic-state-reconstruction-using-Deep-CNN

We propose a statistical learning-based traffic speed estimation method that uses sparse vehicle trajectory information. Using a convolutional encoder-decoder based architecture, we show that a well trained neural network can learn spatio-temporal traffic speed dynamics from timespace diagrams. We demonstrate this for a homogeneous road section using simulated vehicle trajectories and then validate it using real-world data from NGSIM. Our results show that with probe vehicle penetration levels as low as 5%, the proposed estimation method can provide a sound reconstruction of macroscopic traffic speeds and reproduce realistic shockwave patterns, implying applicability in a variety of traffic conditions. We further discuss the model’s reconstruction mechanisms and confirm its ability to differentiate various traffic behaviors such as congested and free-flow traffic states, transition dynamics, and shockwave propagation.

bilzinet/Traffic-state-reconstruction-using-Deep-CNN

We propose a statistical learning-based traffic speed estimation method that uses sparse vehicle trajectory information. Using a convolutional encoder-decoder based architecture, we show that a well trained neural network can learn spatio-temporal traffic speed dynamics from timespace diagrams. We demonstrate this for a homogeneous road section using simulated vehicle trajectories and then validate it using real-world data from NGSIM. Our results show that with probe vehicle penetration levels as low as 5%, the proposed estimation method can provide a sound reconstruction of macroscopic traffic speeds and reproduce realistic shockwave patterns, implying applicability in a variety of traffic conditions. We further discuss the model’s reconstruction mechanisms and confirm its ability to differentiate various traffic behaviors such as congested and free-flow traffic states, transition dynamics, and shockwave propagation.

bilzinet/pifno

Physics Informed Fourier Neural Operator

bilzinet/AnisoCNN-HighRes-SpeedEstimation

We propose an Anisotropic Deep Convolutional Neural Network model exploiting causaility in human-drivne vehicular traffic flow. We show results for traffic speed field estimation. The key takeaway is that physics-informing deep learning models using domain knowledge can significantly reduce model complexity and improve generalizability.

bilzinet/bilzinet

Config files for my GitHub profile.

bilzinet/cvpinns

bilzinet/Network-Traffic-Signal-Tampering

bilzinet/nyu-latex-templates

Beamer presentation and poster template for New York University / NYU Abu Dhabi / NYU Shanghai

bilzinet/opensource-data

bilzinet/PINNs

Physics Informed Deep Learning: Data-driven Solutions and Discovery of Nonlinear Partial Differential Equations