Physics Informed Deep Learning for Traffic State Estimation

Huang, Jiheng; Agarwal, Shaurya

doi:10.1109/itsc45102.2020.9294236

Cited by 45 publications

(44 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This includes early detection of vehicle congestion blockades and high transportation demand. An example is a detection of a sudden drop in the average speed v would indicate severe congestion or an accident [1].…”

Section: Physics Informed Deep Learning For Traffic State Estimationmentioning

confidence: 99%

“…The accuracy is then calculated using the Frobenius norm to measure the accuracy of the neural network. The model was tested using varying data sizes and collection locations and there were positive results [1].…”

Section: Physics Informed Deep Learning For Traffic State Estimationmentioning

confidence: 99%

“…These two models have different advantages and disadvantages. Mathematical models used in the estimation of any process are mainly derived from underlying processes [1].…”

Section: Introductionmentioning

confidence: 99%

“…Data analysis methods have also been used to understand the spreading patterns of COVID-19 including the machine learning (ML) approach [3,15]. The viability of using artificial intelligence (AI) methods to solve ODEs has been disputed since these equations are governed by scientific laws which are never instilled during the training process [1]. A new framework called the Physics Informed Neural Networks (PINNS) has been developed and aims to eliminate this problem.…”

mentioning

confidence: 99%

“…The PINNS is a Artificial Neural Network (ANN) framework which during the training process exposes the developed neural network to data sets and governing laws. The governing laws are provided in the form of ODEs or PDEs to the model [1,2,35]. Understanding the dynamics of COVID-19 is crucial in reducing the effects of the virus.…”

mentioning

confidence: 99%

See 4 more Smart Citations

Determining COVID-19 Dynamics Using Physics Informed Neural Networks

Malinzi¹,

Gwebu²,

Motsa³

2021

Preprint

View full text Add to dashboard Cite

The Physics Informed Neural Networks framework is applied to the understanding of the dynamics of Coronavirus of 2019. To provide the governing system of equations used by the framework, the Susceptible-Infected-Recovered-Death mathematical model is used. The study focused on finding the patterns of the dynamics of the disease which involves predicting the infection rate, recovery rate and death rate; thus predicting the active infections, total recovered, susceptible and deceased at any required time. The study used data that was collected on the dynamics of COVID-19 from the Kingdom of Eswatini between March 2020 and September 2021. The obtained results showed less errors thus making highly accurate predictions.

show abstract

Section: Physics Informed Deep Learning For Traffic State Estimationmentioning

confidence: 99%

Section: Physics Informed Deep Learning For Traffic State Estimationmentioning

confidence: 99%

“…These two models have different advantages and disadvantages. Mathematical models used in the estimation of any process are mainly derived from underlying processes [1].…”

Section: Introductionmentioning

confidence: 99%

mentioning

confidence: 99%

mentioning

confidence: 99%

See 3 more Smart Citations