Statistical Analytics and Regional Representation Learning for COVID-19 Pandemic Understanding

Fazeli, Shayan; Moatamed, Babak; Sarrafzadeh, Majid

doi:10.1109/ichi52183.2021.00047

Cited by 1 publication

(2 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Many studies showed that the RW method is applicable to most time-series data, especially when the samples have the same distribution and are independent of each other. A Gaussian Random Walk for variable 𝑦 𝑡 can be written by: 𝑦 𝑡 = 𝑦 𝑡 −1 + 𝜖 𝑡 (7) where 𝜖 𝑡 follows Gaussian distribution.…”

Section: Random Walkmentioning

confidence: 99%

“…Early studies such as the one proposed in [4] used the SIR model for forecasting the infection rate in different countries. Other work [7] used ARIMA to predict the daily death rate in different states in the United States. [10] introduced AUG-NN model that enriches neural network models by augmentation which resulted in significant improvements in the accuracy.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Improving COVID-19 Forecasting using eXogenous Variables

Toutiaee,

Li,

Chaudhari

et al. 2021

Preprint

View full text Add to dashboard Cite

In this work, we study the pandemic course in the United States by considering national and state levels data. We propose and compare multiple time-series prediction techniques which incorporate auxiliary variables. One type of approach is based on spatio-temporal graph neural networks which forecast the pandemic course by utilizing a hybrid deep learning architecture and human mobility data. Nodes in this graph represent the state-level deaths due to COVID-19, edges represent the human mobility trend and temporal edges correspond to node attributes across time. The second approach is based on a statistical technique for COVID-19 mortality prediction in the United States that uses the SARIMA model and eXogenous variables. We evaluate these techniques on both state and national levels COVID-19 data in the United States and claim that the SARIMA and MCP models generated forecast values by the eXogenous variables can enrich the underlying model to capture complexity in respectively national and state levels data. We demonstrate significant enhancement in the forecasting accuracy for a COVID-19 dataset, with a maximum improvement in forecasting accuracy by 64.58% and 59.18% (on average

show abstract

Section: Random Walkmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%