An Autoregressive Graph Convolutional Long Short-Term Memory Hybrid Neural Network for Accurate Prediction of COVID-19 Cases
- 28 April 2022
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computational Social Systems
- Vol. 10 (2) , 724-735
Abstract
Efficient prediction of COVID-19 cases could prepare the healthcare system to accommodate the COVID-19 cases in the forthcoming days and improve the overall resource management. A hybrid model comprised of an autoregressive filter, a graph convolutional neural network (GCN), and a long short-term memory neural network is proposed for COVID-19 cases prediction in USA. It captures accurately both linearities and nonlinearities present in the time series. An adjacency matrix is exploited in GCN that relies on Granger causality tests applied to historical COVID-19 cases for each state in USA. By doing so, the latent information about the spread of the virus is captured efficiently and the prediction performance of the hybrid model is improved, revealing which state truly affects the other ones. The proposed method outperforms the state-of-the-art techniques.Keywords
This publication has 39 references indexed in Scilit:
- Forecasting at ScaleThe American Statistician, 2018
- Financial Time Series Prediction Based on Deep LearningWireless Personal Communications, 2017
- Penalised Complexity Priors for Stationary Autoregressive ProcessesJournal of Time Series Analysis, 2017
- Estimation of flood warning runoff thresholds in ungauged basins with asymmetric error functionsHydrology and Earth System Sciences, 2016
- Forecasting Time Series With Complex Seasonal Patterns Using Exponential SmoothingJournal of the American Statistical Association, 2011
- Behaviour of Granger causality under filtering: Theoretical invariance and practical applicationJournal of Neuroscience Methods, 2011
- A hybrid neural network and ARIMA model for water quality time series predictionEngineering Applications of Artificial Intelligence, 2010
- Some properties of a simple moving average when applied to forecasting a time seriesJournal of the Operational Research Society, 1999
- Lag Order and Critical Values of the Augmented Dickey-Fuller TestJournal of Business & Economic Statistics, 1995
- The Holt-Winters Forecasting ProcedureJournal of the Royal Statistical Society Series C: Applied Statistics, 1978