Time series prediction of COVID-19 transmission in America using LSTM and XGBoost algorithms

Abstract

In this paper, we establish daily confirmed infected cases prediction models for the time series data of America by applying both the long short-term memory (LSTM) and extreme gradient boosting (XGBoost) algorithms, and employ four performance parameters as MAE, MSE, RMSE, and MAPE to evaluate the effect of model fitting. LSTM is applied to reliably estimate accuracy due to the long-term attribute and diversity of COVID-19 epidemic data. Using XGBoost model, we conduct a sensitivity analysis to determine the robustness of predictive model to parameter features. Our results reveal that achieving a reduction in the contact rate between susceptible and infected individuals by isolated the uninfected individuals, can effectively reduce the number of daily confirmed cases. By combining the restrictive social distancing and contact tracing, the elimination of ongoing COVID-19 pandemic is possible. Our predictions are based on real time series data with reasonable assumptions, whereas the accurate course of epidemic heavily depends on how and when quarantine, isolation and precautionary measures are enforced.

Predicting the epidemic curve of the coronavirus (SARS-CoV-2) disease (COVID-19) using artificial intelligence: An application on the first and second waves

“…In contrast to our model, neither Wuhan data were included nor metadata from other restriction measures were used. The model forecasting for the first week shows similar accuracy to our model, but over longer periods, our approach is much closer to the real behavior [ 23 ].…”

“…In Luo et al (2021), a simple LSTM model and the XGBoost algorithm were compared on US COVID-19 data [ 23 ]. The training set contains data between April 2020 and September 2020, while the prediction is given for 30 days.…”

Forecasting COVID-19 new cases using deep learning methods

“…In addition to CNN, multiple studies have used the long short-term memory [ 28 ] (LSTM) framework for forecasting the transmission of COVID-19, because of its memory capacity [ [29] , [30] , [31] ]; P [ 12 ]. Since the prediction of COVID-19 cases is a time series problem and involves capturing time dependencies in the data, we develop an LSTM model that can predict the COVID-19 cases.…”

Forecasting COVID-19 recovered cases with Artificial Neural Networks to enable designing an effective blood supply chain

“…Finally, the output gate determines which information to read and output. The equations for the forget gate, input gate, and output gate are given in Equations (14) , (15) , (16) , respectively [ 124 ]. Where be the sigmoid function, are relevant weights in forget, input and output gate, denotes the previous output at time , is the input vector at time , and are bias neurons at the respective gate associated with each LSTM block.…”