A Novel Matrix Profile-Guided Attention LSTM Model for Forecasting COVID-19 Cases in USA

Abstract

Background: The outbreak of the novel coronavirus disease 2019 (COVID-19) has been raging around the world for more than 1 year. Analysis of previous COVID-19 data is useful to explore its epidemic patterns. Utilizing data mining and machine learning methods for COVID-19 forecasting might provide a better insight into the trends of COVID-19 cases. This study aims to model the COVID-19 cases and perform forecasting of three important indicators of COVID-19 in the United States of America (USA), which are the adjusted percentage of daily admitted hospitalized COVID-19 cases (hospital admission), the number of daily confirmed COVID-19 cases (confirmed cases), and the number of daily death cases caused by COVID-19 (death cases).Materials and Methods: The actual COVID-19 data from March 1, 2020 to August 5, 2021 were obtained from Carnegie Mellon University Delphi Research Group. A novel forecasting algorithm was proposed to model and predict the three indicators. This algorithm is a hybrid of an unsupervised time series anomaly detection technique called matrix profile and an attention-based long short-term memory (LSTM) model. Several classic statistical models and the baseline recurrent neural network (RNN) models were used as the baseline models. All models were evaluated using a repeated holdout training and test strategy.Results: The proposed matrix profile-assisted attention-based LSTM model performed the best among all the compared models, which has the root mean square error (RMSE) = 1.23, 31612.81, 467.17, mean absolute error (MAE) = 0.95, 26259.55, 364.02, and mean absolute percentage error (MAPE) = 0.25, 1.06, 0.55, for hospital admission, confirmed cases, and death cases, respectively.Conclusion: The proposed model is more powerful in forecasting COVID-19 cases. It can potentially aid policymakers in making prevention plans and guide health care managers to allocate health care resources reasonably.

A data-driven combined prediction method for the demand for intensive care unit healthcare resources in public health emergencies

“…Support vector machine (SVM) is a machine-learning language for classification developed by Vapnik [ 29 ]. Suppose there are two categories of samples: H1 and H2.…”

Short-term forecasting of COVID-19 using support vector regression: An application using Zimbabwean data

“…Liu et al. 18 proposed a novel forecasting algorithm to model and predict the three indicators (hospital admission, confirmed cases and death cases). Vijander et al.…”

Calculating the matrix profile from noisy data

“…The MP has also been used in anomaly detection on IT operations time series data to address the issue of monitoring IT systems’ Key Performance Indicators [ 13 ]. The MP has offered market analysis based techniques in terms of stock-market financial time series data [ 14 ], while recent research has shown that in predicting COVID-19 cases, a hybrid of the MP and an attention-based long short-term memory (LSTM) model performed best when compared to other models [ 15 ].…”