Predicting COVID-19 cases, deaths and recoveries using machine learning methods

Mohamed Lounis,Farhan Mohammad Khan

doi:10.30538/psrp-easl2021.0079

Abstract

In the presented work we applied three machine learning techniques to forecast and predict COVID-19 cases, deaths ad recoveries numbers in Algeria for the next six months using data from February 25th, 2020 to April 26th , 2021. These models are represented by the Gaussian process regression (GPR), the support vector machine (SVM) and the decision tree (DT). The plotting results and parameters evaluation pointed out that the Gaussian Process Regression (GPR) has the best performance. Prediction with this model showed that the number of cases, deaths and recoveries will increase in the next months Algeria recording a peak in the month of August and the curve will tend to decrease later.

Highlights

S eventeen months after its emergence, the coronavirus disease 2019 (COVID-19) continues its propagation affecting more than 165 million patients leading to more than 3.4 million deaths surpassing all expectations
COVID-19 time series data available till 26th April 2021 in Algeria were used for a projection of daily cases, deaths and recoveries for the six months using three machine learning techniques that are Gaussian process regression (GPR), support vector machine (SVM) and decision tree (DT)
Three machine learning approaches were applied to predict the number of COVID-19 cases, deaths and cured persons in Algeria

Summary

Introduction

S eventeen months after its emergence, the coronavirus disease 2019 (COVID-19) continues its propagation affecting more than 165 million patients leading to more than 3.4 million deaths surpassing all expectations. To understand the epidemiological traits of this disease and to predict its evolution and its probable end-point multiple approaches have been used in Algeria and around the world. These approaches varied from epidemiological and mathematical/statistical to deep learning/machine learning models [2]. Machine learning models are of great importance [3] These tools which have proved their role in different complicated problems in different field in the last years including health, agriculture, engineering, sport, climate and robotics [4] have been widely used in the current context of COVID-19 [5–8]. Among these models we can find auto regressive integrated moving average (ARIMA) models [5], BSTS (Bayesian structural time series) [4], simple RNN (recurrent neural network) [7], artificial neural network (ANN) [8], long-short term memory (LSTM) [9], linear regression [10], adaptive neurofuzzy inference system (ANFIS) [11], least absolute shrinkage and selection operator (LASSO) regression [12], CUBIST (cubist regression) [13], Gaussian process regression (GPR) [14], exponential smoothing (ES) [15], random forest (RF) [8,13,16], ridge regression (RIDGE) [13], support vector machine (SVM) [8,13], Naïve bayes (NB) [8], decision tree (DT) [8], box-jenkins method [17], variational auto encoder (VAE) [7,10], gated recurrent units (GRU) [7,9] and multi-layer perceptron (MLP), models [18]

Related works

Methodology

Results and discussion

Conclusion