In this research, an extreme learning machine (ELM) is proposed to predict the new COVID-19 cases in Algeria. In the present study, public health database from the Algeria health ministry has been used to train and test the ELM models. The input parameters for the predictive models include Cumulative Confirmed COVID-19 Cases (CCCC), Calculated COVID-19 New Cases (CCNC), and Index Day (ID). The predictive accuracy of the seven models has been assessed via several statistical parameters. The results showed that the proposed ELM model achieved an adequate level of prediction accuracy with smallest errors (MSE= 0.16, RMSE=0.4114, and MAE= 0.2912), and highest performances (NSE = 0.9999, IO = 0.9988, R2 = 0.9999). Hence, the ELM model could be utilized as a reliable and accurate modeling approach for predicting the new COVIS-19 cases in Algeria.

This study investigates the potential of a simple artificial neural network for the prediction of COVID-19 New Confirmed Cases in Algeria (CNCC). Four different ANN models were built (GRNN, RBFNN, ELM, and MLP). The performance of the predictive models is evaluated based on four numerical parameters, namely root mean squared error (RMSE), mean absolute error (MAE), Nash-Sutcliffe efficiency (NSE), and Pearson correlation coefficient (R). Taylor diagram was also used to examine the similarities and differences between the observed and predicted values obtained from the proposed models. The results showed the potential of the multi-layer perceptron neural network (MLPNN) which exhibited a high level of accuracy in comparison to the other models.

No abstract