Predictions for COVID-19 with deep learning models of LSTM, GRU and Bi-LSTM

Abstract

COVID-19, responsible of infecting billions of people and economy across the globe, requires detailed study of the trend it follows to develop adequate short-term prediction models for forecasting the number of future cases. In this perspective, it is possible to develop strategic planning in the public health system to avoid deaths as well as managing patients. In this paper, proposed forecast models comprising autoregressive integrated moving average (ARIMA), support vector regression (SVR), long shot term memory (LSTM), bidirectional long short term memory (Bi-LSTM) are assessed for time series prediction of confirmed cases, deaths and recoveries in ten major countries affected due to COVID-19. The performance of models is measured by mean absolute error, root mean square error and r2_score indices. In the majority of cases, Bi-LSTM model outperforms in terms of endorsed indices. Models ranking from good performance to the lowest in entire scenarios is Bi-LSTM, LSTM, GRU, SVR and ARIMA. Bi-LSTM generates lowest MAE and RMSE values of 0.0070 and 0.0077, respectively, for deaths in China. The best r2_score value is 0.9997 for recovered cases in China. On the basis of demonstrated robustness and enhanced prediction accuracy, Bi-LSTM can be exploited for pandemic prediction for better planning and management.

Impact of Input Filtering and Architecture Selection Strategies on GRU Runoff Forecasting: A Case Study in the Wei River Basin, Shaanxi, China

“…The best model occurs in S6, which means that the bi-directional architecture performs better than the single directional architecture for two-day-ahead forecasting after hyperparameter optimisation. The outperformance of the bi-directional architecture has been claimed by many studies [52,53,60,66] in other domains and is still supported by this research when applying to runoff forecasting.…”

“…Another study [51] shows that a better prediction result (the test NSE of 0.942 compared with 0.666) has been obtained when using a selected subset of all rain gauges as the input. Furthermore, the LSTM or GRU networks' architectures can also influence the forecasting results [52,53].…”

Prediction of COVID-19 confirmed cases combining deep learning methods and Bayesian optimization

“…Also, in [9] , a new ensemble approach based on ANNs and fuzzy aggregation was proposed and its performance was evaluated on COVID-19 time series of Mexico and its 12 states which showed significant improvement than single ANN. In recent studies [ 2 , [10] , [11] , [12] ], deep learning methods such as LSTM and bidirectional LSTM (BiLSTM) have been utilized for COVID-19 time series forecasting . The results indicated that LSTM and its variants have good performance in predicting the COVID-19 time series.…”

Forecasting of COVID-19 cases using deep learning models: Is it reliable and practically significant?

“… Zeroual et al, 2020 , Tomar and Gupta, 2020 , Czarnowski et al, 2008 , El Zowalaty and Järhult, 2020 , Shahid et al, 2020 , Hewamalage et al, 2021 , Jiménez et al, 2020 , Kaushik et al, 2020 , BhedadJamshidi et al, 2020 , Ribeiro et al, 2020 , Naudé, 2020 , Arora et al, 2020 , Ribeiro et al, 2020 , Ogundokun et al, 2020 , Alzahrani et al, 2020 , Shastri et al, 2020 , Alakus and Turkoglu, 2020 , Papastefanopoulos et al, 2020 , Chimmula and Zhang, 2020 , Wang et al, 2020 , Wang et al, 2020 , DataGov , Car et al, 2020 .…”