Forecasting COVID-19 Spreading in Canada using Deep Learning
Khennou, F.; Akhloufi, M. A.
Show abstract
AO_SCPLOWBSTRACTC_SCPLOWThe novel coronavirus disease 2019 (COVID-19) is disrupting all aspects of our lives as the global spread of the virus continues. In this difficult period, various research projects are taking place to study and analyse the dynamics of the pandemic. In the present work, we firstly present a deep overview of the main forecasting models to predict the new cases of COVID-19. In this context, we focus on univariate time series models in order to analyze the dynamic change of this pandemic through time. We secondly shed light on multivariate time series forecasting models using weather and daily tests data, to study the impact of exogenous features on the progression of COVID-19. In the final stage of this paper, we present our proposed approach based on LSTM and GRU ensemble learning model and evaluate the results using the MAE, RMSE and MAPE for the prediction of new cases. The results of our experiments using the Canadian dataset show that the ensemble model performs well in comparison to other models. In addition, this research provides us with a new outcome regarding the dynamic correlation between temperature, humidity and daily test data and its impact on the new contaminated cases.
Matching journals
The top 9 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- A new, simple method of describing COVID-19 trajectory and dynamics in any country based on Johnson Cumulative Distribution Function fitting 95%
- Comparing protein-protein interaction networks of SARS-CoV-2 and (H1N1) influenza using topological features 95%
- YieldNet: A Convolutional Neural Network for Simultaneous Corn and Soybean Yield Prediction Based on Remote Sensing Data 95%
Similar papers in this journal
- Improving Tuberculosis Detection in Chest X-ray Images through Transfer Learning and Deep Learning: A Comparative Study of CNN Architectures 92%
- Predicting COVID-19 Pandemic in Saudi Arabia Using Modified Singular Spectrum Analysis 92%
- The influence of SARS-CoV-2 variants of concern on national case fatality rates 92%
Similar papers in this journal
- Evaluating three different adaptive decomposition methods for EEG signal seizure detection and classification 92%
- A Transfer Entropy-based methodology to analyze information flow under eyes-open and eyes-closed conditions with a clinical perspective 91%
- Local and Global Measures of Information Storage for the Assessment of Heartbeat-Evoked Cortical Responses 91%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.