To assist policy makers in taking adequate decisions to stop the spread of the COVID-19 pandemic, accurate forecasting of the disease propagation is of paramount importance.
In this webinar, two COVID-19 prediction models will be presented. The first one uses a deep learning approach to forecast the cumulative number of COVID-19 cases based on data from countries having similar demographic, socioeconomic and health sector indicators. The model also takes as input, the adopted lockdown measures.
The second approach uses a deep-learning model for evaluating and predicting the impact of various lockdown policies on daily COVID-19 cases. This is achieved by first grouping countries having similar lockdown policies, then training a prediction model based on the daily cases of the countries in each cluster along with a data description of these policies. Once the model is trained, it is used to evaluate several scenarios associated with the lockdown policies and investigate their impact on the predicted COVID-19 cases.
Quantitative evaluation shows that the proposed techniques improve forecast accuracy of daily cumulative COVID-19 cases. Additionally, our analyses focusing on Qatar highlighted that lifting restrictions, particularly on schools and borders, would result in a significant increase in the number of cases.
Dr. Abdelkarim Erradi is an Associate Professor in the Computer Science and Engineering Department at Qatar University. His research and development activities and interests focus on service-oriented computing, cloud services composition and mobile crowdsensing. He received his PhD in computer science from the University of New South Wales, Sydney, Australia.
Dr. Ahmed Ben Said received his PhD degree in Computer Science from the University of Burgundy, France. His research interests include machine learning and computer vision. He is also interested in urban computing and mobile health systems. Dr. Said is currently a data scientist at Qatar University.