ATTENTION/WARNING - NE PAS DÉPOSER ICI/DO NOT SUBMIT HERE

Ceci est la version de TEST de DIAL.mem. Veuillez ne pas soumettre votre mémoire sur ce site mais bien à l'URL suivante: 'https://thesis.dial.uclouvain.be'.
This is the TEST version of DIAL.mem. Please use the following URL to submit your master thesis: 'https://thesis.dial.uclouvain.be'.
 

Prediction of the number of new coronavirus-related hospitalizations based on open source data

Gérard, Margaux ; Delecluse, Augustin
(2021)

Files

Delecluse_19231600_Gerard_76591600_2021.pdf
  • Open access
  • Adobe PDF
  • 5.05 MB
Download

Details

Supervisors
Schaus, Pierre
Faculty
Ecole polytechnique de Louvain
Degree label
Master [120] : ingénieur civil en informatique, à finalité spécialisée
Abstract
The health crisis due to the COVID-19 that we have now been experiencing for over a year has affected over 175 000 000 people and killed over 3 800 000 people around the world so far. Could we have lowered these numbers if we had been able to predict the outbreak of the pandemic accurately? Being able to predict the number of hospitalizations due to COVID-19 in our country accurately would have been very useful in recent months. Indeed, it could have allowed our leaders to take difficult decisions such as announcing a new lockdown more quickly and thus avoid saturation of hospitals before it being too late. This is why we decided to develop an artificial intelligence prediction model based on open data, namely the number of hospitalizations in Belgium (and a few other regions of interest) and Google Trends data. The aim of our work is also to determine to what extent the data collected via Google Trends can help us refine a basic short-term prediction.