مدى قدرة الشبكة العصبونية على محاكاة و التنبؤ بإصابات فيروس كورونا في الجزائر

Abstract EN

Forecasting in pandemics and disasters is one of the means that contribute to reducing the damage of this pandemic, and today, the corona virus is the most dangerous pandemic that the whole world suffers from, the problematic of our study was about : how effective is the neural network methodology in simulating the behavior of new injuries corona virus in Algeria and its prediction, and which training algorithms are the most accurate ? therefore, we divided the study into two parts : in the first section we touched on concepts about the neural network and its training algorithms, and the second section was for an applied study where the various stages of the methodology were applied with its three training algorithms on data represented in new infections of COVID 19 in Algeria from February 25, 2020 to 22 December 2021, and finally we concluded that the neural network methodology based on the LM training algorithm is the most accurate in simulating and predicting serious infections of the corona virus in Algeria.