COVID-19 has infected more than 68 million people worldwide since it was first detected about a year ago. Machine learning time series models have been implemented to forecast COVID-19 infections. In this paper, we develop time series models for the Gulf Cooperation Council (GCC) countries using the public COVID-19 dataset from Johns Hopkins. The dataset set includes the one-year cumulative COVID-19 cases between 22/01/2020 to 22/01/2021. We developed different models for the countries under study based on the spatial distribution of the infection data. Our experimental results show that the developed models can forecast COVID-19 infections with high precision.
翻译:自一年前首次发现COVID-19以来,全世界已有6 800多万人感染了COVID-19。机器学习时间序列模型已经用于预测COVID-19感染情况。在本文件中,我们利用约翰·霍普金斯的公共COVID-19数据集,为海湾合作委员会(海合会)国家开发了时间序列模型。数据集包括从22/01/2020年至22/01/2021年的一年累计COVID-19病例。我们根据感染数据的空间分布,为正在研究的国家开发了不同的模型。我们的实验结果显示,开发的模型可以非常精确地预测COVID-19感染情况。</s>