Zhang, T.L. and Lin, G. (2020) Generalized k-Means in GLMs with Applications to the Outbreak of COVID-19 in the United States. Computational Statistics & Data Analysis, 159, 107217.
https://doi.org/10.1016/j.csda.2021.107217

has been cited by the following article:

• TITLE: Fighting against COVID-19: Who Failed and Who Succeeded?

  AUTHORS: Hussein Baalbaki, Hassan Harb, Ali Jaber, Chamseddine Zaki, Chady Abou Jaoude, Kifah Tout, Layla Tannoury

  KEYWORDS: COVID-19, Data Clustering and Prediction, Co-Means, ANOVA, LSTM, Prophet

  JOURNAL NAME: Journal of Computer and Communications, Vol.10 No.4, April 15, 2022

  ABSTRACT: Recently, governments and public authorities in most countries had to face the outbreak of COVID-19 by adopting a set of policies. Consequently, some countries have succeeded in minimizing the number of confirmed cases while the outbreak in other countries has led to their healthcare systems breakdown. In this work, we introduce an efficient framework called COMAP (COrona MAP), aiming to study and predict the behavior of COVID-19 based on deep learning techniques. COMAP consists of two stages: clustering and prediction. The first stage proposes a new algorithm called Co-means, allowing to group countries having similar behavior of COVID-19 into clusters. The second stage predicts the outbreak’s growth by introducing two adopted versions of LSTM and Prophet applied at country and continent scales. The simulations conducted on the data collected by WHO demonstrated the efficiency of COMAP in terms of returning accurate clustering and predictions.