ABSTRACT
To understand and approach the spread of the SARS-CoV-2 epidemic, machine learning offers fundamental tools. This study presents the use of machine learning techniques for projecting COVID-19 infections and deaths in Mexico. The research has three main objectives: first, to identify which function adjusts the best to the infected population growth in Mexico; second, to determine the feature importance of climate and mobility; third, to compare the results of a traditional time series statistical model with a modern approach in machine learning. The motivation for this work is to support health care providers in their preparation and planning. The methods compared are linear, polynomial, and generalized logistic regression models to describe the growth of COVID-19 incidents in Mexico. Additionally, machine learning and time series techniques are used to identify feature importance and perform forecasting for daily cases and fatalities. The study uses the publicly available data sets from the John Hopkins University of Medicine in conjunction with the mobility rates obtained from Google's Mobility Reports and climate variables acquired from the Weather Online API. The results suggest that the logistic growth model fits best the pandemic's behavior, that there is enough correlation of climate and mobility variables with the disease numbers, and that the Long short-term memory network can be exploited for predicting daily cases. Given this, we propose a model to predict daily cases and fatalities for SARS-CoV-2 using time series data, mobility, and weather variables.
ABSTRACT
Research universities have a strong devotion and advocacy for research in their core academic mission. This is why they are widely recognized for their excellence in research which make them take the most renowned positions in the different worldwide university leagues. In order to examine the uniqueness of this group of universities we analyze the scientific production of a sample of them in a 5 year period of time. On the one hand, we analyze their preferences in research measured with the relative percentage of publications in the different subject areas, and on the other hand, we calculate the similarity between them in research preferences. In order to select a set of research universities, we studied the leading university rankings of Shanghai, QS, Leiden, and Times Higher Education (THE). Although the four rankings own well established and developed methodologies and hold great prestige, we choose to use THE because data were readily available for doing the study we had in mind. Having done that, we selected the twenty academic institutions ranked with the highest score in the last edition of THE World University Rankings 2020 and to contrast their impact, we also, we compared them with the twenty institutions with the lowest score in this ranking. At the same time, we extracted publication data from Scopus database for each university and we applied bibliometrics indicators from Elsevier's SciVal. We applied the statistical techniques cosine similarity and agglomerative hierarchical clustering analysis to examine and compare affinities in research preferences among them. Moreover, a cluster analysis through VOSviewer was done to classify the total scientific production in the four major fields (health sciences, physical sciences, life sciences and social sciences). As expected, the results showed that top universities have strong research profiles, becoming the leaders in the world in those areas and cosine similarity pointed out that some are more affine among them than others. The results provide clues for enhancing existing collaboration, defining and re-directing lines of research, and seeking for new partnerships to face the current pandemic to find was to tackle down the covid-19 outbreak.