ABSTRACT
Due to the SARS-COV-2 pandemic, educational institutions are immediately faced with a new challenge to adapt, forcing the transition from face-to-face teaching to distance learning in a short period. Distance education supported by technology is a challenge for educational institutions based on binomial technology/teaching. This paper presents a proposal for an e-learning technology structure, supported by a cluster of servers capable of responding to the requirements of distance learning based on the premises of High Availability, High Performance, Load Balancing. The beginning of this study consisted of a literature review to find the various existing technologies, a way to combine them and create a system capable of providing the necessary functionalities, and whose performance could host all the users of an institution simultaneously. The implemented system results from this combination of technologies and allows its capacity to be scaled at any moment according to momentary needs. In technological terms, the solution was based on a free Linux distribution, the Ubuntu Server installed inside a cluster of servers with VMware ESXi, and a cluster of database nodes based on Gallera technology. The eLearning platform used in this study was Moodle because it is one of the resources most used by institutions. The aspects of teaching, provision of content and execution of evaluation tests, were explored. With the implementation of the presented scenario, it was possible to guarantee the High Availability and load balancing of the platform and guarantee a high performance of the whole solution. © 2022 IEEE.
ABSTRACT
Historically, weather conditions are depicted as an essential factor to be considered in predicting variation infections due to respiratory diseases, including influenza and Severe Acute Respiratory Syndrome SARS-CoV-2, best known as COVID-19. Predicting the number of cases will contribute to plan human and non-human resources in hospital facilities, including beds, ventilators, and support policy decisions on sanitary population warnings, and help to provision the demand for COVID-19 tests. In this work, an integrated framework predicts the number of cases for the upcoming days by considering the COVID-19 cases and temperature records supported by a kNN algorithm. © 2021, ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering.