Theoretical Artificial Intelligence Based on Shannon Entropy to Identify Strains in Covid-19 Pandemic

• Autor: Nieto-Chaupis, Huber
• Formato: artículo
• Fecha de Publicación: 2021
• Institución: Universidad Autónoma del Perú
• Repositorio: AUTONOMA-Institucional
• Lenguaje: inglés
• OAI Identifier: oai:repositorio.autonoma.edu.pe:20.500.13067/1817
• Enlace del recurso: https://hdl.handle.net/20.500.13067/1817; https://doi.org/10.1109/TransAI51903.2021.00016
• Nivel de acceso: acceso restringido
• Materia: COVID-19; Correlation; Pandemics; Entropy; Software; Data models; Proposals; https://purl.org/pe-repo/ocde/ford#2.02.04

Based in the fact that ongoing pandemic is caused by a kind of disorder, this paper employs the concept of Shannon entropy to model data of infections by Covid-19. The usage of this represents a proposal as a type of artificial intelligence that might be used in advanced softwares to perform instantaneous measurements of new infections. The presented theory is applied to the case of UK data, yielding an interesting matching. Therefore, it is seen that waves of pandemics can be explained in terms of apparition of strains and entropy.