Deep Learning Detection of COVID-19, Temporal Variation and its Link with Temperature in Nigeria
Ebiendele Eromosele Precious *
Department of Meteorology and Climate Science, Federal University of Technology, Akure, Nigeria.
*Author to whom correspondence should be addressed.
Abstract
COVID-19 was announced as a global pandemic on 11 March 2020 by the World Health Organization due to its spread globally. Nigeria recorded its first case on 27 February 2020. Since then, it has spread to all parts of the country. In this paper we study the effectiveness and skill performance of deep learning architectures in assisting health workers in detecting COVID-19 infected patient through X-ray images. Analytical deductions obtained from 500 X-ray images of both infected and non-infected patients confirmed that our proposed model InceptionV3 is effective in detecting COVID-19 and attain an average accuracy of 92%. The relationship or link between the COVID-19 daily occurrence and two meteorological variables (minimum and maximum temperatures) are further assessed. The result also indicated that the cases recorded in Wednesdays and Fridays are observed to be higher than other days which usually coincide with either religious activities or market days in the country, while a progressively decline in weekday cases is observed towards the weekend with Sundays (ranging from 152 to 280 cases) having the lowest cases. The study further indicated statistically that COVID-19 daily cases significantly decline when maximum and minimum temperature are increasing (-0.79 and -0.44 correlation coefficient).
Keywords: Deep learning, artificial intelligence, COVID-19, X-ray images, VGG19 and Inceptionv3.