Low-cost Prevention of the Spread of Viral Diseases Using Neural Networks

Abstract

Research background: Globalization has both positive and negative consequences. For more than a year, the whole world has been feeling very strongly about one of the negative consequences of globalization. And that is the rapid spread of infectious diseases. Within a few months of the first COVID 19 diseases, a pandemic occurred. The most common symptoms of this disease are fever, muscle aches, fatigue, loss of appetite and difficulty breathing. Therefore, it is essential to control body temperature reliably. If the process of temperature monitoring takes place in closed spaces, and simultaneously, the identification of a person is necessary, we propose a low-cost solution. This consists of using a mobile device in combination with a thermal camera for capturing people and subsequent evaluation using classification methods. Purpose of the article: The aim of this article is to create a model of a system for self-shooting. Follows recognition of elevated body temperature of persons and their identification to reduce the global impact of COVID-19 on the economy and society. Methods: A mobile device (tablet) combined with a thermal camera is used as a sensor. This is followed by face detection in both visible and thermal images. Methods of artificial intelligence (convolutional neural networks) are used for subsequent classifications of individual persons. Findings & Value added: The proposed model of self-sensing and subsequent identification of persons and their classification into groups (increased body temperature, normal temperature). In places where it is necessary to identify people, the system also detects elevated body temperature. This will help fight the spread of infectious diseases, which are characterized by fever.