ABSTRACT
Recently, the individuals are under lockdown and limited mobility due to the random spreading of the COVID-19, i.e., coronavirus disease - 2019, worldwide as well as pandemic declared by the World Health Organization (WHO). RT-PCR, i.e., reverse transcriptase-polymerase chain reaction, tests that can detect the RNA from nasopharyngeal swabs have become the norm to allow people to travel within the nation and also to international destinations. This test is people-intensive, i.e., it involves a person collecting the sample, needs transportation with strict precautionary measures, and a lab technician to perform the test which may take up to 2 days to get the results. There is a lot of inconvenience to the people due to this process. Alternatively, X-Ray images have been used primarily by physicians to detect COVID-19 and its severity. Detection of COVID-19 through X-Ray can act as a safe, faster, and alternative method to RT-PCR tests. This method uses a Convolutional Neural Network (CNN) to classify the X-Ray scans into two categories, i.e., COVID-19 positive and negative. In this paper, a novel method named COVIHunt: an intelligent CNN-based COVID-19 detection technique using CXR imaging, is proposed for binary classification. From experiments, it is observed that the proposed work outperforms in comparison with other existing techniques. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
ABSTRACT
Since the Coronavirus (COVID19) pandemic, all activities have been held digitally, necessitating the surveillance of guests' real-time attendance. Previously, online attendance included getting the list of attendees, which was inconvenient because many people chose to keep silent or leave the meeting completely. As a result, a technique for collecting attendance using facial recognition that can correctly identify participants who remain online for the duration of the lecture is required. The goal of this work is to develop a system named IOSTS, an intelligent online attendance tracking system, that can track attendance while using minimum bandwidth and maintaining user privacy. This proposed work is based on the concepts of facial recognition and edge computing. The entire utility will be run on the client's PC. From random experiments, it is observed that achieving an accuracy of 98 % in facial recognition. This new approach is a foolproof method of tracking attendance and increasing digital transparency. © 2022, Ismail Saritas. All rights reserved.
ABSTRACT
Healthcare is a human right that must be accessible to all disregarding the social or economic conditions of any human being. The burden on healthcare system has increased immensely in the last few months. The COVID19 pandemic has brought to the fore gaps in the healthcare system world over. The doctors and front-line workers are directly getting exposed to the virus and patients that might need other healthcare services are vulnerable to the exposure. These problems would be catered by the proposed device as it would be operated by the patients and the real time data can be collected by the doctors to assess the vital body parameters through cloud without being physically present in the same environment. The parameters that can be monitored are body temperature, pulse rate, and oxygen saturation level. Hence, the proposed device includes sensors for measuring the body temperature (i.e. LM35) and pulse and oxygen level (i.e. MAX30100). The experimental setup has been built using Android based Blynk Cloud Platform where data is collected from remote places and stored the cloud. It is further available for assessment by the healthcare professionals. © 2021 IEEE.
ABSTRACT
An extremely infectious disease, coronavirus disease 2019 (COVID-19) nowadays, is continuously threatening the whole world by its omnidirectional spreading. The aggressiveness and impact of COVID-19 disease worldwide have made the World Health Organization (WHO) to declare it as global pandemic. Machine learning (ML), an application of AI, can be implemented efficiently to track COVID-19, predict the increase of the pandemic, and design approaches to limit its spread. In this paper, three ML regression techniques, namely linear regression, polynomial regression, and support vector regression, are used to propose a model. Some experiments are performed on the online time series data from the dashboard of Johns Hopkins University sourced from Github repository using Python language to predict the affected people in the next 60 days. This article will help out in creating awareness among people toward the prevention of spread of infection due to COVID-19. © 2021, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.