ABSTRACT
COVID-19 virus named CORONA is a vigorous disease spread all over the world very quickly and creates a pandemic situation to the human beings normal life. As per the doctors and researchers from the laboratory point of view, it will spread to a huge volume when humans are not followed certain principles. Moreover, this disease is easily transferred to neighbors and others in a short period which leads to death. To rectify the remedy for this virus, various spread countries and research peoples are creating the vaccines and some precautionary methods for living hood situation. Recent techniques are used to detect and monitoring the COVID-19- affected person's lifestyle and insisting they take precaution steps for early pre-pandemic life. IoT is a framework that is used to generate data from the human body from the sensors opted for human conditions. Wearable devices have been created with these sensors and communicated with human bodies directly or indirectly. The generated data will send through the server using any connectivity techniques such as Bluetooth or Wi-Fi. Analytics will be done at the server side for taking actions like the human body is affected by the COVID-19 virus or not. Finally, the generated data from a human can continuously store in real time in a cloud server which will be managed as a framework efficiently. This research work proposes a framework for data management in the early detection and monitoring of COVID-19 persons through IoT wearable devices in a pre-pandemic life. The experiments have been done at different zones, and the results are shown symptoms of COVID-19 disease. Parallel work reveals the data management in a cloud server since data have generated continuously in real time and tracking details also stored genuinely. Data management is the typical process in this research because all the data were generated in real time and analytics will be done whenever required. For that large amount of space and effective retrieval technique is required for data extraction. This research work data set is derived from various Internet sources like government web sites and mobile applications, and then, results have displayed the COVID-19 disease details accurately in real time.
ABSTRACT
The coronavirus, one of the deadliest virus erupted in Wuhan, China in December and has claimed millions of lives worldwide and infected too. This virus has off-late demonstrated mutations thus making it difficult for the health professionals to adopt a uniform means of cure. Many people due to lack of support have confined themselves at home. The hospitals too are running short of equipment and support systems. Thus, computational connectivity between the patients at home and the hospitals needs to be established. The objective of this paper is to propose a framework/model that connects all the stakeholders so that either in regular monitoring or in emergency cases help can be provided to them. It has been well established through research and case studies that critical factors associated with this disease are oxygen level (SPO2), pulse rate, fever, chest infection, cough causing choking, and breathlessness. Data shall be collected, stored, and analyzed for the above symptoms and for this cloud storage and blockchain technology would be used. It has been established through various studies that non-clinical techniques like AI and machine learning prove to be effective for the prediction and diagnosis of COVID-19. Using this theory as the standard basis, machine learning models like SVM, Naive Bayes, and decision trees can be used for the analysis, diagnosis, and prediction. Using IoT and its variants, remote monitoring of patient, and consultation can be provided to the patient. Appropriate action would be taken. In addition, a mobile application would enable the patients to gather or read about experiences of other patients. Thus, it would be established through the proposed framework, that an integrated approach of technologies has a great potential in such applications and offers several advantages.
ABSTRACT
SARS-CoV-2 and the consequential COVID-19 virus is one of the major concerns of the 21st century. Pertaining to the novelty of the disease, it became necessary to discover the efficacy of deep learning techniques in the quick and consistent discovery of COVID-19 based on chest X-ray and CT scan image analysis. In this related work, Prognostic tool using regression was designed for patients with COVID-19 and recognizing prediction patterns to make available important prognostic information on mortality or severity in COVID-19 patients. And reliable convolutional neural network (CNN) architecture models (DenseNet, VGG16, ResNet, Inception Net)to institute whether it would work preeminent in terms of accuracy as well as efficiency with image datasets with Transfer Learning. CNN with Transfer Learning were functional to accomplish the involuntary recognition of COVID-19 from numerary chest X-ray and CT scan images. The experimental results emphasize that selected models, which is formerly broadly tuned through suitable parameters, executes in extensive levels of COVID-19 discovery against pneumonia or normal or lung opacity through the precision of up to 87% for X-Ray and 91% intended for CT scans.