ABSTRACT
The outburst of the coronavirus is in the phase of development due to lack of precise diagnosis needed by patients. Because the virus spreads quickly from a corona positive individual to the others, the health of any area that is densely inhabited is quite important. Presently, medical community has reached a disaster level since the number of cases are rising very fast and the medical facilities are very limited. Therefore, it is high time that an intelligent model is conceived and developed for monitoring the symptoms of patient health online, then estimate and find the anomaly in the health status of patient further. By assessing the tracked health parameters in this way, a corona virus-infected patient's health condition may be analysed using a well-adapted prediction model. In this study, an overview on the benchmark approaches utilized in recent remote monitoring in covid 19 diagnosis studies is provided where the different algorithms are elucidated and the comparison between the advantages is performed. Also, the problems and drawbacks that covid 19 diagnosis research encounters commonly is discussed. On the whole, this article comprehensively delves into the field of automated remote monitoring in covid 19 diagnosis and also the future research endeavors in this field are put forward. Copyright © 2022 Authors. All rights reserved.
ABSTRACT
Illness due to infectious diseases has been always a global threat. Millions of people die per year due to COVID-19, pneumonia, and Tuberculosis (TB) as all of them infect the lungs. For all cases, early screening/diagnosis can help provide opportunities for better care. To handle this, we develop an application, which we call MobApp4InfectiousDisease that can identify abnormalities due to COVID-19, pneumonia, and TB using Chest X-ray image. In our MobApp4InfectiousDisease, we implemented a customized deep network with a single transfer learning technique. For validation, we offered in-depth experimental study and we achieved, for COVID-19-pneumonia-TB cases, accuracy of 97.72%196.62%199.75%, precision of 92.72%1100.0%199.29%, recall of 98.89%188.54%199.65%, and F1-score of 95.00%194.00%199.00%. Our results are compared with state-of-the-art techniques. To the best of our knowl-edge, this is the first time we deployed our proof-of-the-concept MobApp4InfectiousDisease for a multi-class infec-tious disease classification. © 2022 IEEE.
ABSTRACT
Artificial intelligence has developed in recent years. It is mostly enviable to discover the facility of contemporaneous state-of-the-art techniques and to examine lung nodule features in terms of a large population. Now a days lung plays a major role all over the world in early prevention in disease identification. The latest progress of deep learning sustains the recognition and categorization of medical images of respiratory problems. There are varieties of lung diseases to be analyzed to select the high mortality rate among them. In this paper, we have provided a comprehensive study of several lung ailments, in particular lung cancer, pneumonia, and COVID-19/SARS, Chronic Obstructive Pulmonary Disease. Existing deep learning methodology used to diagnose lung diseases are clearly explained and it will be helpful for the lung disease identify the system. © 2022, IFIP International Federation for Information Processing.