Forecasting COVID 19 cases on radiological images using deep learning and VGG model

Non covid patients with pneumonia are first analyzed using Chest-X ray (CXR) radiography. But the diagnosis is difficult when analyzing the features of COVID-19 and pneumonia patients since both are having similar features. During this work we have proposed a hypothesis that deep learning can be useful in distinguishing the X ray mages of COVID-19 and pneumonia. can be used as a first-line triage process for non-COVID-19 patients with other forms of pneumonia. The publicly available dataset of COVID 19 is used from Kaggle for evaluating the performance. We have first analyzed the performance using various machine learning algorithms including SVM, KNN, NB, CART etc. Various features used are color and texture descriptors. By using machine learning algorithms we have obtained the accuracy of 81% for 70% training data and 30% evaluation data. Various versions of deep learning models have been used for foresting of COVID 19. Performance is evaluated using One Block VGG, Two block VG, three block VGG, dropout and transfer learning. Performance of One block VGG is 85% with 30 epochs. To summarize the work, we have introduced the use of deep learning techniques for analysis of COVID 19 from chest X ray images. The system is user friendly and rapid.

Privacy-Preserving Association Rule Mining Considering Multi-objective through an Evolutionary Algorithm

The COVID-19 pandemic has led to an increase in digitization. With the strict social and physical distancing measures in place, new routines require accessing the internet for most online services which have led to the explosive growth of data. As a consequence, data mining technologies are used for the extraction of useful information from a huge compilation of such digital data. Thus, the desire to mine data from varied sources to discover behaviors and patterns among entities such as customers, diseases, and environmental conditions is on the rise which can be accomplished by association rule mining. However, such pattern discovery by association rule mining also discloses the personal information of an individual or organization. Thus, the challenge of association rule mining is privacy preservation wherein confidentiality of sensitive rules should be maintained while releasing the database of third parties. Privacy-preserving association rule mining is the process of modifying the original database to hide the sensitive rules for preserving privacy. Thus, the paper emphasizes multiple objectives like minimizing the side effects of hiding sensitive rules. i.e. reduce the number of ghost rules, lost rules, and hiding failure along with the increase in utility of the data. Copyright © 2022 by the authors.