No abstract

No abstract

The fast spread of Coronavirus (COVID-19) poses a huge risk to people all around the world. Recently, COVID-19 testing kits have been unavailable due to rise in effected people and large demand of tests. Keeping the urgency of the situation in mind, an automatic diagnosis method for early detection of COVID-19 is needed. The proposed deep learning decision support system (DSS) for COVID-19 employs MobileNet v2 Deep learning (DL) model for effective and accurate detection. Here we collected Cough auscultations through self-designed digital sensor. The primary experimental results show that the maximum accuracy for training is around 99.91%, and the maximum accuracy for validation is 98.61%, with 97.5% precision, 98.5%recall, and 98% F1-score. The Deep Learning-based model described here strives for similar performance to medical professionals and can help pulmonologist/radiologists increase their working productivity.

Cognitive Radio (CR) is an emerging and promising technology which is predicted to solve the problem of spectrum shortage by utilization of the spectrum efficiently by exploiting the licensed spectrum white spaces. Video on demand (VoD) is a very popular present day service. It is a well-known fact, that video on demand internet service needs a large amount of bandwidth. CR WMNs is envisaged to provide the much needed bandwidth for video streaming as CR WMNs has the ability to access a large part of the under-utilized licensed spectrum. In CR WMNs interference is a critical issue which degrades cognitive radio wireless mesh networks (CR WMNs) performance. As the number of users rises, interference also increases resulting in low throughput. In this paper first an analytical model for CR WMNs has been presented. We have also presented an efficient VoD model and an optimizing approach which minimizes interference to provide a much needed higher network capacity to VoD services. Simulation results show effectiveness of our proposed approach as there is an increase in the number of concurrent VoD sessions.

No abstract