ABSTRACT
Globally, millions of people were affected by the Corona-virus disease-2019 (COVID-19) causing loads of deaths. Most COVID-19 affected people recover in a few spans of weeks. However, certain people even those with a milder variant of the disease persist in experiencing symptoms subsequent to their initial recuperation. Here, a novel Block-Chain (BC)-assisted optimized deep learning algorithm, explicitly improved dragonfly algorithm based Deep Neural Network (IDA-DNN), is proposed for detecting the different diseases of the COVID-19 patients. Initially, the input data of the COVID-19 recovered patients are gathered centered on their post symptoms and their data is amassed as a BC for rendering security to the patient's data. After that, the disease identification of the patient's data is performed with the aid of system training. The training includes '4' disparate datasets for data collection, and then, performs preprocessing, Feature Extraction (FE), Feature Reduction (FR), along with classification utilizing ID-DNN on the gathered inputted data. The IDA-DNN classifies '2' classes (presence of disease and absence of disease) for every type of data. The proposed method's outcomes are examined as well as contrasted with the other prevailing techniques to corroborate that the proposed IDA-DNN detects the COVID-19 more efficiently.