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.
ABSTRACT
In recent times, COVID-19, has a great impact on the healthcare sector and results in a wide range of respiratory illnesses. It is a type of Ribonucleic acid (RNA) virus, which affects humans as well as animals. Though several artificial intelligence-based COVID-19 diagnosis models have been presented in the literature, most of the works have not focused on the hyperparameter tuning process. Therefore, this paper proposes an intelligent COVID-19 diagnosis model using a barnacle mating optimization (BMO) algorithm with a cascaded recurrent neural network (CRNN) model, named BMO-CRNN. The proposed BMO-CRNN model aims to detect and classify the existence of COVID-19 from Chest X-ray images. Initially, pre-processing is applied to enhance the quality of the image. Next, the CRNN model is used for feature extraction, followed by hyperparameter tuning of CRNN via the BMO algorithm to improve the classification performance. The BMO algorithm determines the optimal values of the CRNN hyperparameters namely learning rate, batch size, activation function, and epoch count. The application of CRNN and hyperparameter tuning using the BMO algorithm shows the novelty of this work. A comprehensive simulation analysis is carried out to ensure the better performance of the BMO-CRNN model, and the experimental outcome is investigated using several performance metrics. The simulation results portrayed that the BMO-CRNN model has showcased optimal performance with an average sensitivity of 97.01%, specificity of 98.15%, accuracy of 97.31%, and F-measure of 97.73% compared to state-of-the-art methods.
ABSTRACT
BACKGROUND: Physical exercise programs are required to improve students' physical ability, physical fitness, self-responsibility, and satisfaction to remain physically active for a lifetime. The supporting system's demanding characteristics include lack of school leadership support, and lack of communication skills among students is considered an essential factor in the physical education system. OBJECTIVE: In this paper, an Internet of Things (IoT)-based intelligent physical support framework (IoT-IPSF) has been proposed to encourage education leadership and student social interaction in the physical education system. METHOD: Training service analysis is introduced to improve adequate leadership support, helping in the physical education system's growth. Self-determination analysis is integrated with IoT-IPSF to enhance effective communication among school teachers, educational experts, and curriculum officers in the physical education system. RESULTS: The simulation results show that the proposed method achieves a high accuracy ratio of 98.7%, an efficiency ratio of 95.6, student performance 97.8%, fitness level 82.3%, activity involvement 94.5% compared to other existing models.
