Ensemble Deep Learning for IoT Based COVID 19 Health Care Pollution Monitor

作     者：Nithya Rekha Sivakumar 

作者机构：Department of Computer SciencesCollege of Computer and Information SciencesPrincess Nourah Bint Abdulrahman UniversityRiyadh11671Saudi Arabia 

出 版 物：《Intelligent Automation & Soft Computing》 (智能自动化与软计算（英文）)

年 卷 期：2023年第35卷第2期

页      面：2383-2398页

核心收录：

学科分类：12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 081104[工学-模式识别与智能系统] 08[工学] 0835[工学-软件工程] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：supported by Princess Nourah bint Abdulrahman University Researchers Supporting Project number(PNURSP2022R194) Princess Nourah bint Abdulrahman University,Riyadh,Saudi Arabia 

主　　题：Internet of Things Covid-19 ensemble deep learning framingham feature extraction 

摘      要：Internet of things(IoT)has brought a greater transformation in health-care sector thereby improving patient care,minimizing treatment *** pre-sent method employs classical mechanisms for extracting features and a regression model for *** methods have failed to consider the pollu-tion aspects involved during COVID 19 *** Ensemble Deep Learning and Framingham Feature Extraction(FFE)techniques,a smart health-care system is introduced for COVID-19 pandemic disease *** Col-lected feature or data via predictive mechanisms to form pollution *** maps are used to implement real-time countermeasures,such as storing the extracted data or feature in a Cloud server to minimize concentrations of air *** integrated with patient management systems,this solution would minimize pollution emitted via patient’s sensors by offering spaces in the cloud server when pollution thresholds are ***,the Gini Index factor infor-mation gain technique eliminates unimportant and redundant attributes while selecting the most relevant,reducing computing overhead and optimizing system ***,the COVID-19 disease prognosis ensemble deep learning-based classifier is *** analysis is planned to measure the prediction accuracy,error,precision and recall for different numbers of *** results show that prediction accuracy is improved by 8%,error rate was reduced by 47%and prediction time is minimized by 36%compared to exist-ing methods.