Back to Search Start Over

Machine learning-based IoT system for COVID-19 epidemics.

Authors :
Arowolo, Micheal Olaolu
Ogundokun, Roseline Oluwaseun
Misra, Sanjay
Agboola, Blessing Dorothy
Gupta, Brij
Source :
Computing; Apr2023, Vol. 105 Issue 4, p831-847, 17p
Publication Year :
2023

Abstract

The planet earth has been facing COVID-19 epidemic as a challenge in recent time. It is predictable that the world will be fighting the pandemic by taking precautions steps before an operative vaccine is found. The IoT produces huge data volumes, whether private or public, through the invention of IoT devices in the form of smart devices with an improved rate of IoT data generation. A lot of devices interact with each other in the IoT ecosystem through the cloud or servers. Various techniques have been presented in recent time, using data mining approach have proven help detect possible cases of coronaviruses. Therefore, this study uses machine learning technique (ABC and SVM) to predict COVID-19 for IoT data system. The system used two machine learning techniques which are Artificial Bee Colony algorithm with Support Vector Machine classifier on a San Francisco COVID-19 dataset. The system was evaluated using confusion matrix and had a 95% accuracy, 95% sensitivity, 95% specificity, 97% precision, 96% F1 score, 89% Matthews correlation coefficient for ABC-L-SVM and 97% accuracy, 95% sensitivity, 100% specificity, 100% precision, 97% F1 score, 93.1% Matthews correlation coefficient for ABC-Q-SVM. In conclusion, the system shows that the process of dimensionality reduction utilizing ABC feature extraction techniques can boost the classification production for SVM. It was observed that fetching relevant information from IoT systems before classification is relatively beneficial. [ABSTRACT FROM AUTHOR]

Details

Language :
English
ISSN :
0010485X
Volume :
105
Issue :
4
Database :
Complementary Index
Journal :
Computing
Publication Type :
Academic Journal
Accession number :
162544569
Full Text :
https://doi.org/10.1007/s00607-022-01057-6