Machine Learning Techniques in Service of COVID-19: Data Augmentation Based on Multi-Exposure Image FusionTowards Anomaly Prediction

SARS-CoV-2, the novel coronavirus that causes COVID-19, has wreaked havoc worldwide, with patients displaying a wide range of difficulties that have prompted healthcare professionals to look for innovative technology solutions and treatment methods. The COVID-19 problem is better understood and mana...

Full description

Saved in:
Bibliographic Details
Published in2022 4th International Conference on Current Research in Engineering and Science Applications (ICCRESA) pp. 54 - 58
Main Authors Alzamli, Zainab, Danach, Kassem, Frikha, Mondher
Format Conference Proceeding
LanguageEnglish
Published IEEE 20.12.2022
Subjects
Computer architecture
Computers
COVID-19
Data Augmentation
Deep learning
Human intelligence
Machine Learning
Medical services
Multi-exposure Image
Organizations
Online AccessGet full text

Cover

More Information
Summary:SARS-CoV-2, the novel coronavirus that causes COVID-19, has wreaked havoc worldwide, with patients displaying a wide range of difficulties that have prompted healthcare professionals to look for innovative technology solutions and treatment methods. The COVID-19 problem is better understood and managed thanks to machine learning approaches. Machine learning enables computers to mimic human intelligence and digest massive volumes of data to identify patterns and insights quickly. In the fight against COVID-19, organizations have been quick to use machine-learning skills in various ways, including enhancing consumer messaging, better understanding how COVID-19 spreads, and accelerating research and treatment. In this study, we aim to use deep learning techniques to predict COVID-19-affected people. A data augmentation stage is taken into consideration based on multi-exposure image fusion. Our dataset consists of chest X-ray images of COVID-19-afflicted persons and ordinary people.
DOI:10.1109/ICCRESA57091.2022.10352482