Related Experiment Video
Updated: Oct 5, 2025
04:17
DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning
Published on: May 10, 2024
938
A framework of genetic algorithm-based CNN on multi-access edge computing for automated detection of COVID-19
Md Rafiul Hassan1, Walaa N Ismail2, Ahmad Chowdhury3
1College of Arts and Sciences, University of Maine at Presque Isle, Presque Isle, ME04769 USA.
The Journal of Supercomputing
|January 26, 2022
Summary
A new framework using artificial intelligence, specifically convolutional neural networks (CNN) and genetic algorithms (GA), accurately detects COVID-19 from X-rays. This computational intelligence approach offers rapid diagnosis, aiding healthcare during surges.
Area of Science:
- Medical Imaging Analysis
- Computational Intelligence
- Artificial Intelligence in Healthcare
Background:
- Standard COVID-19 testing (RT-PCR) is time-consuming, and expert radiologists are scarce, delaying treatment for severe cases.
- Hospitals face immense pressure during infection peaks, with shortages of beds, testing kits, and staff.
- Accurate and rapid COVID-19 detection is crucial for timely treatment and mitigating disease transmission.
Purpose of the Study:
- To design and develop a computational intelligence-based framework for rapid and accurate COVID-19 detection using chest X-ray images.
- To integrate multi-access edge computing and 5G technology for accessible, cloud-based CNN resource utilization.
- To address the challenge of optimal hyperparameter selection for efficient CNN models in COVID-19 detection.
Main Methods:
- Development of a novel Convolutional Neural Network (CNN) model integrated with a Genetic Algorithm (GA) for hyperparameter optimization.
- Utilization of multi-access edge computing (MEC) and 5G technology to enable cloud-based access to the CNN detection tool via 5G devices.
- Training and testing the framework on raw chest X-ray images for automated COVID-19 classification.
Main Results:
- The developed framework achieved a high accuracy of 98.48% in classifying COVID-19 positive X-ray images.
- The proposed CNN-GA model demonstrated superior performance compared to existing studies in COVID-19 detection.
- The framework enables rapid, automated detection of COVID-19, accessible through 5G-enabled devices.
Conclusions:
- Computational intelligence, specifically the CNN-GA framework, offers a highly accurate and rapid solution for COVID-19 detection from X-rays.
- The integration of MEC and 5G technology enhances accessibility and efficiency of AI-driven diagnostic tools.
- This approach can serve as a valuable emergency measure alongside traditional testing, improving patient outcomes and public health responses.