| Autor: |
Punitha, S., Al-Turjman, Fadi, Stephan, Thompson |
| Předmět: |
|
| Zdroj: |
Journal of Experimental & Theoretical Artificial Intelligence; Oct2024, Vol. 36 Issue 7, p1101-1119, 19p |
| Abstrakt: |
Accurate and early diagnosis of COVID-19 can reduce the mortality rate caused by the disease across the globe. Computer-aided diagnosis (CAD) helps radiologists efficiently extract and diagnose the abnormal portions. The healthcare market is currently experiencing rapid development owing to the Internet of Things (IoT). This paper proposes a framework that integrates machine learning and intelligence-based e-Health service systems that can be used as an application of the Internet of Medical Things (IoMT) for the early diagnosis of COVID-19 disease. This framework consists of a classification approach for diagnosing the abnormalities in lung CT images using a whale optimisation algorithm (WOA) optimised wavelet neural network (WNN). WOA optimises the input features, initial weights, hidden nodes, momentum constant, and learning parameters of a WNN in the proposed system. The proposed approach extracts the Laws 16 Texture Energy Measures (LTEM) from the preprocessed CT lung images and classifies the abnormal regions with the help of a WNN classifier. The proposed framework is evaluated using a publicly available COVID-19 dataset that contains both theCOVID-19 and non-COVID-19 cases. The result shows that theproposed approach has a sensitivity of 82%, a specificity of 73.3%, and an accuracy of 84.8%. [ABSTRACT FROM AUTHOR] |
| Databáze: |
Complementary Index |
| Externí odkaz: |
|
