Optimizing Energy and Time for Powered Rapid and Accurate COVID-۱۹ Patients Detection

The healthcare systems have been greatly affected by the COVID-۱۹ pandemic highlighting the need for accurate diagnosis of COVID-۱۹ patients. This study focuses on using chest X-rays to achieve this goal. The researchers suggest utilizing CNN models, a form of intelligence to automate the diagnostic process. While an initial model showed accuracy (۹۹.۰%), issues with data quality were noted. To overcome this, they implemented techniques such as data balancing, expert evaluation, and data enhancement. These enhancements resulted in a final model. The researchers investigated the use of CNNs to detect COVID-۱۹ from chest X-rays automatically. Despite a high accuracy rate (۹۹.۰%), refinements were made due to identified limitations. Through model optimization, significant performance improvements were achieved. Early and precise diagnosis of COVID-۱۹ is crucial. Chest X-ray data poses challenges for machine learning models. Lightweight CNNs provide a solution for automated detection, with enhanced data quality through processing techniques. Determining the number of layers is essential to prevent overfitting, which was addressed by the researchers leading to model enhancement. This study emphasizes the significance of development and optimization to maximize machine learning model performance

کلیدواژه ها:

COVID-۱۹ Classification ، X-Ray Image ، CNN