Engineering Technology & Applied Science Research, Год журнала: 2025, Номер 15(2), С. 20953 - 20958
Опубликована: Апрель 3, 2025
Rapid and accurate detection of COVID-19 from medical images, such as X-rays CT scans, is critical for timely diagnosis treatment. This paper presents an innovative approach that combines Super-Resolution Generative Adversarial Network (SRGAN) image enhancement with optimized MobileNetV3-Small model to achieve efficient high-accuracy classification. The proposed method significantly reduces computational complexity while maintaining performance. Specifically, the achieves 99.5% accuracy X-ray images 99.8% only ~0.8M parameters ~2.5 MB memory usage, making it highly suitable real-time web applications in resource-constrained environments. Comparative analysis related works demonstrates outperforms other models terms accuracy, efficiency, lightweight design. results highlight potential a practical solution rapid detection, contributing development accessible scalable diagnostic tools.
Язык: Английский