Robust Self-Supervised Deep Learning for Real-Time Aerial Object Detection Under Low-Visibility Conditions

Abstract:
In order to improve healthcare diagnostics using intelligent, affordable, and sustainable technologies, this study proposes an AI-driven deep learning architecture. The suggested model efficiently analyses complicated medical pictures to increase the accuracy of early illness diagnosis by using transformer-based architectures and convolutional neural networks (CNNs). Automation as well as data-driven intelligence work together to provide quick and accurate diagnostic procedures, which helps achieve SDG 3 (Good Health while Well-Being) by improving healthcare results. Additionally, by encouraging technological innovation and promoting smart healthcare ecosystems, the integration of sophisticated AI models inside healthcare infrastructure is consistent towards SDG 9 (Industry, Innovation, as well as Infrastructure).In order to fulfil SDG 10 (Reduced Inequalities), the framework also places a strong emphasis on fair utilisation of AI-based diagnostic tools. All things considered, this study shows how sustainable AI innovation may revolutionise international healthcare systems and enhance inclusive health.