A SYSTEMATIC REVIEW OF EDGE COMPUTING FOR SUGARCANE DISEASE DIAGNOSIS

Abstract

Timely disease identification and control are crucial for sugarcane agricultural output, which is a vital crop for economic growth in developing nations like India. Traditional disease detection techniques, however, have drawbacks including slow reaction times, large processing requirements, and reliance on centralized cloud systems—which might be sluggish and constrained by connectivity problems in remote locations.With an emphasis on real-time data collection, processing, and analysis using IoT, Artificial Intelligence (AI), and edge-fog-cloud architectures, this study examines developments in early disease detection throughout the phenological phases of sugarcane utilizing edge computing. Our research shows that algorithmic methods, especially CNN-based deep learning models incorporated into edge computing frameworks, greatly lower latency and processing cost while achieving over 90% illness detection accuracy.The study also shows how edge computing might revolutionize preventative therapies by identifying possibilities in real-time IoT connections and lightweight model modifications for early illness identification. The resilience and sustainability of sugarcane farming in resource-constrained locations are improved by this strategy, which closes important gaps in scalability, cost-efficiency, and accessibility.