Abstract
<jats:p>Low-cost, edge-computing IoT nodes placed in agricultural areas are integrated into the GAIS architecture. High-resolution cameras and environmental sensors (which track temperature, humidity, and soil moisture) are used to strengthen these nodes. Data is continuously gathered and sent to a central cloud platform, mostly leaf photos. A specially trained KSK (Kutubuddin S. Kazi) Approach, which is ideal for identifying and categorizing dominant illnesses (such as wilt, Pomegranate bacterial blight, and Jawar leaf blight) is the fundamental intelligence. Following classification, the system makes use of a proprietary, rules-based expert system that quickly produces calibrated treatment protocols that take into account the disease stage, environmental factors, and viable fungicide/pesticide substitutes. According to preliminary testing, the GAIS greatly outperforms manual detection techniques in terms of speed and consistency, achieving a disease classification accuracy of over 96%.</jats:p>