A Novel Approach to IoT Based Plant Health Monitoring System Based on MLR-RBF Approach

New plant diseases are appearing as a result of pests, climate change, and infections; these diseases pose a risk to ecosystems and human health and reduce agricultural output. In light of these challenges, this research introduces an Internet of Things (loT)-based plant health monitoring system that reduces crop output losses caused by biotic and abiotic stresses, detects and tracks plant illnesses in real time using advanced sensor technologies, and generally improves plant health. The application of wearable technology in agricultural and plant research is in its early stages, in contrast to the fast advancements in these fields for human health monitoring. The proposed approach makes use of Internet of Things (loT) sensors, preprocessing of machine learning pipelines, image alignment, background removal, and automated feature extraction to identify disease-specific characteristics. Training an MLR-RBF model is contrasted with training an MLR or RBF model independently. In terms of plant disease classification, the combined model achieves a superior performance of 95.30% according to the experimental data. Rapid, accurate, and efficient disease detection is possible with loT-based plant health monitoring, according to this research, which improves crop management and supports sustainable agriculture.