Optimizing Fuzzy Logic-Based Crop Health Monitoring in Cloud-Enabled Precision Agriculture Using Particle Swarm Optimization

Abstract

Precision agriculture leverages advanced computing technologies such as the Internet of Things (IoT), cloud computing, and artificial intelligence to enhance crop monitoring and decision-making. However, traditional fuzzy logic-based crop classification systems suffer from suboptimal performance due to manually defined membership functions and rules, leading to inaccurate health assessments. Existing crop health monitoring systems rely on traditional fuzzy logic, which requires manual tuning of membership functions and rules, leading to suboptimal classification accuracy. These methods struggle with handling uncertainty and environmental variations, reducing their adaptability to dynamic agricultural conditions. Additionally, real-time processing and large-scale deployment remain challenging due to computational inefficiencies and limited cloud integration. Addressing these issues necessitates an optimized, scalable, and cloud-enabled approach for accurate and efficient crop health classification. To address this limitation, this study proposes a cloud-enabled Fuzzy Logic-Based Crop Health Monitoring System integrated with Particle Swarm Optimization (PSO) for optimizing fuzzy membership functions and rule parameters. Real-time environmental and soil data collected from IoT sensors (e.g., soil moisture, temperature, humidity, pH) is transmitted to a cloud platform for storage, preprocessing, and analysis. The PSO-optimized fuzzy inference system (FIS) improves classification accuracy, enabling efficient identification of healthy, stressed, or disease-prone crops. The system is deployed in a cloud-based Decision Support System (DSS), providing real-time monitoring, automated alerts, and integration with smart irrigation for timely interventions. Experimental results demonstrate improved classification accuracy (78%), scalability, and energy efficiency, highlighting the system's effectiveness in sustainable precision agriculture.