Paper Title
INTELLIGENT AGRICULTURAL SYSTEM USING MODIFIED CONVOLUTIONAL NEURAL NETWORK IN IoT

Abstract
Abstract - Plant disease monitoring in agriculture using automation by leveraging a Modified Convolutional Neural Network (MCNN) and Raspberry Pi technology. The system integrates advanced image recognition techniques for plant disease detection, providing more accurate and efficient means of identifying potential crop ailments. The MCNN is trained on a diverse dataset, enhancing its ability to recognize subtle variations in plant health indicators. The core of the system is implemented on the Raspberry Pi, a versatile and cost-effective computing platform. The Raspberry Pi processes the image data locally, enabling real-time disease identification without relying on external servers. This ensures rapid response times and increased autonomy for the Intelligent Agriculture system. Intelligent agriculture system, equipped with sensors for soil moisture, pH levels, and temperature, collaborates with the MCNN to make informed decisions regarding irrigation, fertilization, and pest control. The Raspberry Pi's GPIO pins control actuators such as water pumps and pesticide sprayers, enabling precise and timely interventions. This research contributes to the evolution of precision agriculture, offering an innovative solution that combines state-of-the-art CNN technology, the affordability of Raspberry Pi, and the efficiency of agriculture automation. The MCNN-Based Plant Disease Monitoring and Intelligent agriculture system promises to revolutionize farming practices, improving crop yield, minimizing resource usage, and empowering farmers with data-driven insights for sustainable and productive agriculture. Keywords - MCNN, Intelligent Agriculture System, Raspberry Pi, Internet of Things (IoT)