CHMP-CNN: To Implement the IoT Based Crops Health Monitoring and Prediction Using Deep Learning

Agriculture is entering a new era marked by the Internet of Things (IoT), which is completely changing how we monitor and manage crops. The adoption of remote monitoring and control has resulted in reduced operational expenses and increased production. The significance of agriculture in maintaining human existence makes it necessary to adopt technical innovations to guarantee its effectiveness and sustainability. This research provides a novel approach to IoT-based smart agriculture that addresses multiple agricultural characteristics and maximizes crop productivity. The sophisticated network of sensors that make up the hardware part of the proposed system includes the DHT11 temperature and humidity sensor, raindrop sensors that sense the presence of rain, ultrasonic sensors that monitor water level, and the ESP32-CAM wireless image transmission sensor. Real-time data gathering and analysis are made possible by the combination of these sensors and the Arduino Mega processing unit. In the proposed model uses chili plant disease dataset and apply a convolutional neural network on which tune the performance and improve the accuracy more than the traditional existing model. The software component for plant disease identification uses Convolutional Neural Network (CNN) techniques to improve farmers' predictive analytics and decision-making.