IoT-Based Convolutional Neural Networks in a Farm Pest Detection Using Transfer Learning
摘要
In this study explores agriculture pest detection using transfer learning with IoT devices, evaluating VGG16, VGG19, Inception, and Xception CNN architectures with the agripest dataset. VGG16 and VGG19 show effective learning with consistent accuracy improvements. Inception V3 exhibits strong training but with variability in validation metrics, while Xception demonstrates robust performance and strong generalization to new data. The integrated system utilizes cameras, sensors, and drones for real-time image processing through a gateway and cloud server with a customized agripest dataset. Transfer learning generates a deployable.h5 file for pest identification. The generated custom model deployed on a gateway or server to classifies pests, alerting farmers through SMS, dashboard, or mobile app notifications. This synergy between machine learning and IoT offers rapid and precise pest detection in agriculture.