Internet of things-based remote monitoring and classification of Spinacia oleracea leaf disease using deep learning approach

Due to the change in the climatical conditions, there is a considerable impact on the plant's growth. Hence, a system with a model has been developed for monitoring Spinacia oleracea plant which has many health benefits. It will control, monitors and protect it from different disease-causing agents. Here the leafy plant was grown and quality has compared in both fields. The environmental sensors installed in the field continuously capture and stores in the database. The image data in the database are analysed using transfer learning methods, i.e., MobileNetV2, ResNet152V2, InceptionV3, DenseNet201, and VGG16. From experimental results, it has been found that MobileNetV2 has reached the highest accuracy of 95% compared to other models. Finally, web app was developed which will quickly identify and classify the occurrence of the diseases. It has been seen that Spinacia oleracea is better in growth, nutrient content, and disease-free when grown inside the polyhouse.