IoT enabled prediction of agriculture's plant disease using improvedϖ quantum whale optimization DRDNN approach

Abstract

The population of the earth is increasing at a very rapid rate. Ensuring access to nutritious food is essential to the survival of the world's population, given this continued growth. Agriculture also plays a critical role in developing countries economies. The difference in supply and demand for food or agriculture has an impact on the overall state of the economy. Plant diseases pose a serious risk to food yield, which could lead to hunger and economic slowdown. The proposed Improved Quantum Whale Optimization with Principle Component Analysis (IQWO-PCA) on using a Machine Learning (ML) model to evaluate a collection of images of tomato disease to take the appropriate preventative measures to deal with this agricultural catastrophe. The dataset used in this study was derived from an easily available plant village dataset. The network is developed after the hyper-parameters are optimized in the systematic review. Four trained prototypes are used to develop the transmission learning-based DNN: Alexnet, VGG16, ResNet50, and DenseNet121.Using an approach to optimize composite building blocks, the main features of the data set are retrieved. To better classify tomato diseases, the recovered data are loaded into a deep neuronal network. The proposed model is then evaluated using traditional ML methodologies to determine its superiority in terms of precision measurements and loss rates.