A Study In Paddy Blast Disease And Its Drug Systems Using Neural Learning Techniques With Pca Methods

Abstract

In many nations that produce rice, paddy blast has emerged as the most common disease. Different statistical techniques have been developed to forecast paddy blast, however earlier techniques failed to accurately predict illnesses. However, there is a growing need for a new model that takes into accounts both weather-related aspects and non-weather data, such as data on blast diseases that affect paddy disease. Artificial intelligence (AI) based drug development has recently received a lot of attention due to its capacity to significantly reduce the time and cost necessary to produce new treatments. Neural learning (NL) and Deep Learning (DL) technologies have been used in the disciplines of medicinal research and development to create novel therapeutic candidates. As a result of the abundance of medication-related data, neural learning and deep learning-based techniques are beginning to appear at every stage of the drug development process. When the results of the drug systems model are closely examined, bagging classifier performs better compared to drug systems that are proposed in predicting paddy blast illness. Our proposed ensemble neural learning techniques withPrincipal Component Analysis(PCA) methods classifiers for paddy blast disease prediction have achieved high precision and high recall.