Fertilizers Recommendation System For Disease Prediction Using Improved SVM

Abstract

Agriculture is several of the key industries that affect a nation's industrial prosperity. Most people in countries like India rely on agriculture to make a living. Numerous innovations are being incorporated into farming to make it simpler for growers to cultivate and increase their production, such as Neural and machine learning methodologies. The relevant functionalities are performed in this article's software: cultivar recommendations, fertilizer suggestions, and phytopathogens forecasting, correspondingly. One of the main causes of decreases in the amount and quality of food products is vegetation diseases, particularly on the stems. If a plant has a crop disease in the context of agriculture, this stunts the progress of the farming level. Identifying plant diseases is a crucial part of preserving crops. Following pre-processing with thresholding, segmentation is conducted using the Guided Active Contour approach, and ultimately, a Support Vector Machine is used to identify the crop diseases. To propose fertiliser, the illness similarity metric is employed.