A Deep Dive into Precision Horticulture: Unravelling Olive Peacock Spot Intensity with Hybrid Deep Learning

Abstract

The old olive tree, a big part of farming around the world is constantly facing problems from an unknown sickness called Olive Peacock Spot. This disease comes from a hard-to-find fungus named Spilocaea oleagina. Our research is focusing on this problem and we are introducing a new way to manage illness through something called Olive Peacock Spot Intensity Analysis. Our way of doing things is special because it uses a new mixed model for deep learning. This includes layers that find patterns (Convolutional Neural Networks or CNN) and another system to figure out past predictions using two related values in math, known as Logistic Regression. This amazing invention is strongly supported by a carefully made collection of 26000 pictures. These pictures show all types and places where the special mark called olive peacock spots can be seen among many kinds of plants or countries' land areas. Our main goal in our study is to help improve exact farming methods like picking and monitoring diseases on plants. We want people involved with this problem to have a smart computer system that can figure out how bad diseases are. The hybrid model's great all-around correctness shows how good it is at using olive peacock spot strength numbers as it resulted in an overall accuracy of 99.29%. These help us figure out things accurately throughout complex tasks. A tough side-by-side check says our mix model is a front-runner in finding out diseases surpass traditional methods of identifying options that have a longer lifespan and have unfavorable outcomes. This study emphasizes the significance of employing an alternative model. It possesses the ability to provide comprehensive and accurate information through several means, hence greatly aiding in the complete comprehension of various subjects. Confusion matrices, which display visual representations of data, assessing the accuracy of a model.

Topics & Concepts