NORMA eResearch @NCI Library

An Approach to Identify and Classify Banana leaf pests using Machine Learning and Deep Learning Neural Networks

Rokade, Yogesh Ravindra (2022) An Approach to Identify and Classify Banana leaf pests using Machine Learning and Deep Learning Neural Networks. Masters thesis, Dublin, National College of Ireland.

[thumbnail of Master of Science]
PDF (Master of Science)
Download (1MB) | Preview
[thumbnail of Configuration manual]
PDF (Configuration manual)
Download (1MB) | Preview


Leaf pests’ infection are the most common phenomena which can be seen across the world. In recent years, agriculture has significantly contributed to Gross Domestic Product (GDP) across several countries. Most Asian nations are agriculture-based, and their economies are heavily reliant on the export of agricultural products and make huge profit from production of crops. After China, India is the world's second largest fruit production, as well as India ranks first in banana production. As most of Asian countries have extreme weather, there has been a huge increase in bacterial and fungal diseases, thus degrading the quality and productivity of plants. Not detecting these diseases at early stages may result in low production of fruit. Many farmers are uncertain about disease type that has infected their crops, hence leading to inappropriate usage of pesticides on plant affecting their growth. Also obtaining expert guidance in such circumstances is time consuming and costly for farmers. Many survey states that due to crop losses huge number of farmer’s attempt suicide. To overcome these severe issues, identifying and classifying the banana leaf pests at the earliest is important. The aim of this study is to build a machine learning model that can help farmers to classify the pests, reduce plant loss and eventually help increase GDP. For classification, six machine and deep learning models are evaluated with different performance metrics. The models VGG19 and DenseNet201 outperforms other models with an accuracy of 95%.

Item Type: Thesis (Masters)
Uncontrolled Keywords: Banana leaf; gross domestic product; SVM; Random Forest; VGG19; DenseNet201; machine learning
Subjects: Q Science > QA Mathematics > Electronic computers. Computer science
T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science
S Agriculture > SB Plant culture
Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions: School of Computing > Master of Science in Data Analytics
Depositing User: Tamara Malone
Date Deposited: 08 Mar 2023 18:03
Last Modified: 08 Mar 2023 18:03

Actions (login required)

View Item View Item