Detection of Pneumonia using Resnet Models

Mohan, Sharan (2023) Detection of Pneumonia using Resnet Models. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration manual) Download (997kB) | Preview

Abstract

Pneumonia is a lung disease which mostly affects the children and old aged people. To detect the presence of pneumonia in a fast way deep learning was introduced using x-ray images. In the past several deep learning models were implemented, whereas in this paper a specific model with various layers is implemented. This research studies the difference between the four residual networks (Inception-Resnet, Resnet-152,Resnet-101 and Resnet-50) and also to detect the disease pneumonia. The four models were evaluated using different metrics such as accuracy, precision, recall and F1-score. Even though the four models gave almost same accuracy, the F1-score of Resnet-152 outperforms all other models with a F1-score of 57 percentage with a train accuracy of 95 percent and 89 on validation accuracy.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Ul Ain, Qurrat UNSPECIFIED
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science R Medicine > RF Otorhinolaryngology 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:	23 May 2023 12:58
Last Modified:	23 May 2023 12:58
URI:	https://norma.ncirl.ie/id/eprint/6622

Actions (login required)

View Item