Multiclass Classification of COVID-19, Pneumonia, or Normal Lungs Based on Chest X-Ray Images with Ensemble Deep Learning

Saputra, Tarissya Brilianna and Pasaribu, Novie Theresia Br. and Gany, Audyati and Hasugian, Meilan Jimmy and Sartika, Erwani Merry (2022) Multiclass Classification of COVID-19, Pneumonia, or Normal Lungs Based on Chest X-Ray Images with Ensemble Deep Learning. In: 20222 Fortei-International Conference on Electrical Engineering, 11-13 Oktober 2022, Tanjungpinang.

	Text 1 ForteiICEE-Multiclass Classification (2022).pdf Download (1580Kb)
	Text 7. Turnitin_Multiclass Classification of COVID-19, Pneumonia, or Normal Lungs Based on Chest X-Ray Images.pdf Download (2106Kb)

Abstract

Coronavirus Disease of 2019 (COVID-19) has a high transmission and death rate. It is important to diagnose COVID-19 accurately and distinguish it clearly from other common lung diseases, e.g., pneumonia. Both diseases are detectable from chest X-Ray images. Therefore, an ensemble deep learning model is applied for multiclass classification of COVID-19, pneumonia, or normal lungs based on chest X-Ray images. ResNet50, VGG16, and InceptionV3 pretrained CNN models are employed to form an ensemble model. The chest X�Ray images are preprocessed in three steps, i.e., cropping, resizing, and normalization. Then, the pretrained models are trained with a new classifier at the top layer of the model. After the classifier is trained, then the pretrained ResNet50, VGG16, and InceptionV3 are fine-tuned. Lastly, the decisions from each model are assembled using Soft Voting. The ensemble deep learning model which produces the best result, which is formed by combining pretrained and fine-tuned ResNet50, VGG16, and InceptionV3 models, results weighted accuracy of 0.9752, weighted sensitivity of 0.9612, and weighted specificity of 0.9804

Item Type:	Conference or Workshop Item (Paper)
Contributors:	Contribution Contributors NIDN/NIDK Email UNSPECIFIED Saputra, Tarissya Brilianna UNSPECIFIED UNSPECIFIED UNSPECIFIED Pasaribu, Novie Theresia Br. UNSPECIFIED UNSPECIFIED UNSPECIFIED Gany, Audyati UNSPECIFIED UNSPECIFIED UNSPECIFIED Hasugian, Meilan Jimmy UNSPECIFIED UNSPECIFIED UNSPECIFIED Sartika, Erwani Merry UNSPECIFIED UNSPECIFIED
Subjects:	T Technology > T Technology (General)
Depositing User:	Perpustakaan Maranatha
Date Deposited:	05 Apr 2023 07:38
Last Modified:	10 Apr 2023 08:39
URI:	http://repository.maranatha.edu/id/eprint/31647

Actions (login required)

View Item