KLASIFIKASI KONDISI GIGI BERDASARKAN CITRA RGB MENGGUNAKAN CONVOLUTIONAL NEURAL NETWORKS

SIHOTANG, GABRIEL MEDIOSE ALFRANDA and Supardi, Julian (2024) KLASIFIKASI KONDISI GIGI BERDASARKAN CITRA RGB MENGGUNAKAN CONVOLUTIONAL NEURAL NETWORKS. Masters thesis, Sriwijaya University.

	Image RAMA_55101_09012682327001_cover.jpg - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (227kB) | Request a copy
	Text RAMA_55101_09012682327001.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (14MB) | Request a copy
	Text RAMA_55101_09012682327001_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (3MB) | Request a copy
	Text RAMA_55101_09012682327001_0010077210_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (820kB)
	Text RAMA_55101_09012682327001_0010077210_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (425kB) | Request a copy
	Text RAMA_55101_09012682327001_0010077210_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (455kB) | Request a copy
	Text RAMA_55101_09012682327001_0010077210_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (920kB) | Request a copy
	Text RAMA_55101_09012682327001_0010077210_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (108kB) | Request a copy
	Text RAMA_55101_09012682327001_0010077210_06_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (185kB) | Request a copy
	Text RAMA_55101_09012682327001_0010077210_07_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (12MB) | Request a copy

Abstract

This study utilizes a deep learning model using a Convolutional Neural Network with ResNet – 18 architecture in classifying dental conditions based on RGB images consisting of four classes: Calculus, Caries, Gingivitis, and Tooth Discoloration. The data used came from a collection of several dental and oral diseases. The preprocessing stages include Resize, Center Crop, Random Resized Crop, Random Horizontal Flip, Random Rotation, To Tensor, and Normalize. The model training process using hyperparameters includes Epoch 50, Learning Rate 0.001, Batch Size 16, and Optimizer Adam. The research conducted the implementation of Residual Network -18. The results of the model evaluation had a fairly high accuracy performance in the Caries class with an accuracy score of 97% and the Tooth Discoloration class with an accuracy of 96%. However, the accuracy performance was low in the Gingivitis class of 88% and the Calculus class of 78%. Differences in accuracy performance between classes are due to the characteristics of the dataset or when distinguishing visual features between classes. This research provides a practical approach and contributes to improving efficiency in the diagnosis of dental conditions, especially reducing considerable radiation exposure in patients during X-Ray examinations. By using deep learning methods, this approach has the potential to speed up the diagnosis process, while offering safer and more practical solutions for doctors and patients. This not only improves the accuracy in detecting dental conditions but also supports more effective medical practices in the future.

Item Type:	Thesis (Masters)
Uncontrolled Keywords:	Deep Learning, CNN, Klasifikasi Kondisi Gigi, Diagnosis Gigi, Residual-Network-18
Subjects:	Q Science > QA Mathematics > QA75-76.95 Calculating machines > QA76.9.B45 Big data. Machine learning. Quantitative research. Metaheuristics.
Divisions:	09-Faculty of Computer Science > 55101-Informatics (S2)
Depositing User:	Gabriel Mediose Alfranda Sihotang
Date Deposited:	19 Jan 2025 14:39
Last Modified:	19 Jan 2025 14:39
URI:	http://repository.unsri.ac.id/id/eprint/165189

Actions (login required)

View Item