Prambudi, Katarina Inezita (2024) Laporan Kerja Praktik Implementasi Model Klasifikasi Menggunakan Metode Transfer Learning untuk Pemilihan Slice Citra 3D CBCT di Departemen Teknik Informatika Institut Teknologi Sepuluh Nopember Periode 1 Mei 2024 - 31 Juli 2024. Project Report. [s.n.], [s.l.]. (Unpublished)
![[thumbnail of 5025211148-Project_Report.pdf]](http://repository.its.ac.id/style/images/fileicons/text.png) |
Text
5025211148-Project_Report.pdf - Accepted Version Download (1MB) |
Abstract
Pemasangan implan gigi merupakan salah satu pilihan dalam menggantikan gigi yang hilang. Rencana perawatan yang tepat bisa didapat dari hasil interpretasi yang berasal dari alat CBCT 3D Artificial Intelligence (AI) digunakan dalam dunia kedokteran gigi untuk mendukung diagnostik pencitraan medis dan gigi digunakan pendekatan deep learning dalam mengklasifikasi ukuran implan gigi. Pemodelan klasifikasi ini memanfaatkan metode transfer learning dengan menggunakan algoritma Convolutional Neural Network (CNN).Model transfer learning yang digunakan untuk klasifikasi terdiri dari VGG-16, ResNet50, ResNet101, ResNet152, dan MobileNet. Model VGG-16 memiliki akurasi tertinggi sebesar 98,20% pada skenario menggunakan histogram equalization dan
layer trainable false.
============================================================================================================================
One method of replacing lost teeth is to insert dental implants. The 3D CBCT tool's interpretation results can be used to choose the best course of treatment. In dentistry, artificial intelligence (AI) is utilized to assist diagnostics related to medical and dental imaging. Dental implant sizes are classified using a deep learning technique. This categorization modeling makes use of the Convolutional Neural Network (CNN) algorithm and the transfer learning approach. The transfer learning models ResNet50, ResNet101, ResNet152, and MobileNet are the ones utilized for categorization. In this scenario, the VGG-16 model with fake trainable layers and histogram equalization achieves the maximum accuracy (98.20%).
| Item Type: | Monograph (Project Report) |
|---|---|
| Uncontrolled Keywords: | Implan Gigi, Citra 3D CBCT, Transfer Learning, Histogram Equalization, Layer Trainable |
| Subjects: | T Technology > T Technology (General) |
| Divisions: | Faculty of Intelligent Electrical and Informatics Technology (ELECTICS) > Informatics Engineering > 55201-(S1) Undergraduate Thesis |
| Depositing User: | Katarina Inezita Prambudi |
| Date Deposited: | 03 Sep 2024 08:47 |
| Last Modified: | 03 Sep 2024 08:47 |
| URI: | http://repository.its.ac.id/id/eprint/115579 |
Actions (login required)
 |
View Item |