The Sriwijaya University Library

  • Home
  • Information
  • News
  • Help
  • Login
  • Librarian
  • Member Area
  • Select Language :
    Arabic Bengali Brazilian Portuguese English Espanol German Indonesian Japanese Malay Persian Russian Thai Turkish Urdu

Search by :

ALL Author Subject ISBN/ISSN Advanced Search

Last search:

{{tmpObj[k].text}}
Image of PEMANFAATAN KECERDASAN BUATAN GENERATIF UNTUK LESI PRA-KANKER SERVIKS DALAM MENINGKATKAN AKURASI PENGAMBILAN KEPUTUSAN KLINIS
Bookmark Share

Skripsi

PEMANFAATAN KECERDASAN BUATAN GENERATIF UNTUK LESI PRA-KANKER SERVIKS DALAM MENINGKATKAN AKURASI PENGAMBILAN KEPUTUSAN KLINIS

Nabilah, Aini - Personal Name;

Data scarcity and class imbalance remain significant challenges in developing deep learning models for medical image classification, including the classification of Cervical Intraepithelial Neoplasia (CIN). Limited data availability and imbalanced class distribution, particularly in minority classes such as CIN 2 and CIN 3, may affect the stability, generalization capability, and performance of multi-class classification models. Conventional augmentation techniques provide limited improvement in distributional diversity. This study investigates the use of StyleGAN2-ADA as a Generative Adversarial Network (GAN)-based augmentation method to generate synthetic images that approximate the distribution of real CIN data while helping improve class balance. The evaluation was conducted using two classification settings: models trained with real data only and models trained with a combination of real and augmented data. In addition, two experimental schemes were designed to analyze the effect of data quantity on generative quality, namely GAN training after data splitting and GAN training before data splitting. This study evaluated several deep learning classification models, including YOLOv11, Vision Transformer (ViT), EfficientNetV2-S, and ConvNeXt. The quality of synthetic images was assessed using the Fréchet Inception Distance (FID), while classification performance was evaluated using accuracy, precision, recall, and F1-score. The results indicate that lower FID values tend to be associated with more consistent improvements in classification performance, including better handling of class imbalance reflected by improved F1-score values. Among the evaluated models, EfficientNetV2-S achieved the best performance with an accuracy and F1-score of 88% after augmentation. These findings suggest that GAN-based augmentation can contribute to improving CIN classification performance while helping address data scarcity and class imbalance, provided that generative quality and experimental design are appropriately managed.


Availability
#
Central Library (REFERENCES) T1983992026
T198399
Available but not for loan - Not for Loan
Detail Information
Series Title
-
Call Number
T1983992026
Publisher
Indralaya : Prodi Magister Ilmu Komputer, Fakultas Ilmu Komputer Universitas Sriwijaya., 2026
Collation
xvii, 122 hlm.; ilus.; tab.; 29 cm.
Language
Indonesia
ISBN/ISSN
-
Classification
618.107
Content Type
Text
Media Type
-
Carrier Type
-
Edition
-
Subject(s)
Prodi Magister Ilmu Komputer
Serviks—Lesi prakanker
Specific Detail Info
-
Statement of Responsibility
TUTI
Other version/related
TitleEditionLanguage
KLASIFIKASI PENYAKIT GINJAL KRONIS DENGAN MENGGUNAKAN ALGORITMA MACHINE LEARNINGid
PENGEMBANGAN DIALOG ADAPTIF MENGGUNAKAN KECERDASAN BUATAN GENERATIF PADA GIM VISUAL NOVELid
File Attachment
  • PEMANFAATAN KECERDASAN BUATAN GENERATIF UNTUK LESI PRA-KANKER SERVIKS DALAM MENINGKATKAN AKURASI PENGAMBILAN KEPUTUSAN KLINIS
Comments

You must be logged in to post a comment

The Sriwijaya University Library
  • Information
  • Services
  • Librarian
  • Member Area

About Us

As a complete Library Management System, SLiMS (Senayan Library Management System) has many features that will help libraries and librarians to do their job easily and quickly. Follow this link to show some features provided by SLiMS.

Search

start it by typing one or more keywords for title, author or subject

Keep SLiMS Alive Want to Contribute?

© 2026 — Senayan Developer Community

Powered by SLiMS
Select the topic you are interested in
  • Computer Science, Information & General Works
  • Philosophy & Psychology
  • Religion
  • Social Sciences
  • Language
  • Pure Science
  • Applied Sciences
  • Art & Recreation
  • Literature
  • History & Geography
Icons made by Freepik from www.flaticon.com
Advanced Search
Where do you want to share?