Skripsi

KLASIFIKASI GAMBAR ANIME VULGAR MENGGUNAKAN METODE CONVOLUTION NEURAL NETWORK

---

Penilaian

---

Anime is very popular and highly demanded by many circles ranged from children to adults. However, not all anime is appropriate for all ages. There are some anime that contains vulgar content which can be unintentionally exposed to children. This research aims to create a classifier that can seperate anime content that contains vulgarity using the convolution neural network method. The architecture of convolution neural network method that is used as the model in this research is an EfficientNet architecture using anime pictures dataset which contains 2869 safe images and 2734 vulgar images. This research is done by creating models using variations of batch size, epoch, and learning rate which has been previously established and evaluate them using confusion matrix and accuracy, precision, recall, and F1-score metrics. The results from this research shows the model is able to classify vulgar anime images with the highest accuracy being 96,79%. This research shows that convolution neural network method can be used to classify vulgar content although there are some room for improvement especially in collecting dataset with more defined criteria.

---

Availability

Inventory Code	Barcode	Call Number	Location	Status
2507005610	T183622	T1836222025	Central Library (Reference)	Available but not for loan - Not for Loan

Detail Information

Series Title

-

Call Number

T1836222025

Publisher

Indralaya : Prodi Teknik Informatika, Fakultas Ilmu Komputer Universitas Sriwijaya., 2025

Collation

xiv, 76 hlm.; ilus,; tab, 29 cm

Language

Indonesia

ISBN/ISSN

-

Classification

006.307

Content Type

Text

Media Type

unmediated

Carrier Type

other (computer)

Edition

-

Subject(s)

Kecerdasan Buatan
Prodi Teknik Informatika

Specific Detail Info

-

Statement of Responsibility

SEPTA

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment