Skripsi

IMPLEMENTASI EFFICIENTNETB3 UNTUK PENGENALAN SISTEM ISYARAT BAHASA INDONESIA (SIBI) SECARA REAL-TIME

---

Penilaian

---

The Indonesian Sign Language System (SIBI) is widely used as a communication standard within the deaf community. However, communication barriers still exist between deaf individuals and the general public who are not proficient in sign language. Therefore, an effective technological solution is required to bridge this communication gap. This study aims to develop a real-time SIBI sign language recognition system using the Convolutional Neural Network (CNN) method with the EfficientNetB3 architecture to classify SIBI gestures with high accuracy and computational efficiency. The dataset used in this study was obtained from Kaggle, consisting of 5,280 image files. Six models were trained with batch size parameters of 24 and 32, and epochs of 20, 30, and 40. The experimental results showed that the model trained with a batch size of 24 and 40 epochs achieved the best performance, with test results of 98.74% accuracy, 98.86% precision, 98.74% recall, and 98.80% F1-score. These findings indicate that the proposed model performs very effectively in detecting SIBI hand gestures.

---

Availability

Inventory Code	Barcode	Call Number	Location	Status
2507006248	T185534	T1855342025	Central Library (Reference)	Available but not for loan - Not for Loan

Detail Information

Series Title

-

Call Number

T1855342025

Publisher

Indralaya : Prodi Sistem Komputer, Fakultas Ilmu Komputer Universitas Sriwijaya., 2025

Collation

xvii, 105 hlm.; ilus.; tab.; 29 cm.

Language

Indonesia

ISBN/ISSN

-

Classification

419.07

Content Type

Text

Media Type

unmediated

Carrier Type

other (computer)

Edition

-

Subject(s)

Bahasa Isyarat
Prodi Sistem Komputer

Specific Detail Info

-

Statement of Responsibility

MI

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment