Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal Journal of Information Systems and Informatics Journal of Computer and Information Systems Ampera
Mahmud Mahmud
Universitas Bina Darma
Computer Science & IT

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

 1 
Pengembangan Aplikasi Pengenalan Aksara Komering Menggunakan Metode Deep Learning Berbasis Android Mahmud Mahmud; Yesi Novaria Kunang
Journal of Computer and Information Systems Ampera Vol. 1 No. 2 (2020): Journal of Computer and Information Systems Ampera
Publisher : APTIKOM SUMSEL

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51519/journalcisa.v1i2.38

Abstract

Penggunaan aksara Komering dari waktu ke waktu mulai ditinggalkan di kalangan masyarakat suku Komering dengan banyaknya budaya luar masuk ke Indonesia. Penelitian ini bertujuan untuk melestarikan dan menghidupkan kembali aksara Komering beserta bahasanya dengan menggunakan pemanfaatan teknologi Deep learning yang dibenamkan kedalam aplikasi android. Teknologi DL yang merupakan suatu sub ilmu dari bidang Machine Learning yang dikembangkan atas dasar cara berfikir dari struktur otak manusia sehingga dapat menghasilkan klasifikasi yang lebih baik. Salah satu algoritma dari DL yang terkenal baik dalam mengenali gambar ialah Convolutional Neural Network. Pada penelitian ini percobaan pengklasifikasian gambar aksara Komering dilakukan dengan data sebanyak 1540 gambar, 29 class. Hasil yang didapatkan dari data testing dengan data asli yaitu 58%, sedangkan untuk testing data augmented 80%. Persentase dalam pengujian aplikasi android melalui kamera 84,14%, galeri 87,58% dan penulisan 93,79%
Rule-Based Transliteration of Ulu Kaganga Script using Character Mapping Ilman Zuhri Yadi; Yesi Novaria Kunang; Tia Permata Sari; Mahmud Mahmud; Nuzulur Ramadhona
Journal of Information System and Informatics Vol 6 No 4 (2024): December
Publisher : Asosiasi Doktor Sistem Informasi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51519/journalisi.v6i4.1000

Abstract

Ulu Kaganga script is a historical writing tradition that developed in the southern region of Sumatra. With the widespread use of Latin script, the Ulu Kaganga script has become rare, and very few people can read and write in this script. To preserve the Ulu script, a tool is needed to assist in transliterating Latin text into the Ulu script. This research aims to preserve the Ulu script with the help of technology. In this study, a mobile and web-based application has been developed to transliterate the Ulu Kaganga script from Latin text. The technique used for this script conversion is rule-based, which is employed to break words into syllables and map those syllables into Ulu script characters. Through the rule-based technique and character mapping, adding Indonesian syllables and writing Ulu Kaganga script characters, consisting of 1139 primary characters, becomes easy. This application has been repeatedly tested to improve the mapping of Ulu script characters. The results of testing the application to transliterate 1746 words from Latin script were successful in transliterating. The tests conducted show that the approach used is very effective, with a transliteration accuracy from Latin to Ulu script of 99.98% The testing results show that the application can transcribe text accurately and conveniently, allowing non-expert users to write in Ulu script characters.
Co-Authors Ilman Zuhri Yadi Nuzulur Ramadhona Tia Permata Sari Yesi Novaria Kunang