Article Per Year (5 Year)
p-Index From 2021 - 2026
0.444
P-Index
This Author published in this journals
All Journal Jurnal Teknologi Informasi dan Ilmu Komputer Jurnal Sistem Cerdas
Purba, Risa Tioria Marlini
Unknown Affiliation
Automotive Engineering Computer Science & IT Control & Systems Engineering Education Electrical & Electronics Engineering Engineering

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

Found 2 Documents
Search

 1 
Melanin-Aware and ArcFace Methods in Facial Recognition for Dark-Skinned Individuals Purba, Risa Tioria Marlini; Hidayat, Fadhil; Supangkat, Suhono Harso; Arman, Arry Akhmad
Jurnal Sistem Cerdas Vol. 8 No. 3 (2025)
Publisher : APIC

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37396/jsc.v8i3.587

Abstract

The facial recognition system employing the Melanin-Aware method in conjunction with ArcFace, trained on a dataset of 1,000 dark-skinned facial samples, demonstrates the ability to accurately recognize individuals with dark skin while maintaining performance for non-dark-skinned individuals. ArcFace is utilized as the primary feature extractor, leveraging the additive angular margin to enhance inter-class separability. The experiments were conducted using 1,000 dark-skinned facial samples for training and 100 samples for testing. Evaluation results indicate that melanin-aware preprocessing improves average accuracy by up to 17% compared to the absence of preprocessing, and by 7% compared to the standard aggressive CLAHE-based method. Furthermore, the True Acceptance Rate (TAR) increased from 88.15% to 93.33% at FAR = 1e−2, and from 83.7% to 86.67% at FAR = 1e−3, signifying enhanced system stability under stringent security conditions. The performance gains are supported by a more stable distribution of similarity scores and lower threshold values, reflecting improved separation between genuine and impostor pairs.
Simplifikasi Graf Pemanggilan Fungsi: Pendekatan Community Detection Untuk Mempermudah Pemahaman Struktur Kode Tioria Marlini Purba, Risa; Purba, Risa Tioria Marlini; Tonang, Ari Sandy Putra Ari; Karim, Abdulah; Soekidjo, Gusti Ayu Putri Saptawati; Muhamad, Koyimatu; Arifiansyah, Fitra
Jurnal Teknologi Informasi dan Ilmu Komputer Vol 13 No 2: April 2026
Publisher : Fakultas Ilmu Komputer, Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25126/jtiik.132

Abstract

Dalam pengembangan perangkat lunak skala besar, pemahaman terhadap struktur kode sangat penting untuk menganalisis interaksi antar-fungsi dalam kode sumber. Graf pemanggilan fungsi (function call graph) merupakan kakas yang efektif untuk memetakan hubungan antar-fungsi, yang membantu pengembang dalam menelusuri jalur eksekusi dan memahami pola struktur kode modular yang kompleks. Namun, pada kode sumber yang rumit, graf pemanggilan fungsi sering kali menjadi sangat besar dan sulit diinterpretasi karena banyaknya node dan edge yang terlibat. Untuk mengatasi masalah ini, teknik simplifikasi graf melalui community detection diterapkan sebagai solusi untuk mengelompokkan fungsi-fungsi yang saling terkait dalam cluster, sehingga menghasilkan visualisasi yang lebih terstruktur dan mudah dipahami. Penelitian ini bertujuan untuk mengembangkan kakas berbasis Python yang mampu menyederhanakan graf pemanggilan fungsi menggunakan algoritma Girvan-Newman. Kakas ini memanfaatkan pustaka networkx untuk membentuk graf dan menerapkan deteksi komunitas, ast untuk parsing kode, serta matplotlib dan streamlit untuk visualisasi dan interaksi pengguna. Hasil eksperimen pada 10 program dengan ukuran 10-85 baris kode menunjukkan bahwa metode community detection mampu mereduksi jumlah node dan edge dalam graf pemanggilan fungsi hingga 60%, dengan skor modularitas tertinggi 0.6605. Evaluasi dengan 25 pengembang perangkat lunak menunjukkan tingkat kepuasan 80% dalam hal kemudahan penggunaan dan peningkatan produktivitas analisis kode.   Abstract In large-scale software development, understanding the code structure is crucial for analyzing the interactions between functions in the source code. A function call graph is an effective tool for mapping the relationships between functions, assisting developers in tracing execution paths and understanding object-oriented complex code structures. However, in complex source code, the function call graph often becomes very large and complicated to interpret due to the many nodes and edges involved. To address this issue, graph simplification techniques, such as community detection, are applied as a solution to group related functions into clusters, thereby producing a more structured and easier-to-understand visualization. This study aims to develop a Python-based tool that simplifies function call graphs using the Girvan-Newman algorithm. The tool utilizes the networkx library to construct graphs and apply community detection, ast for code parsing, and matplotlib and streamlit for visualization and user interaction. The results of experiments on 10 programs, ranging in size from 10 to 85 LOC, showed that the community detection method was able to reduce the number of nodes and edges in the function invocation graph by up to 60%, achieving the highest modularity score of 0.6605. An evaluation of 25 software developers revealed an 80% satisfaction rate in terms of ease of use and increased productivity in code analysis.
Co-Authors Arifiansyah, Fitra Arry Akhmad Arman Gusti Ayu Putri Saptawati Hidayat, Fadhil Karim, Abdulah Muhamad, Koyimatu Suhono Harso Supangkat Tioria Marlini Purba, Risa Tonang, Ari Sandy Putra Ari