Article Per Year (5 Year)
p-Index From 2021 - 2026
0.444
P-Index
This Author published in this journals
All Journal Media Informatika JURNAL REKAYASA INFORMASI SWADHARMA (JRIS)
Landung Sudarmana
Universitas Proklamasi 45 Yogyakarta
Computer Science & IT

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

Found 2 Documents
Search

 1 
Simulasi Penggunaan Listrik Tarif Sosial Menggunakan Algoritma ERNN Titik Rahmawati; Landung Sudarmana; Agung Priyanto
Media Informatika Vol 21 No 3 (2022)
Publisher : P3M STMIK LIKMI

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (879.164 KB) | DOI: 10.37595/mediainfo.v21i3.145

Abstract

The use of electricity under the social tariff category has increased significantly each year, both purely social and commercial social use. The use of social tariff electricity is intended for public interest activities for both the lower and upper middle social strata which are oriented towards fulfilling growth and development facilities for the public interest, so that a simulation of social electricity usage is needed to map a picture of the condition of the amount of social electricity usage in the future. The research was conducted to determine the estimation of how much electricity is used by using the Elman Recurrent Neural Network (ERNN) algorithm by reducing the input dimensions. The ERNN algorithm is used to simulate network parameters formed from complex input-output relationships, so that data patterns can be found. The factors of the input dimensions of this study are demographic data, electricity usage, social customers, population, gross regional domestic product (GRDP) and industrial growth. The results showed that the ERNN algorithm is capable of simulating formed network parameters that can be used for training and validation so that the value of the network Mean Square Error (MSE) can be determined, with prediction accuracy using the Mean Absolute Percentage Error (MAPE) for forecast in sample in the forecast period of 5 years obtained an average of 0.77%, and able to know the dominant factors that influence the use of social tariff electricity.
IMPLEMENTASI REST API GOLANG PADA SISTEM PRESENSI WAJAH BERBASIS FACE EMBEDDING ARCFACE Septian Dwiky Hermawan; Landung Sudarmana; Gustina Sapriani
JRIS : Jurnal Rekayasa Informasi Swadharma Vol 6, No 2 (2026): JURNAL JRIS EDISI JULI 2026
Publisher : Institut Teknologi dan Bisnis (ITB) Swadharma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56486/jris.vol6no2.1208

Abstract

Conventional attendance systems carry a high risk of data manipulation, necessitating more secure biometric technology. This study aims to implement a facial biometric attendance system using a REST API architecture with the Golang programming language. The research method used is applied research, while system development follows the Waterfall model. The facial recognition process is carried out by extracting image features into a numerical representation, a face embedding (a 512-dimensional vector), using the ArcFace Convolutional Neural Network (CNN) model. The embedding data is stored in a PostgreSQL database using the pgvector extension to support cosine similarity search. Test results show that the system is capable of accurate identity verification. With a threshold of 0.43, the system achieved an accuracy of 78.04%, a False Acceptance Rate (FAR) of 0.00%, and a False Rejection Rate (FRR) of 23.15%. This demonstrates the effectiveness of using face embedding in a Golang REST API service for providing a secure, real-time attendance solution.Sistem presensi konvensional memiliki risiko manipulasi data yang tinggi, sehingga diperlukan teknologi biometrik yang lebih aman. Penelitian ini bertujuan mengimplementasikan sistem presensi biometrik wajah menggunakan arsitektur REST API dengan bahasa pemrograman Golang. Metode penelitian yang digunakan adalah penelitian terapan (applied research), sedangkan pengembangan sistem dalam penelitian ini mengikuti model Waterfall. Proses pengenalan wajah dilakukan dengan mengekstraksi fitur citra menjadi representasi numerik berupa face embedding (vektor 512-dimensi) melalui model Convolutional Neural Network (CNN) ArcFace. Data embedding disimpan dalam basis data PostgreSQL menggunakan ekstensi pgvector untuk mendukung pencarian kemiripan berbasis cosine similarity. Hasil pengujian menunjukkan bahwa sistem mampu melakukan verifikasi identitas secara akurat. Dengan nilai ambang batas (threshold) 0,43, sistem memperoleh nilai akurasi 78,04% dengan False Acceptance Rate (FAR) 0,00% dan False Rejection Rate (FRR) 23,15%. Hal ini membuktikan bahwa penggunaan face embedding pada layanan REST API Golang efektif dalam memberikan solusi presensi yang aman dan real-time
Co-Authors Agung Priyanto Gustina Sapriani Septian Dwiky Hermawan Titik Rahmawati