Article Per Year (5 Year)
p-Index From 2021 - 2026
0.408
P-Index
This Author published in this journals
All Journal Algoritme Jurnal Mahasiswa Teknik Informatika MDP Student Conference
Krisna Putra, Jelvin
Unknown Affiliation
Computer Science & IT Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Electrical & Electronics Engineering

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

Found 2 Documents
Search

 1 
Transfer Learning dengan MobileNetV3 untuk Deteksi Serangan Spoofing Wajah pada Foto Krisna Putra, Jelvin; Yoannita, Yoannita
Algoritme Jurnal Mahasiswa Teknik Informatika Vol 5 No 2 (2025): April 2025 || Algoritme Jurnal Mahasiswa Teknik Informatika
Publisher : Program Studi Teknik Informatika Universitas Multi Data Palembang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35957/algoritme.v5i2.10954

Abstract

Deteksi serangan spoofing wajah menjadi tantangan dalam teknologi pengenalan wajah, terutama pada sistem presensi karyawan yang rentan terhadap penyalahgunaan, seperti penggunaan foto untuk memalsukan kehadiran. Penelitian ini mengembangkan metode deteksi spoofing berbasis transfer learning dengan memanfaatkan arsitektur MobileNetV3, yang dirancang untuk efisiensi pada perangkat dengan keterbatasan sumber daya, seperti perangkat seluler. Model yang dikembangkan dilatih menggunakan dataset dengan pembagian rasio 70:15:15 untuk pelatihan, validasi, dan pengujian, menggunakan pendekatan supervised learning. Hasil eksperimen menunjukkan bahwa varian MobileNetV3-Large dengan teknik fine-tuning, yang dilakukan dengan membuka kembali lapisan setelah lapisan ke-130, mampu mencapai akurasi 99,58% pada data pelatihan, 99,94% pada validasi, dan 99,77% pada pengujian. Selain itu, model ini memperoleh HTER sebesar 0,002254791432, yang menunjukkan efektivitas tinggi dalam mengidentifikasi serangan spoofing wajah.
Implementasi Sistem Informasi Kehadiran Karyawan di PT Anugerah Alam Konstruksi Maximilliano, Wesley; Krisna Putra, Jelvin; Yoannita, Yoannita
MDP Student Conference Vol 4 No 1 (2025): The 4th MDP Student Conference 2025
Publisher : Universitas Multi Data Palembang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35957/mdp-sc.v4i1.10956

Abstract

PT Anugerah Alam Konstruksi faces challenges in employee attendance recording, which is still done manually, where field workers submit photos via WhatsApp, while office staff attendance is recorded directly by the admin. This method results in disorganized attendance data and requires more time for processing. To address this issue, an Android and web-based Employee Attendance Information System was designed and developed. This study employs an iterative method, allowing system development to be carried out in stages through multiple cycles. The stages include requirements analysis, system design using an Entity Relationship Diagram (ERD), implementation using Dart for the Android application and PHP for the web administration, as well as system testing and evaluation. The Android application enables employees to clock in based on predefined time and location, while the web-based system facilitates admins in managing, verifying, and compiling attendance reports. The implementation of this system is expected to enhance operational efficiency and company productivity through more accurate and organized attendance recording.
Co-Authors Maximilliano, Wesley Yoannita, Yoannita