Article Per Year (5 Year)
p-Index From 2019 - 2024
0.444
P-Index
This Author published in this journals
All Journal Teknika Jurnal Teknik Komputer AMIK BSI
Sherli Trisnawati
Institut Informatika Dan Bisnis Darmajaya
Automotive Engineering Chemical Engineering, Chemistry & Bioengineering Computer Science & IT Control & Systems Engineering Electrical & Electronics Engineering Engineering

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

Found 2 Documents
Search

 1 
Perbandingan Algoritma Support Vector Machine dan AdaBoost Dalam Memprediksi Waktu Kelulusan Mahasiswa Hary Sabita; Sherli Trisnawati
TEKNIKA Vol. 17 No. 2 (2023): Teknika Juli - Desember 2023
Publisher : Politeknik Negeri Sriwijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.5281/zenodo.8220872

Abstract

Fokus penelitian ini adalah untuk membuat sebuah model machine learning dengan menggunakan dua metode yang berbeda. Metode yang dikembangkan akan menghasilkan model yang nantinya akan dapat memprediksi waktu kelulusan mahasiswa. Metode yang di gunakan adalah klasifikasi dengan membandingkan dua algoritma, yaitu Support Vector Machine (SVM) dan AdaBoost. Penelitian ini menggunakan 660 data internal di prodi Teknik Informatika IIB Darmajaya dan dianalisa dengan menggunakan bahasa pemrograman python. Hasil akhir dari penelitian ini adalah akurasi sebesar 0,73 untuk algoritma AdaBoost dan 0,62 untuk SVM. Hasil penelitian ini sangat berguna untuk memprediksi waktu kelulusan mahasiswa berdasarkan 6 variabel independent, yaitu; pendidikan orang tua, pendapatan orang tua, jalur pendidikan, kegiatan internal dan eksternal yang diikuti serta ipk mahasiswa.
FaceVoting: e-Voting Berbasiskan Pengenalan Wajah Rahmalia Syahputri; Berkat Fa’atulo Halawa; Sherli Trisnawati; Nurfiana Nurfiana; Taufik Taufik
JURNAL TEKNIK KOMPUTER AMIK BSI Vol 10, No 2 (2024): Periode Juli 2024
Publisher : Universitas Bina Sarana Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31294/jtk.v10i2.21918

Abstract

FaceVoting is an electronic voting system that employs facial recognition technology to authenticate voters, enhancing the security and efficiency of voting processes. This research showcases the integration of the Haar Cascade algorithm, renowned for its rapid and accurate object detection capabilities, tailored explicitly for face recognition in varied conditions. Through rigorous testing, the system proved highly effective at recognising faces across different distances, angles, and expressions despite some limitations in detecting obscured or unregistered faces. Extensive evaluations involved recording faces at 30 cm and 100 cm distances, yielding consistent detection scores of 0.2586751709411996, illustrating the system's robustness. Additionally, face recordings validated under varying angles demonstrated the system’s ability to maintain accuracy with minimal score variation, highlighting its adaptability to different voter positions. Further tests on diverse objects and facial expressions underscored the system’s precision in real-world scenarios, albeit with challenges in recognising non-human objects, other people’s faces, and partially obscured faces. About 96.5% of the 110 participants expressed satisfaction with the facial recognition feature, emphasising their confidence in its potential to secure and streamline the voting process. The study confirms the viability of facial recognition technology in e-voting systems, providing a substantial improvement over traditional methods in terms of accessibility, reliability, and fraud prevention, thereby supporting a more inclusive and transparent electoral process. 
Co-Authors - Nurfiana Berkat Fa’atulo Halawa Hary Sabita Rahmalia Syahputri Taufik Taufik