SISTEM MONITORING KEHADIRAN DAN DURASI KEBERADAAN REALTIME BERBASIS MULTI-FACE RECOGNITION MENGGUNAKAN METODE DEEP METRIC LEARNING DAN YOLOV8

IDRAKHI, FAVIAN FAWAZ (2026) SISTEM MONITORING KEHADIRAN DAN DURASI KEBERADAAN REALTIME BERBASIS MULTI-FACE RECOGNITION MENGGUNAKAN METODE DEEP METRIC LEARNING DAN YOLOV8. S1 thesis, Universitas Mercu Buana Jakarta.

Preview	Text (HAL COVER) COVER.pdf Download (8MB) | Preview
	Text (BAB I) BAB 1.pdf Restricted to Registered users only Download (263kB)
	Text (BAB II) BAB 2.pdf Restricted to Registered users only Download (355kB)
	Text (BAB III) BAB 3.pdf Restricted to Registered users only Download (985kB)
	Text (BAB IV) BAB 4.pdf Restricted to Registered users only Download (911kB)
	Text (BAB V) BAB 5.pdf Restricted to Registered users only Download (245kB)
	Text (DAFTAR PUSTAKA) DAFTAR PUSTAKA.pdf Restricted to Registered users only Download (231kB)
	Text (LAMPIRAN) LAMPIRAN.pdf Restricted to Registered users only Download (968kB)

Abstract

Conventional attendance recording systems in office environments often face problems related to time inefficiency, vulnerability to data manipulation (proxy attendance), and the inability to automatically monitor the total duration of an individual's presence. This study aims to design and implement a Real-Time Presence and Duration Monitoring System using artificial intelligence technology based on Multi-Face Recognition. The approach integrates the YOLOv8 (You Only Look Once version 8) object detection algorithm for simultaneous multi-face localization, with the Deep Metric Learning method via the Dlib library (ResNet-34) to extract 128-dimensional facial feature vectors. The identification process is carried out by measuring the vector similarity using the Euclidean Distance calculation. In terms of software development, the system interface is built dynamically using React.js and TailwindCSS, the backend processing utilizes Python, and data management is streamed in real-time using WebSocket protocols and the Supabase cloud database. The testing results demonstrate that the combination of YOLOv8 and Dlib can detect and recognize faces with high accuracy under normal lighting conditions. This system successfully records not only the arrival time (check-in) but also automatically accumulates the effective duration of the employee's presence within the monitored area. The implementation of this system is proven to minimize attendance manipulation, simplify administrative tasks, and provide objective working duration analytical data for management. xi Keywords: Multi-Face Recognition, YOLOv8, Deep Metric Learning, Presence Duration, Real-Time Monitoring Sistem pencatatan kehadiran konvensional di lingkungan perkantoran maupun instansi sering kali menghadapi permasalahan terkait inefisiensi waktu, rentannya manipulasi data (proxy attendance), serta ketidakmampuan sistem dalam memantau total durasi keberadaan individu secara otomatis. Penelitian ini bertujuan untuk merancang dan mengimplementasikan Sistem Monitoring Kehadiran dan Durasi Keberadaan Real-Time menggunakan teknologi kecerdasan buatan berbasis Multi-Face Recognition. Pendekatan yang digunakan adalah mengintegrasikan algoritma pendeteksi objek YOLOv8 (You Only Look Once versi 8) untuk pelokalisasian banyak wajah secara simultan, dengan metode Deep Metric Learning melalui pustaka Dlib (ResNet-34) untuk mengekstrak vektor fitur wajah berdimensi 128. Proses identifikasi dilakukan dengan mengukur tingkat kemiripan vektor menggunakan perhitungan Euclidean Distance. Pada sisi pengembangan perangkat lunak, antarmuka sistem dibangun secara dinamis menggunakan React.js dan TailwindCSS, pemrosesan backend menggunakan Python, serta pengelolaan data yang disalurkan secara real-time menggunakan protokol WebSocket dan basis data cloud Supabase. Hasil pengujian menunjukkan bahwa kombinasi YOLOv8 dan Dlib mampu mendeteksi dan mengenali wajah dengan akurasi yang tinggi pada kondisi pencahayaan normal. Sistem ini tidak hanya berhasil mencatat waktu kedatangan (check-in), melainkan juga secara otomatis mengakumulasi durasi efektif keberadaan karyawan di dalam area pantauan. Implementasi sistem ini terbukti meminimalisasi celah manipulasi absensi, menyederhanakan tugas administrasi, dan menyediakan ix data analitik durasi kerja yang objektif bagi pihak manajemen. Kata Kunci: Multi-Face Recognition, YOLOv8, Deep Metric Learning, Durasi Keberadaan, Real-Time Monitoring

Item Type:	Thesis (S1)
NIM/NIDN Creators:	41522010260
Uncontrolled Keywords:	Multi-Face Recognition, YOLOv8, Deep Metric Learning, Durasi Keberadaan, Real-Time Monitoring
Subjects:	000 Computer Science, Information and General Works/Ilmu Komputer, Informasi, dan Karya Umum > 000. Computer Science, Information and General Works/Ilmu Komputer, Informasi, dan Karya Umum > 004 Data Processing, Computer Science/Pemrosesan Data, Ilmu Komputer, Teknik Informatika 000 Computer Science, Information and General Works/Ilmu Komputer, Informasi, dan Karya Umum > 000. Computer Science, Information and General Works/Ilmu Komputer, Informasi, dan Karya Umum > 006 Special Computer Methods/Metode Komputer Tertentu > 006.4 Computer Pattern Recognition/Pola Pengenalan Komputer 100 Philosophy and Psychology/Filsafat dan Psikologi > 150 Psychology/Psikologi > 153 Conscious Mental Process and Intelligence/Intelegensia, Kecerdasan Proses Intelektual dan Mental > 153.1 Memory and Learning/Memori dan Pembelajaran > 153.15 Learning/Pembelajaran
Divisions:	Fakultas Ilmu Komputer > Informatika
Depositing User:	khalimah
Date Deposited:	08 Sep 2026 01:34
Last Modified:	08 Sep 2026 01:34
URI:	http://repository.mercubuana.ac.id/id/eprint/103699

Actions (login required)

View Item