IMPLEMENTASI METODE YOLOV8 UNTUK MENDETEKSI TINGKAT FOKUS DAN KELELAHAN PADA WAJAH PEGAWAI SAAT BEKERJA

Wicaksana, Kevin Hanif (2025) IMPLEMENTASI METODE YOLOV8 UNTUK MENDETEKSI TINGKAT FOKUS DAN KELELAHAN PADA WAJAH PEGAWAI SAAT BEKERJA. Undergraduate thesis, UPN Veteran Jawa Timur.

	Text (Cover) Cover.pdf Download (2MB)
	Text (Bab 1) 18081010130_Bab1.pdf Download (1MB)
	Text (Bab 2) 18081010130_Bab2.pdf Restricted to Repository staff only until 24 July 2027. Download (7MB)
	Text (Bab 3) 18081010130_Bab3.pdf Restricted to Repository staff only until 24 July 2027. Download (12MB)
	Text (Bab 4) 18081010130_Bab4.pdf Restricted to Repository staff only until 24 July 2027. Download (11MB)
	Text (Bab 5) 18081010130_Bab5.pdf Download (382kB)
	Text (Daftar pustaka) 18081010130_DaftarPustaka.pdf Download (618kB)

Abstract

The coronavirus disease (Covid-19) pandemic that occurred at the end of 2019 had a major impact worldwide. In addition to impacting the health sector, other sectors such as business and technology are also very influential factors. At the same time, trends in artificial intelligence, machine learning, and deep learning are also emerging, bringing tremendous developments worldwide. New methods and advanced architectures such as YOLO (You Only Look Once) are attracting much attention because they can accurately detect objects with very high probability. YOLO is considered the "fastest deep learning object detector" and is an object detection network architecture that focuses on accuracy and speed. YOLOv8 allows you to perform accurate facial recognition to detect fatigue on employee faces. This detection evaluates how well employees focus on their work. To help companies maintain safety and prevent accidents at work. Such as jobs that require a level of focus to avoid accidents such as construction workers or taxi drivers or customers or people related to the job. The best level of accuracy obtained with YOLOv8 in real-time, has a detection accuracy or a large value of mAP (Mean Average Precision) of up to 0.977 or 97.7%.

Item Type:

Thesis (Undergraduate)

Contributors:

Contribution	Contributors	NIDN/NIDK	Email
Thesis advisor	Diyasa, I Gede Susrama Mas	NIDN0019067008	igusrama.if@upnjatim.ac.id
Thesis advisor	Anggraeny, Fetty Tri	NIDN0711028201	fettyangraeny.if@upnjatim.ac.id

Subjects:

T Technology > T Technology (General)

Divisions:

Faculty of Computer Science > Departemen of Informatics

Depositing User:

Kevin Hanif Wicaksana -

Date Deposited:

25 Jul 2025 08:15

Last Modified:

25 Jul 2025 08:15

URI:

https://repository.upnjatim.ac.id/id/eprint/40727