Detection of Facial Fatigue in High-Risk Workers Using YOLOV4
Deteksi Kelelahan Wajah Pada Pekerja Beresiko Tinggi Menggunakan YOLOV4
DOI:
https://doi.org/10.21070/ups.1705Keywords:
Fatigue, Face, YOLOV4, Face Detection, Image ProcessingAbstract
Work fatigue is a condition where the capacity and focus of workers decrease, affecting their ability to perform tasks. Workers need to be monitored periodically and in real-time so that their fatigue levels can be addressed by supervisors. This study proposes a mechanism for monitoring worker fatigue using real-time digital image processing through a webcam. The study utilizes the YOLOv4 framework for facial recognition. The objective is to detect fatigue signs on workers' faces using YOLO. The research comprises several stages, including system analysis, dataset collection, data preprocessing, YOLO network configuration, data training, testing, and implementation. A total of 500 images were used for training, with 2 classes and 4 criteria. The 2 classes consist of normal and fatigue, while the 4 criteria include tired eyes, normal eyes, normal mouth, and yawning mouth. Based on the conducted testing, the system successfully detected faces with a best mAP score of 98.30%
Downloads
References
M. J. L. Gaol, A. Camelia, and A. Rahmiwati, “Analisis Faktor Risiko Kelelahan Kerja Pada Keryawan Bagian Produksi PT. Arwana Anugrah Keramik, Tbk,” J. Ilmu Kesehat. Masy., vol. 9, no. 1, pp. 53–63, Mar. 2018, doi: 10.26553/jikm.2018.9.1.53-63.
B. A. Deyulmar, Suroto, and I. Wahyuni, “Analisis Faktor-Faktor Yang Berhubungan Dengan Kelelahan Kerja Pada Pekerja Pembuat Kerupuk Opak Di Desa Ngadikerso, Kabupaten Semarang,” J. Kesehat. Masy., vol. 6, no. 4, pp. 278–285, 2018, doi: 10.14710/jkm.v6i4.21428.
S. Firdaus and K. D. Artika, “Deteksi Kelelahan Pengemudi Mobil Menggunakan Citra Wajah,” Elem. J. Tek. MESIN, vol. 8, no. 1, p. 16, Jun. 2021, doi: 10.34128/je.v8i1.154.
L. Lady and A. S. Wiyanto, “TINGKAT KELELAHAN KERJA PADA PEKERJA LUAR RUANGAN DAN PENGARUH LINGKUNGAN FISIK TERHADAP PENINGKATAN KELELAHAN,” J. Ind. Serv., vol. 5, no. 1, pp. 58–64, Oct. 2019, doi: 10.36055/jiss.v5i1.6504.
F. O. Reynaldi, “Analisa Performa Arsitektur Mobilenetv1 Dan Resnet Menggunakan Meta-Learning Dalam Mendeteksi Objek Hewan Kucing,” Indones. J. Bus. Intell., vol. 4, no. 1, p. 1, 2021, doi: 10.21927/ijubi.v4i1.1686.
N. Irtija, M. Sami, and M. A. R. Ahad, “Fatigue Detection Using Facial Landmarks,” Int. Symp. Affect. Sci. Eng., vol. ISASE2018, no. November, pp. 1–6, 2018, doi: 10.5057/isase.2018-C000041.
J. Redmon and A. Farhadi, “YOLOv3: An Incremental Improvement,” Apr. 2018, doi: 10.48550/arXiv.1804.02767.
A. Bochkovskiy, C.-Y. Wang, and H.-Y. M. Liao, “YOLOv4: Optimal Speed and Accuracy of Object Detection,” Apr. 2020, doi: 10.48550/arXiv.2004.10934.
D. H. Fudholi, R. A. N. Nayoan, M. Suyuti, and R. Rahmadi, “Deteksi Indikasi Kelelahan Menggunakan Deep Learning,” J-SAKTI (Jurnal Sains Komput. dan Inform., vol. 5, pp. 1–9, 2021, doi: 10.30645/j-sakti.v5i1.292.
E. R. Setyaningsih and M. S. Edy, “YOLOv4 dan Mask R-CNN Untuk Deteksi Kerusakan Pada Karung Komoditi,” Teknika, vol. 11, no. 1, pp. 45–52, 2022, doi: 10.34148/teknika.v11i1.419.
D. J. P. Manajang, S. R. U. A. Sompie, and A. Jacobus, “Implementasi Framework Tensorflow Object Detection Dalam Mengklasifikasi Jenis Kendaraan Bermotor,” J. Tek. Inform., vol. 8, no. 4, pp. 1821–1831, Dec. 2021, doi: doi.org/10.35793/jti.15.3.2020.29775.
Timj, “Fatigue Dataset,” Kaggle, 2021. https://www.kaggle.com/datasets/timmjy/fatigue-detection.
M. Sarosa and N. Muna, “Implementasi Algoritma You Only Look Once ( Yolo ) Untuk Implementation of You Only Look Once ( Yolo ) Algorithm for,” J. Teknol. Inf. dan Ilmu Komput., vol. 8, no. 4, pp. 787–792, 2021, doi: 10.25126/jtiik.202184407.
C.-Y. Wang, H.-Y. Mark Liao, Y.-H. Wu, P.-Y. Chen, J.-W. Hsieh, and I.-H. Yeh, “CSPNet: A New Backbone that can Enhance Learning Capability of CNN,” in 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Jun. 2020, vol. 2020-June, pp. 1571–1580, doi: 10.1109/CVPRW50498.2020.00203.
K. Khairunnas, E. M. Yuniarno, and A. Zaini, “Pembuatan Modul Deteksi Objek Manusia Menggunakan Metode YOLO untuk Mobile Robot,” J. Tek. ITS, vol. 10, no. 1, 2021, doi: 10.12962/j23373539.v10i1.61622.
N. Chen, Y. Man, and Y. Sun, “Abnormal Cockpit Pilot Driving Behavior Detection Using YOLOv4 Fused Attention Mechanism,” Electronics, vol. 11, no. 16, p. 2538, Aug. 2022, doi: 10.3390/electronics11162538.
C.-Y. Wang, A. Bochkovskiy, and H.-Y. M. Liao, “Scaled-YOLOv4: Scaling Cross Stage Partial Network,” in 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Jun. 2021, pp. 13024–13033, doi: 10.1109/CVPR46437.2021.01283.
R. S. Huda, R. Wulanningrum, and D. Swanjaya, “PEMANFAATAN YOLOV4 UNTUK DETEKSI PELANGGARAN HELM DAN MASKER SERTA IDENTIFIKASI PELAT NOMOR MENGGUNAKAN TESSERACT-OCR,” JOUTICA, vol. 7, no. 2, p. 596, Sep. 2022, doi: 10.30736/informatika.v7i2.873.
Q. Chen and Q. Xiong, “Garbage Classification Detection Based on Improved YOLOV4,” J. Comput. Commun., vol. 08, no. 12, pp. 285–294, 2020, doi: 10.4236/jcc.2020.812023.
S. Jupiyandi, F. R. Saniputra, Y. Pratama, M. R. Dharmawan, and I. Cholissodin, “Pengembangan Deteksi Citra Mobil Untuk Mengetahui Jumlah Tempat Parkir Menggunakan Cuda Dan Modified Yolo Development of Car Image Detection To Find Out the Number of Parking Space Using Cuda and Modified Yolo,” J. Teknol. Inf. dan Ilmu Komput., vol. 6, no. 4, pp. 413–419, 2019, doi: 10.25126/jtiik.201961275.
A. F. Fandisyah, N. Iriawan, and W. S. Winahju, “Deteksi Kapal di Laut Indonesia Menggunakan YOLOv3,” J. Sains dan Seni ITS, vol. 10, no. 1, 2021, doi: 10.12962/j23373520.v10i1.59312.
T. A. A. H. Kusuma, K. Usman, and S. Saidah, “PEOPLE COUNTING FOR PUBLIC TRANSPORTATIONS USING YOU ONLY LOOK ONCE METHOD,” J. Tek. Inform., vol. 2, no. 1, pp. 57–66, Feb. 2021, doi: 10.20884/1.jutif.2021.2.2.77.
A. K. A. Tianto, I. Qadrijati, and S. Haryati, “Faktor-Faktor Yang Berhubungan Dengan Keluhan Kelelahan Mata Pada Pekerja Kantor X Karanganyar,” J. Kesehat. Masy., vol. 1, no. 2, pp. 58–66, 2023, doi: 10.14710/jkm.v11i1.36786.
Downloads
Additional Files
Posted
License
Copyright (c) 2023 UMSIDA Preprints Server
This work is licensed under a Creative Commons Attribution 4.0 International License.
