Pembelajaran Mesin Untuk Deteksi Helm Keselamatan Menggunakan Algoritma YOLOv8

Namri Fatkhin, Akhmad Fadjeri

Abstract


Implementation of Occupational Safety and Health (K3) in construction projects is an effort to create a safe and healthy work environment, free from work accidents and work-related diseases. Based on the International Labor Organization (ILO) report in 2019, more than 395 million workers worldwide experienced non-fatal work injuries. In Indonesia, BPJS Employment reported 370,747 work accident cases in 2023, with an increase of 19.7% from the previous year. As many as 32.12% of these incidents were caused by not using personal protective equipment (APD), including safety helmets. This research aims to build a model through machine learning to automatically detect the use of safety helmets using the YOLOv8 algorithm. The YOLO algorithm is known to have good detection speed and is suitable for complex construction environments. The model evaluation results show that Average Precision reached 78% for all classes, 82% for the APD class, 72% for the non-APD class, and 80% for the non-safety class. The resulting precision value was 77.7% and the recall value was 60.7%, with a mAP (mean Average Precision) level reaching 68.9%. The model training time lasted 1 hour 7 minutes.

Keywords


You Only Look Once; Deteksi Objek; Alat Pelindung Diri; Helm Keselamatan

Full Text:

PDF

References


Amanda Putri, S., Ramadhan, G., Alwildan, Z., Irwan, I., & Afriansyah, R. (2023). Perbandingan Kinerja Algoritma YOLO Dan RCNN Pada Deteksi Plat Nomor Kendaraan. Jurnal Inovasi Teknologi Terapan, 1(1), 145–154. https://doi.org/10.33504/jitt.v1i1.30

Bao, J., Li, S., Wang, G., Xiong, J., & Li, S. (2023). Improved YOLOV8 Network and Application in Safety Helmet Detection. Journal of Physics: Conference Series, 2632(1). https://doi.org/10.1088/1742-6596/2632/1/012012

Dhruv, A. J., Patel, R., & Doshi, N. (2021). Python: The Most Advanced Programming Language for Computer Science Applications. Proceedings of the International Conference on Culture Heritage, Education, Sustainable Tourism, and Innovation Technologies (CESIT 2020), Cesit 2020, 292–299. https://doi.org/10.5220/0010307902920299

Hadi Supriyanto, Sarosa Castrena Abadi, & Aliffa Shalsabilah. (2024). Deteksi Helm Keselamatan Menggunakan Jetson Nano dan YOLOv7. Journal of Applied Computer Science and Technology, 5(1), 1–8. https://doi.org/10.52158/jacost.v5i1.637

Ji, Y., Cao, Y., Cheng, X., & Zhang, Q. (2022). Research on the Application of Helmet Detection Based on YOLOv4. Journal of Computer and Communications, 10(08), 129–139. https://doi.org/10.4236/jcc.2022.108009

Kumar, T., Mileo, A., Brennan, R., & Bendechache, M. (2023). Image Data Augmentation Approaches: A Comprehensive Survey and Future directions. 6223. https://doi.org/https://doi.org/10.48550/arXiv.2301.02830

Kurnia, J. S., & Risyda, F. (2014). Rancang Bangun Penerapan Model Prototype dalam Perancangan Sistem Informasi Pencatatan Persediaan Barang Berbasis Web. JURNAL SISTEM INFORMASI UNIVERSITAS SURYADARMA, 8(2), 223–230. https://doi.org/10.35968/jsi.v8i2.737

Laily, M. E., Fajri, F. N., & Pratamasunu, G. Q. O. (2022). Deteksi Penggunaan Alat Pelindung Diri (APD) Untuk Keselamatan dan Kesehatan Kerja Menggunakan Metode Mask Region Convolutional Neural Network (Mask R-CNN). Jurnal Komputer Terapan, 8(2), 279–288. https://doi.org/10.35143/jkt.v8i2.5732

Pane, S. F., & Rahcmadani, E. V. (2020). Big Data: Forecasting Menggunakan Python. Kreatif. https://books.google.co.id/books?id=DCjZDwAAQBAJ

Purnomo, D. (2017). Model Prototyping. JIMP-Jurnal Informatika Merdeka Pasuruan, 2(2), 54–61.

Putri, D. N., & Lestari, F. (2023). Analisis penyebab kecelakaan kerja pada pekerja di proyek konstruksi : Literatur review. Jurnal Kesehatan Masyarakat, 7(1), 451–452.

Raup, A., Ridwan, W., Khoeriyah, Y., Supiana, S., & Zaqiah, Q. Y. (2022). Deep Learning dan Penerapannya dalam Pembelajaran. JIIP - Jurnal Ilmiah Ilmu Pendidikan, 5(9), 3258–3267. https://doi.org/10.54371/jiip.v5i9.805

Torang Siregar. (2023). Stages of Research and Development Model Research and Development (R&D). DIROSAT: Journal of Education, Social Sciences & Humanities, 1(4), 142–158. https://doi.org/10.58355/dirosat.v1i4.48

Tsimenidis, S., Vrochidou, E., & Papakostas, G. A. (2022). Omics Data and Data Representations for Deep Learning-Based Predictive Modeling. International Journal of Molecular Sciences, 23(20). https://doi.org/10.3390/ijms232012272

Vishwakarma, A. (2024). a Review: Machine Learning Algorithms. Data Science: Practical Approach with Python & R, 9(1), 162–175. https://doi.org/10.58532/nbennurch299

Zhang, B., Sun, C. F., Fang, S. Q., Zhao, Y. H., & Su, S. (2022). Workshop Safety Helmet Wearing Detection Model Based on SCM-YOLO. Sensors, 22(17). https://doi.org/10.3390/s22176702




DOI: http://dx.doi.org/10.30646/sinus.v22i2.843

Refbacks

  • There are currently no refbacks.


 

STMIK Sinar Nusantara

KH Samanhudi 84 - 86 Street, Laweyan Surakarta, Central Java, Indonesia
Postal Code: 57142, Phone & Fax: +62 271 716 500 

Email: ejurnal @ sinus.ac.id | https://p3m.sinus.ac.id/jurnal/e-jurnal_SINUS/

ISSN: 1693-1173 (print) | 2548-4028 (online)

Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.

View My Stats