Analisis Algoritma Yolo V11n Untuk Deteksi Kepatuhan Penggunaan Alat Pelindung Diri Pada Live Cam

Shandy Satria Nugraha; Teguh Iman  Hermanto; Muhammad Rafi Muttaqin

Authors

Shandy Satria Nugraha STT Wastukancana Purwakarta
Teguh Iman Hermanto STT Wastukancana Purwakarta
Muhammad Rafi Muttaqin STT Wastukancana Purwakarta

Keywords:

alat pelindung diri, computer vision, live cam, real-time, YOLOv11n

Abstract

Penerapan Keselamatan dan Kesehatan Kerja (K3) merupakan aspek krusial di sektor industri. Meskipun demikian, pemantauan kepatuhan penggunaan Alat Pelindung Diri (APD) secara manual sangat rentan terhadap kelalaian manusia, sementara kamera pengawas statis kerap memiliki keterbatasan area pantau. Penggunaan kamera langsung (live cam) portabel menawarkan fleksibilitas pengawasan seketika, namun menuntut arsitektur kecerdasan buatan yang sangat efisien secara komputasi. Oleh karena itu, penelitian ini bertujuan untuk mengevaluasi kinerja algoritma YOLOv11n (Nano) dalam mengidentifikasi enam kelas target (pekerja, helm, kacamata, sarung tangan, sepatu, dan kemeja reflektor) serta mengintegrasikannya pada sebuah antarmuka web. Metodologi penelitian menerapkan kerangka kerja OSEMN menggunakan 346 data citra privat. Fase pelatihan dieksekusi selama 50 epoch dengan memanfaatkan augmentasi data dinamis guna menyimulasikan kondisi riil di lapangan. Hasil pengujian memvalidasi bahwa model sukses mencatatkan nilai rata-rata presisi (mean Average Precision/mAP50) sebesar 99,2%. Model prediksi selanjutnya dikonversi ke dalam format TensorFlow.js untuk dijalankan secara murni pada peramban klien (client-side). Sistem ini mengadopsi algoritma irisan spasial guna menentukan status kepatuhan, di mana insiden pelanggaran secara otomatis ditransmisikan ke dalam basis data awan Firebase Firestore yang dikendalikan oleh filter pencegah duplikasi data. Kesimpulannya, YOLOv11n terbukti sangat presisi, tangguh, dan berbobot ringan untuk mewujudkan instrumen audit K3 yang terotomatisasi secara komprehensif.

References

[1] V. Saxena, “Evolution of International Occupational Health and Safety Management Systems,” BARC newsletter, 2024.

[2] M. I. B. Ahmed et al., “Personal Protective Equipment Detection: A Deep-Learning-Based Sustainable Approach,” Sustainability (Switzerland), vol. 15, no. 18, 2023, doi: 10.3390/su151813990.

[3] J. H. Lo, L. K. Lin, and C. C. Hung, “Real-Time Personal Protective Equipment Compliance Detection Based on Deep Learning Algorithm,” Sustainability (Switzerland), vol. 15, no. 1, 2023, doi: 10.3390/su15010391.

[4] A. J. Moshayedi, A. S. Roy, A. Taravet, L. Liao, J. Wu, and M. Gheisari, “A secure traffic police remote sensing approach via a deep learning-based low-altitude vehicle speed detector through uavs in smart cites: Algorithm, implementation and evaluation,” Future transportation, vol. 3, no. 1, pp. 189–209, 2023.

[5] X. Suo, W. Tang, and Z. Li, “Motion Capture Technology in Sports Scenarios: A Survey,” 2024. doi: 10.3390/s24092947.

[6] Y. Tao, B. Li, P. Li, J. Qian, and L. Qi, “Improved Lightweight YOLOv11 Algorithm for Real-Time Forest Fire Detection,” Electronics (Switzerland), vol. 14, no. 8, 2025, doi: 10.3390/electronics14081508.

[7] J. Ordrick, G. Wibowo, A. Fahmi, I. Kurniawan, and E. Haq, “YOLOv11-Based Automated PPE Detection System for Workplace Safety Monitoring in Electric Power Distribution Operations,” Journal of Information Systems and Informatics, vol. 7, no. 4, Dec. 2025, doi: 10.63158/journalisi.v7i4.1379.

[8] M. E. Laily, F. N. Fajri, and G. Q. O. Pratamasunu, “Deteksi Penggunaan Alat Pelindung Diri (APD) Untuk Keselamatan dan Kesehatan Kerja Menggunakan Metode Mask Region Convolutional Neural Network (Mask R-CNN),” Jurnal Komputer Terapan, vol. 8, no. 2, 2022, doi: 10.35143/jkt.v8i2.5732.

[9] M. Sambetbayeva et al., “A Multi-Level Annotation Model for Fake News Detection: Implementing Kazakh-Russian Corpus via Label Studio,” Big Data and Cognitive Computing, vol. 9, no. 8, p. 215, 2025.

[10] International Labour Organization, “Issue Paper: OSH Statistics - Supporting the review and update of the international OSH statistical standards at the 22nd ICLS in 2028.,” Geneva, Oct. 2025. Accessed: Mar. 15, 2026. [Online]. Available: https://www.google.com/url?sa=t&source=web&rct=j&opi=89978449&url=https://www.ilo.org/sites/default/files/2025-11/TWG_OSH_Issue_Paper_2025_10_22.pdf&ved=2ahUKEwjOyMCE96CTAxUTxzgGHQ2WLwQQFnoECBgQAQ&usg=AOvVaw2ozrik-5V7DClLkihW_8e-

[11] M. M. Taye, “Understanding of Machine Learning with Deep Learning: Architectures, Workflow, Applications and Future Directions,” 2023. doi: 10.3390/computers12050091.

[12] J. Zhao, S. Miao, R. Kang, L. Cao, L. Zhang, and Y. Ren, “Insulator defect detection algorithm based on improved YOLOv11n,” Sensors, vol. 25, no. 5, p. 1327, 2025.

[13] K. Shameti and B. Cico, “Comparison of Methodological Approaches: CRISP-DM vs OSEMN Methodology Using Linear Regression and Statistical Analysis,” in Balkan Conference in Informatics, Springer, 2024, pp. 47–60.

[14] A. Hayat and F. Morgado-Dias, “Deep learning-based automatic safety helmet detection system for construction safety,” Applied Sciences, vol. 12, no. 16, p. 8268, 2022.