Deteksi Helm Keselamatan Kerja Mengguankan CNN

Priyanto, Helmika Mahendra (2022) Deteksi Helm Keselamatan Kerja Mengguankan CNN. Other thesis, Institut Teknologi Sepuluh Nopember.

Text 07211840000076-Undergraduate_Thesis.pdf Restricted to Repository staff only Download (2MB)

Abstract

Helm keselamatan kerja merupakan salah satu APD yang berfungsi untuk melindungi kepala dari segala bentuk hantaman langsung ke kepala penggunanya. Terdapat aturan pemerintah yang mengatur dan mewajibkan penggunaan Alat Pelindung Diri dimana salah satunya yaitu Helm Keselamatan Kerja seperti pada Peraturan Menteri Tenaga Kerja dan Transmigrasi Republik Indonesia NOMOR PER.08/MEN/VII/2010 tentang ALAT PELINDUNG DIRI. Tetapi hal itu tidak menjamin semua pekerja mengenakan Helm Keselamatan Kerja walaupun sudah ada instruksi untuk digunakan. Masih sering didapati pekerja yang mengabaikan keselamatan kerja. Perusahaan-perusahaan yang melakukan pekerjaan pada umumnya sudah mengerahkan pengawas yang bertugas untuk mengawasi penggunaan APD dimana pengerahannya juga sudah ada aturan yang mengatur. Tetapi pengawas masih melakukan pengawasan secara manual yang dimana memiliki limitasinya sendiri seperti luas area yang dapat diawasi dan banyaknya jumlah pekerja yang harus diawasi. Maka dari itu, dalam penelitian ini diambil suatu tujuan yaitu merancang sistem yang dapat mendeteksi penggunaan helm keselamatan kerja secara real-time. Setelah dilakukan pengujian, didapatkan hasil pengujian model dengan nilai precision 0,92, recall 0,87, mAP@.5 0,9 dan untuk pengujian sistem trigger alarm didapatkan akurasi paling rendah 0,82.
==============================================================================================================================

Safety Helmet or hardhat is one of the Personal Protective Equipment whose purpose is to protect the wearer from direct impact to the head. There are regulations that state the importance and obligate the use of Personal Protective Equipment, in which the Safety Helmet is included, such as the Regulation of the Republic of Indonesia Ministry of Manpower NOMOR PER.08/MEN/VII/2010 for PERSONAL PROTECTIVE EQUIPMENT REGULATION. Despite the obligation to use a safety helmet, it does not guarantee all field workers will wear it. Companies that hold construction projects usually deploy supervisors to ensure that all workers wear safety helmets. The deployment of supervisors is also regulated by the Republic of Indonesia Ministry of Manpower. However, the current supervision method is still performed manually, which has its limitations. The vast area of construction sites and the high number of personnel are challenges for human supervisors to carry out their duties effectively. Therefore, this research aims to develop a system capable of automatically detecting personnel wearing safety helmets and those who do not, triggering an alarm when the system detects personnel not wearing a safety helmet properly. The development of the system utilizes a Convolutional Neural Network, designed for 2D recognition. After conducting tests, the performance results for the model are 0.92 for precision, 0.87 for recall, 0.92 for mAP@.5, and 0.82 for the accuracy of the detection system.

Item Type:	Thesis (Other)
Additional Information:	RSKom 006.42 Pri d-1 2022
Uncontrolled Keywords:	Visi Komputer, You Only Look Once (YOLO), Helm Keselamatan Kerja. Computer Vision, You Only Look Once YOLO, Safety Helmet.
Subjects:	Q Science > QA Mathematics > QA75 Electronic computers. Computer science. EDP
Divisions:	Faculty of Intelligent Electrical and Informatics Technology (ELECTICS) > Computer Engineering > 90243-(S1) Undergraduate Thesis
Depositing User:	Mr. Marsudiyana -
Date Deposited:	17 Jun 2026 06:59
Last Modified:	17 Jun 2026 06:59
URI:	http://repository.its.ac.id/id/eprint/133859

Actions (login required)

View Item