Classification of the use of safety helmets in construction projects using the Convolutional Neural Network
Abstract
The implementation of Health, Safety, and Environment (HSE) encounters several problems, including workers who are not accustomed to working on projects that apply Health, Safety, and Environment (HSE) standards will feel uncomfortable using personal protective equipment, especially for head protection in the form of safety helmets. The next problem is that the construction project of buildings or bridges as a work location has certain places that are protected from the sight of the HSE supervisory team so it is not optimal in monitoring the completeness of personal protective equipment at work. Another problem is the high workload factor for the HSE supervisory team to supervise all the workers, which is very large so it is not optimal in supervising the completeness of personal protective equipment for these workers. To overcome these problems, it is necessary to develop an automatic monitoring system for personal protective equipment, especially safety helmets. The way the system works is that perform classification through digital images with a size of 150x150 pixels using the Convolutional Neural Network (CNN) method for the use of safety helmets at the construction project site. The CNN architectural model used is two convolutional layers and a fully connected layer with 3x3 kernel parameters with 80 filters so that it produces 32 feature maps in the 10th epoch, with an accuracy of 63% obtained.
Full Text:
PDFReferences
UU RI Nomor 1, “Undang-Undang Republik Indonesia Nomor 1 Tahun 1970 Tentang Keselamatan Kerja,” Pres. Republik Indones., no. 14, pp. 1–20, 1970, [Online]. Available: https://jdih.esdm.go.id/storage/document/uu-01-1970.pdf
Kementerian Tenaga Kerja, Peraturan Menteri Tenaga Kerja Nomor : Per. 05/Men/1996 Tentang Sistem Manajemen Keselamatan Dan Kesehatan Kerja, vol. 5. 1996, pp. 1–42.
B. Widodo, H. A. Armanto, and E. Setyati, “Deteksi Pemakaian Helm Proyek Dengan Metode Convolutional Neural Network,” J. Intell. Syst. Comput., vol. 3, no. 1, pp. 23–29, 2021, doi: 10.52985/insyst.v3i1.157.
S. Sugianto, “Deteksi Alat Pelindung Kepala (Helm) Menggunakan Metode Haar Cascade Classifier,” Joutica, vol. 4, no. 1, p. 189, 2019, doi: 10.30736/jti.v4i1.283.
A. H. M. Rubaiyat et al., “Automatic detection of helmet uses for construction safety,” Proc. - 2016 IEEE/WIC/ACM Int. Conf. Web Intell. Work. WIW 2016, pp. 135–142, 2017, doi: 10.1109/WIW.2016.10.
J. Shen, X. Xiong, Y. Li, W. He, P. Li, and X. Zheng, “Detecting safety helmet wearing on construction sites with bounding-box regression and deep transfer learning,” Comput. Civ. Infrastruct. Eng., vol. 36, no. 2, pp. 180–196, 2021, doi: 10.1111/mice.12579.
Y. Roh, G. Heo, and S. E. Whang, “A Survey on Data Collection for Machine Learning: A Big Data-AI Integration Perspective,” IEEE Trans. Knowl. Data Eng., vol. 33, no. 4, pp. 1328–1347, 2021, doi: 10.1109/TKDE.2019.2946162.
Q. H. Nguyen et al., “Influence of data splitting on performance of machine learning models in prediction of shear strength of soil,” Math. Probl. Eng., vol. 2021, 2021, doi: 10.1155/2021/4832864.
E. Rezende, G. Ruppert, T. Carvalho, F. Ramos, and P. De Geus, “Malicious software classification using transfer learning of ResNet-50 deep neural network,” Proc. - 16th IEEE Int. Conf. Mach. Learn. Appl. ICMLA 2017, vol. 2017-Decem, pp. 1011–1014, 2017, doi: 10.1109/ICMLA.2017.00-19.
S. Afaq and S. Rao, “Significance Of Epochs On Training A Neural Network,” Int. J. Sci. Technol. Res., vol. 9, no. 6, pp. 485–488, 2020.
J. Dj Novakovic, A. Veljovi, S. S. Ili, ˇ Zeljko Papi, and M. Tomovi, “Evaluation of Classification Models in Machine Learning,” Theory Appl. Math. Comput. Sci., vol. 7, no. 1, pp. 39–46, 2017.
Refbacks
- There are currently no refbacks.