Publication Date: 2022/03/02
Abstract: Since 2019, there has been a new virus that has changed the world order. This outbreak was named the Covid-19 pandemic and was caused by a virus called the corona virus or severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). The virus has been detected in Indonesia since early March 2020, and until now it has not been well resolved, even though a vaccine has been found (Kemenkes RI, 2020). In fact, recently the Omicron variant caused by SARS-CoV-2 B.1.1.529 was reported to have begun to be detected in Indonesia after positive cases of the corona virus began to subside (Ministry of Health of the Republic of Indonesia, 2021). Wearing a mask is one of the most effective ways to prevent the spread of the corona virus. Based on data from the Covid-19 Handling Task Force (2021) on the behavior of wearing masks in 2021, there are 76-90% of Indonesians who comply. The percentage of people who comply with wearing masks seen from the data is quite high, unfortunately the data was taken only by monitoring about 4 million Indonesians. In fact, the number of Indonesian people far exceeds that number. In addition, monitoring that cannot be carried out at any time makes this effort less effective. The above problems encourage the creation of innovative products that can help provide effective solutions, namely the Face Recognition application which can detect whether a person is wearing a mask or not in certain places. This application is one of the Deep Learning methods , namely Convolutional Neural Network (CNN) and Transfer Learning . The results of this study are CNN's modeling to classify mask users and the interface design of the application.
Keywords: COVID-19; Convolutional Neural Networks; Masks; Transfer Learning
DOI: https://doi.org/10.5281/zenodo.6321487
PDF: https://ijirst.demo4.arinfotech.co/assets/upload/files/IJISRT22FEB461.pdf
REFERENCES