2021, Vol.26, No.5

Journal of The Korea Society of Computer and Information 2023 KCI Impact Factor : 0.65

pISSN : 1598-849X / eISSN : 2383-9945
https://journal.kci.go.kr/jksci

Coronavirus disease 2019 (COVID-19) has affected the world seriously. Every person is required for wearing a mask properly in a public area to prevent spreading the virus. However, many people are not wearing a mask properly. In this paper, we propose an efficient mask detection system. In our proposed system, we first detect the faces of input images using YOLOv5 and classify them as the one of three scene complexity classes (Simple, Moderate, and Complex) based on the number of detected faces. After that, the image is fed into the Faster-RCNN with the one of three ResNet (ResNet-18, 50, and 101) as backbone network depending on the scene complexity for detecting the face area and identifying whether the person is wearing the mask properly or not. We evaluated our proposed system using public mask detection datasets. The results show that our proposed system outperforms other models.

In this paper, we propose a building exploration drone that can be used for a digital twin-based building control system. The existing building control system using a fixed position sensor box has a problem that a management blind spot occurs. And because people patrol themselves, it takes a lot of human resources. In this paper, a drone equipped with a temperature and humidity sensor and a gas leak detection sensor is used to search the internal path of the building centering on the control blind spot. It also aims to solve the problem of the building control system by transmitting information in real time along with the video. In addition, it has a stable hovering function using an optical floor sensor and can be applied to an existing digital twin-based building control system. The results of this study are believed to be of great help in improving the quality of digital twin control systems using drones.

With the application of the Data 3 method, the scope of the use of pseudonym information has expanded. In the case of pseudonym information, a specific individual can be identified by linking and combining with various data, and personal information may be leaked due to incorrect use of the pseudonym information. In this paper, we propose the scope of use of data is subdivided and a differentiated pseudonym information processing method according to the scope. For the study, the formula was modified by using zero-knowledge proof among the pseudonym information processing methods, and when the proposed formula was applied, it was confirmed that the performance improved by an average of 10% in terms of verification time compared to the case of applying the formula of the existing zero-knowledge proof.