2020, Vol.25, No.12

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

In this paper, we propose a novel method for converting the existing 2D processes in the design and construction phase of civil engineering, to the future BIM-based processes. First, we compare and analyze the actual application processes of the outputs of the existing 2D method and the outputs of the 3D BIM method, for the whole process of BIM design of earthworks and road structures and integrated utilization of quantity, process(4D) and construction cost(5D), in view of life-cycle. The proposed method acquire the outputs of the design phase integrating IFC international common standard file information and CBS/OBS/WBS standard classification scheme information, and acquire the outputs of the construction stage by using an integrated utilization module for quantity, process(4D) and construction cost(5D). Ultimately, we intend to commercialize the step by step technologies for BIM design and construction in civil engineering by using the proposed method.

As the number of households with companion animals increases, the demand to monitor the health of companion animals in remote locations far away is increasing. We are going to put a wearable device on a companion animal so that it can monitor the heart beat signal from a remote location. However, the monitoring method using Bluetooth has some disadvantages. it can be accessed only in a short distances. In case of WiFi, large power consumption is the problem. To overcome these issues, we propose a system to reduce power consumption by indirectly receiving a user's request using Bluetooth at a time when the user does not need it, and sending sensor data through WiFi when the user makes a monitoring request.

In this paper, we empirically compare the effectiveness of training models to recognize beauty-related skin disease using supervised deep learning algorithms. Recently, deep learning algorithms are being actively applied for various fields such as industry, education, and medical. For instance, in the medical field, the ability to diagnose cutaneous cancer using deep learning based artificial intelligence has improved to the experts level. However, there are still insufficient cases applied to disease related to skin beauty. This study experimentally compares the effectiveness of identifying beauty-related skin disease by applying deep learning algorithms, considering CNN, ResNet, and SE-ResNet. The experimental results using these training models show that the accuracy of CNN is 71.5% on average, ResNet is 90.6% on average, and SE-ResNet is 95.3% on average. In particular, the SE-ResNet-50 model, which is a SE-ResNet algorithm with 50 hierarchical structures, showed the most effective result for identifying beauty-related skin diseases with an average accuracy of 96.2%. The purpose of this paper is to study effective training and methods of deep learning algorithms in consideration of the identification for beauty-related skin disease. Thus, it will be able to contribute to the development of services used to treat and easy the skin disease.