• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.8
• /
• pp.1103-1110
• /
• 2022

Due to the rapid development of AI-related industries, countless edge devices are working in the real world. Since data generated within the smart space consisted of these devices is beyond imagination, it is becoming increasingly difficult for edge devices to process. To solve this issue, EdgeCPS has appeared. EdgeCPS is a technology to support harmonious execution of various application services including AI applications through interworking between edge devices and edge servers, and augmenting resources/functions. Therefore, we propose a knowledge-sharing graph-based componentized AI application support system applicable to the EdgeCPS platform. The graph is designed to effectively store information which are essential elements for creating AI applications. In order to easily change resource/function augmentation under the support of the EdgeCPS platform, AI applications are operated as components. The application support system is linked with the knowledge graph so that users can easily create and test applications, and visualizes the execution aspect of the application to users as a pipeline.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.5
• /
• pp.161-168
• /
• 2021

Cracks affect the robustness of infrastructures such as buildings, bridge, pavement, and pipelines. This paper presents an automated crack detection system which detect cracks in diverse surfaces. We first constructed the combined crack dataset, consists of multiple crack datasets in diverse domains presented in prior studies. Then, state-of-the-art deep learning models in computer vision tasks including VGG, ResNet, WideResNet, ResNeXt, DenseNet, and EfficientNet, were used to validate the performance of crack detection. We divided the combined dataset into train (80%) and test set (20%) to evaluate the employed models. DenseNet121 showed the highest accuracy at 96.20% with relatively low number of parameters compared to other models. Based on the validation procedures of the advanced deep learning models in crack detection task, we shed light on the cost-effective automated crack detection system which can be applied to different surfaces and structures with low computing resources.

• The Journal of the Convergence on Culture Technology
• /
• v.8 no.3
• /
• pp.183-189
• /
• 2022

COVID-19 is also influencing the coffee industry. This will increase untact consumption, a new consumption trend. Consumption utilizing online channels and delivery service applications that represent untact consumption is becoming commonplace. The coffee industry is also increasingly using coffee shops with drive-through and smart ordering systems that can be ordered with minimal contact. While most of the untact services are preempted at franchise stores, many independent coffee shops still offer differentiated services by communicating directly with customers. However, along with the prolonged COVID-19 infection, coffee shops in the present era, which cannot be free from infectious diseases, have no choice but to worry about delivery services. Therefore, this study analyzed the factors that influence coffee delivery services. Research results due to the influence of COVID-19, regular delivery services have increased along with coffee delivery services. Regular delivery services will play a central role in coffee delivery services due to increased use of home cafes by consumers who want to enjoy coffee in various ways.

• Journal of Cadastre & Land InformatiX
• /
• v.52 no.1
• /
• pp.81-93
• /
• 2022

Recently, there have been many studies on object recognition around the vehicle and recognition of traffic signs and traffic lights in autonomous driving. In particular, such the recognition of traffic lights is one of the core technologies in autonomous driving. Therefore, many studies for such the recognition of traffic lights have been performed, the studies based on various deep learning models have increased significantly in recent. In addition, as a high-quality AI training data set for voice, vision, and autonomous driving is released on AIHub, it makes it possible to develop a recognition model for traffic lights suitable for the domestic environment using the data set. In this study, we developed a recognition model for traffic lights that can be used in Korea using the AIHub's training data set. In particular, in order to improve the recognition performance, we used various models of YOLOv4 and YOLOv5, and performed our recognition experiments by defining various classes for the training data. In conclusion, we could see that YOLOv5 shows better performance in the recognition than YOLOv4 and could confirm the reason from the architecture comparison of the two models.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.22 no.1
• /
• pp.141-151
• /
• 2022

Wireless earphones are products that are consumed together with smart devices (mobile phones, etc), and there is no twisting and convenience compared to general earphones. However, due to the lack of information on the quality of wireless earphones, consumers tend to purchase products based on brand awareness, and manufacturers deliver information to consumers based on different standards for each product due to the lack of standards for measurement methods for quality evaluation. In particular, the playback time of wireless earphones is a factor that can directly affect consumers' purchases, so it is necessary to prepare a standardized test method to properly measure it. This paper introduces the current status of wireless earphones and related standard trends, and proposes a method for measuring the audio playback time of wireless earphones developed through this. In addition, this measurement method will be proposed as an international standard (IEC) after being established as the national standard, the Korean Industrial Standard (KS).

• The Journal of the Convergence on Culture Technology
• /
• v.8 no.6
• /
• pp.135-140
• /
• 2022

In this study, we conducted a care farm program that is currently being operated as a pilot in a care farm in Korea, interviewed the experiences and feelings of dementia patients who experienced this as a patient care-giver, and confirmed the strengths and weaknesses of the care farm program. Accordingly, we investigated the points for improvement and the characteristics of the program in the care farm program and operation. In particular, opinions are gathered on the use of a care farm in the early stages of dementia, accessibility issues from residence to the care farm, continuity of various programs and programs, and development of seasonal content. In order to develop a program related to care agriculture for dementia patients by using healing agriculture in future care farms, it is necessary to consider factors such as use problems, accessibility, diversity, continuity, and seasonality of early dementia patients.

• Journal of Korea Water Resources Association
• /
• v.55 no.spc1
• /
• pp.1187-1195
• /
• 2022

To run the algorithm for identifying the segments of a pipe network, the relative positional relation between nodes, pipes, and valves should be prepared as input information of a segment search algorithm. In order to more accurately identify the segments of real pipe network, pipe network GIS/CAD database that contains all isolation valves is more suitable than modeled pipe network information used for a hydraulic analysis program. In this study, we developed an algorithm that can establish the relative positional relations among node-pipe-valve suitable for pipe network segment search algorithms using GIS/CAD data of a real water supply network, and developed a MATLAB program that can implement it. The effectiveness of the developed MATLAB program was confirmed by applying it to a portion of a real municipal pipe network.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.1
• /
• pp.655-661
• /
• 2023

Big data, an important element of the 4th industrial revolution, is actively opening public data in public institutions and local governments. In the public data portal, everyone can conveniently search for data and check related data, but only those in ICT-related fields are using public data. Although data held by public institutions is open to citizens, it is difficult for anyone to easily utilize public data to develop applications. In this paper, data provided in open API format from public data portals has XML and JSON formats. In this study, we are a method of modularizing public data in XML format into a part that can be easily developed by linking it to a GUI interface. Based on the necessary public data, we propose a way to easily develop mobile programs and promote the use of public data.

• Journal of Advanced Navigation Technology
• /
• v.27 no.2
• /
• pp.173-181
• /
• 2023

Aircraft carriers need to maintain an orderly flow of aircraft in order for military ships to conduct combat through aircraft. Maintaining aircraft flow is an important factor in strengthening ship and aviation safety. In order to maintain aircraft flow, it is essential to develop a state-of-the-art air control system that provides higher quality control information by simultaneously accommodating radar-based monitoring information and monitoring information based on CNS integrated technology. Based on this point, this study describes the function and operation method of specific control equipment for the operation of the Aviation Support System and Air Traffic Control System required to operate light aircraft carriers in Korea based on overseas cases.

• Journal of the Korean Geotechnical Society
• /
• v.24 no.11
• /
• pp.55-60
• /
• 2008

This paper presents how the load transfer mechanism of the ground anchor affects on the stability analysis of anchored slope. The finite element analysis and the conventional limit equilibrium analysis on the anchored slope were performed and compared. The limit equilibrium analysis of the anchored slope is widely used in design practice due to the easiness of the analysis. However, the load transfer mechanism is not considered properly for the analysis. When the failure surface passes through the bonded length of an anchor, the anchor load is disregarded and the factor of safety for the anchored slope is smaller than it should be. In this study, the load transfer distribution was incorporated into the limit equilibrium stability analysis of the anchored slope and the results were compared with those of finite element analysis.