• KEPCO Journal on Electric Power and Energy
• /
• v.7 no.1
• /
• pp.79-84
• /
• 2021

The fundamental element to be kept for big data analysis, artificial intelligence technologies and asset management system is a data quality, which could directly affect the entire system reliability. For this reason, the momentum of data cleaning works is recently increased and data cleaning methods have been investigating around the world. In the field of electric power, however, asset data cleaning methods have not been fully determined therefore, automatic cleaning algorithm of asset data for transmission cables has been studied in this paper. Cleaning algorithm is composed of missing data treatment and outlier data one. Rule-based and expert opinion based cleaning methods are converged and utilized for these dirty data.

• Journal of Korea Multimedia Society
• /
• v.24 no.8
• /
• pp.1122-1137
• /
• 2021

PM_2.5 concentration in Seoul could be predicted by deep neural network model. In this paper, the contribution of input factors to the model's prediction results is analyzed using the LRP(Layer-wise Relevance Propagation) technique. LRP analysis is performed by dividing the input data by time and PM concentration, respectively. As a result of the analysis by time, the contribution of the measurement factors is high in the forecast for the day, and those of the forecast factors are high in the forecast for the tomorrow and the day after tomorrow. In the case of the PM concentration analysis, the contribution of the weather factors is high in the low-concentration pattern, and that of the air quality factors is high in the high-concentration pattern. In addition, the date and the temperature factors contribute significantly regardless of time and concentration.

• International Journal of Internet, Broadcasting and Communication
• /
• v.14 no.2
• /
• pp.136-146
• /
• 2022

Some surface defects make the weak quality of steel materials. To limit these defects, we advocate a one-stage detector model RetinaNet among diverse detection algorithms in deep learning. There are several backbones in the RetinaNet model. We acknowledged two backbones, which are ResNet50 and VGG19. To validate our model, we compared and analyzed several traditional models, one-stage models like YOLO and SSD models and two-stage models like Faster-RCNN, EDDN, and Xception models, with simulations based on steel individual classes. We also performed the correlation of the time factor between one-stage and two-stage models. Comparative analysis shows that the proposed model achieves excellent results on the dataset of the Northeastern University surface defect detection dataset. We would like to work on different backbones to check the efficiency of the model for real world, increasing the datasets through augmentation and focus on improving our limitation.

• Electronics and Telecommunications Trends
• /
• v.37 no.1
• /
• pp.21-31
• /
• 2022

Human behavior and emotions are influenced by experiences accumulated through the past and present. To realize artificial intelligence technology that understands and sympathizes with humans, cognitive computing technology that automatically analyzes human behaviors, habits, and emotions associated with specific situations and uses past data and domain knowledge is required. In this study, we examine the latest research trends on human-understanding cognitive computing technology that recognizes human behavior and emotions, stores them as experience data, and provides services by analyzing the stored data. Further, we introduce high-quality data collection research in real-life and services for improving physical and mental health. We also review key issues essential for developing these technologies.

• The Journal of Korea Robotics Society
• /
• v.17 no.2
• /
• pp.103-109
• /
• 2022

The purpose of this study is to ethical review on the development and service with care assistance robot. An integrative review concept analysis method was used. We analyzed the classification and role of service robots, the concept of the robot ethic and the care ethic. And there were derived the development and service about care assistance robot in ethical viewpoint. For improving current care problem, government had support to developing four types care assistance robots. But there were provided carefully care service due to the limitations of robot technology and lack of overall social awareness with care robot. In addition, in order to be successfully application in the field, care assistance robots were developed to provide high-quality care service that can consider to personal culture and living environment with the development of artificial intelligence and robot technology, as well as ethical care service.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.168-169
• /
• 2022

As the electric vehicle market has grown rapidly, the battery market has grown exponentially. Due to the gap between the generation speed of quality control technology and battery mass production speed for batteries mounted on electric vehicles, many durability problems have arisen for batteries. Most accidents are caused by electrical factors, but there is no technology to quickly inspect them. In this paper, we are going to propose a quick analysis of battery cell defects using the GAN model.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2020.11a
• /
• pp.57-58
• /
• 2020

Recently, government office buildings have become important in reducing maintenance costs. However, the loss of information raised a problem for maintenance work that could not meet the needs of users. Therefore, this study proposed a BIM-based integrated maintenance system for public offices in Jeju to efficiently maintenance work. The system can be integrated with IoT sensors, big data and artificial intelligence technologies to integrate information that occurs throughout the building's entire life cycle to exchange information. This system is also scalable to buildings, plants, region and urban infrastructure facilities as well as single buildings. It is expected that the system will provide reliable, high-quality, real-time information for efficient maintenance work, thereby supporting decision making and appropriate budget planning.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2021.05a
• /
• pp.257-258
• /
• 2021

Construction robotics is rapidly forming a market in conjunction with the development of sensing and artificial intelligence technologies. The layout work for accurately constructing the shape and dimensions of the building frame requires high accuracy and precision, and is one of the high demands for productivity and quality improvement through construction automation. Thus, as a preliminary study, we derived the elemental factors and performance requirements for developing an automated layout robot. In addition, alternatives on driving and marking units were investigated based on literature review and practioner's interview. The result of this study will be used as a basic data for the layout robot design.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2023.05a
• /
• pp.349-350
• /
• 2023

In the field of domestic construction, 3D modeling mainly targets outdoor construction sites, and acquires outdoor spatial information by operating UAVs and UGVs equipped with cameras. 3D modeling of construction sites tends to expand its scope to indoors along with the increasing demand for site monitoring and management through indoor spatial information. In the case of indoors, it is impossible to shoot with a drone after the framework and outer walls of the building are completed, so it is necessary to collect indoor spatial information and 3D modeling using a 360 camera. The purpose of this study is limited to basic research to establish a process that can obtain simple and high-quality indoor 3D modeling results using indoor data collected from 360 cameras.

• Annual Conference of KIPS
• /
• 2023.11a
• /
• pp.430-431
• /
• 2023

교육 분야에서는 각 학생의 특성과 요구에 부응하는 개인화 교육의 중요성이 증가하고 있다. 이에 따라 인공지능 기반의 튜터링 시스템, 특히 대화 기반의 튜터링이 주목받고 있다. 본 연구는 GPT-3.5-turbo 를 사용하여 데이터를 생성하는 과정에서 프롬프트 설계의 중요성과 인간의 감수 과정의 필요성을 확인했다. 또한, 자동 평가 방법을 제안하여 데이터의 품질과 유용성을 평가하였다.