• Proceedings of the Korean Society of Computer Information Conference
• /
• 2022.07a
• /
• pp.81-84
• /
• 2022

제조 산업에서의 이상치 검출은 생산품의 품질과 운영비용을 절감하기 위한 중요한 요소로 최근 딥러닝을 사용하여 자동화되고 있다. 이상치 검출을 위한 딥러닝 기법에는 CNN이 있으며, CNN을 계층적으로 구성할 경우 단일 CNN 모델에 비해 상대적으로 성능의 향상을 보일 수 있다는 것이 많은 선행 연구에서 나타났다. 이에 MVTec-AD 데이터셋을 이용하여 계층 CNN이 다중 클래스 이상치 판별 문제에 대해 효과적인지를 탐구하고자 하였다. 실험 결과 단일 CNN의 정확도는 0.7715, 계층 CNN의 정확도는 0.7838로 다중 클래스 이상치 판별 문제에 있어 계층 CNN 방식 접근이 다중 클래스 이상치 탐지 문제에서 알고리즘의 성능을 향상할 수 있음을 확인할 수 있었다. 계층 CNN은 모델과 파라미터의 개수와 리소스의 사용이 단일 CNN에 비하여 기하급수적으로 증가한다는 단점이 존재한다. 이에 계층 CNN의 장점을 유지하며 사용 리소스를 절약하고자 하였고 K-means, GMM, 계층적 클러스터링 알고리즘을 통해 제작한 새로운 클래스를 이용해 계층 CNN을 구성하여 각각 정확도 0.7930, 0.7891, 0.7936의 결과를 얻을 수 있었다. 이를 통해 Clustering 알고리즘을 사용하여 적절히 물체를 분류할 경우 물체에 따른 개별 상태 판단 모델을 제작하는 것과 비슷하거나 더 좋은 성능을 내며 리소스 사용을 줄일 수 있음을 확인할 수 있었다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.344-345
• /
• 2022

ogy is being used in many fields, such as smart farms, smart oceans, smart homes, and smart energy. Various IoT terminals are used for these IoT services. Here, IoT devices are physically installed in various places. A malicious attacker can access the IoT service using an unauthorized IoT device, access unauthorized important information, and then modify it. In this study, to solve these problems, we propose an authentication system for IoT devices used in IoT services. The IoT device authentication system proposed in this study consists of an authentication module mounted on the IoT device and an authentication module of the IoT server. If the IoT device authentication system proposed in this study is used, only authorized IoT devices can access the service and access of unauthorized IoT devices can be denied. Since this study proposes only the basic IoT device authentication mechanism, additional research on additional IoT device authentication functions according to the security strength is required.IoT technol

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.33 no.6
• /
• pp.947-960
• /
• 2023

In Korea, traditional paper promissory notes are currently undergoing a transformation, being gradually replaced by electronic notes. This transformation is being steered under the Korea Financial Telecommunications Institute, a trusted authority. However, existing electronic systems have security vulnerabilities, including the risk of hacking and internal errors within the institute. To this end, we have defined a novel anonymous electronic promissory note system based on blockchain. We have constructed a concrete protocol and conducted security analysis of our protocol. Note that, in our protocol, every note information is committed so that the note remains undisclosed until the point of payment. Once the note information becomes public on the blockchain, it enables the detection of illicit activities, such as money laundering and tax evasion. Furthermore, our protocol incorporates a feature of split endorsement, which is a crucial functionality permitted by the Korean electronic note system. Consequently, our proposed protocol is suitable for practical applications in financial transactions.

• Journal of the Microelectronics and Packaging Society
• /
• v.30 no.4
• /
• pp.69-78
• /
• 2023

With the rapid growth of artificial intelligence, the demand for semiconductors is enormously increasing everywhere. To ensure the manufacturing quality and quantity simultaneously, the importance of automatic defect detection during the packaging process has been re-visited by adapting various deep learning-based methodologies into automatic packaging defect inspection. Deep learning (DL) models require a large amount of data for training, but due to the nature of the semiconductor industry where security is important, sharing and labeling of relevant data is challenging, making it difficult for model training. In this study, we propose a new framework for securing sufficient data for DL models with fewer computing resources through a divide-and-conquer approach. The proposed method divides high-resolution images into pre-defined sub-regions and assigns conditional labels to each region, then trains individual sub-regions and boundaries with boundary loss inducing the globally coherent and seamless images. Afterwards, full-size image is reconstructed by combining divided sub-regions. The experimental results show that the images obtained through this research have high efficiency, consistency, quality, and generality.

• Journal of Korean Society of Archives and Records Management
• /
• v.23 no.4
• /
• pp.1-24
• /
• 2023

At present, domestic archives within the realm of performing arts predominantly focus on recording through videos, yet they often lack comprehensive documentation of crucial production processes and content services. Recognizing the contemporary significance of archival content services, this study analyzes the archival content within the national performing arts archives websites of the United Kingdom and the United States, serving as international benchmarks. The findings extrapolate insights and implications to propose enhancements for the Museum of Performing Arts in the National Theater of Korea. The analysis focused mainly on the missions and visions on the websites, examining 107 contents from the UK National Theater, 27 from the United States, and 9 from Korea. The suggested improvements encompass clarifying target users and execution tasks in the mission and vision statements, fostering expert collaborations, incorporating preview features, curating content with a single theme, and organizing a comprehensive list on the National Theater's YouTube channel.

• Journal of the Korea Society for Simulation
• /
• v.32 no.4
• /
• pp.59-67
• /
• 2023

Private blockchains can apply enhanced security policies that allow only authorized users to participate in the blockchain network. In addition, when used in a career management system where the validity of an individual's career is important, it has the suitable characteristics in terms of information integrity. However, due to the excessive performance requirements of blockchain technology, identifying performance characteristics through simulation can be helpful in stable operation of the system. This paper presents research results that utilized performance evaluation results while constructing a career management system based on the Ethereum blockchain. The service not only serves as a portfolio that records personal career development activities, certification acquisition, and award results, but also provides a community function for career planning to strengthen employment competitiveness. In addition, we present how a compensation policy can be executed to encourage users to participate in career development through community activities. In particular, an appropriate compensation policy was derived by reviewing changes in performance characteristics in accordance with the transaction volume on Geth nodes.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.6
• /
• pp.77-87
• /
• 2024

In this paper, we propose a study applying the Delphi technique to domestic blockchain experts to determine urgent and pivotal conditions for NFT proliferation. We examine these conditions from a PEST (Political, Economic, Social, and Technological Analysis of the Macro Environment) perspective, as well as the functions of digital assets (measurement, storage, and exchange). Through two rounds of expert surveys on the seven NFT perspectives, we identify 6 activating factors that can help guide future policy-making for the NFT market. These factors have broad implications for the development of new industries using blockchain technology and tokens. The Delphi method employed in this study is a group discussion technique that gathers opinions from experts anonymously through two rounds and to address drawbacks related to expert selection bias and opinion alignment, additional opinion collection and review of projections were conducted in each round.

• Journal of Internet Computing and Services
• /
• v.25 no.1
• /
• pp.177-188
• /
• 2024

As technology evolves, Internet usage continues to grow, resulting in a geometric increase in network traffic and communication volumes. The network path selection process, which is one of the core elements of the Internet, is becoming more complex and advanced as a result, and it is important to effectively manage and analyze it, and there is a need for a representation and visualization method that can be intuitively understood. To this end, this study designs a framework that analyzes network data using BGP, a network path selection method, and applies it to the cyber common operating picture for situational awareness. After that, we analyze the visualization elements required to visualize the information and conduct an experiment to implement a simple visualization. Based on the data collected and preprocessed in the experiment, the visualization screens implemented help commanders or security personnel to effectively understand the network situation and take command and control.

• Journal of the Korean Society for information Management
• /
• v.41 no.1
• /
• pp.283-311
• /
• 2024

This study examined the factors affecting the intention of the public to share electronic medical records(EMR) based on the theory of reasoned action and the privacy calculus model. It also investigated whether the purpose of EMR sharing varies depending on personal characteristics, such as the degree of interest in health and personal medical history. According to an online survey of 145 people, altruistic enjoyment, awareness of personal information protection, recognition of legal and institutional roles, and interest in health had a positive impact on the level of EMR sharing, and trust in hospitals positively adjusted the relationship between recognition of legal and institutional roles and sharing intentions. Accordingly, we confirmed that the public recognized the role of the government and hospitals in the sharing process as necessary. The public interest benefits of sharing are critical to activating public participation in the sharing of EMR, and it is also essential to prepare guidelines that legally guarantee the security and proper use of EMR.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.24 no.4
• /
• pp.57-64
• /
• 2024

The introduction of Smart Factories has transformed manufacturing towards more objective and efficient line management. However, most companies are not effectively utilizing the vast amount of sensor data collected every second. This study aims to use this data to predict product quality and manage production processes efficiently. Due to security issues, specific sensor data could not be verified, so semiconductor process-related training data from the "SAMSUNG SDS Brightics AI" site was used. Data preprocessing, including removing missing values, outliers, scaling, and feature elimination, was crucial for optimal sensor data. Oversampling was used to balance the imbalanced training dataset. The SVM (rbf) model achieved high performance (Accuracy: 97.07%, GM: 96.61%), surpassing the MLP model implemented by "SAMSUNG SDS Brightics AI". This research can be applied to various topics, such as predicting component lifecycles and process conditions.