• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• 제13권5호
• /
• pp.195-201
• /
• 2013

The government has invested much budget for 5years to do the Smart-education and operate digital textbook services since 2011. The private enterprises also decided to focus on constructing Smart learning system by investing much budget. If these systems are constructed nationwide and therefore can access to cyber university by using smart devices, we can reduce the information gap and study online lectures to get a grade whenever, whoever and wherever we want to. However, these convenient systems can cause serious problems like falsifying grades by hacking if security systems are weak. In this paper, we formulated cyber university which is secured in terms of security. For this, we simulated the smart-learning system which strengthened the security, considering code algorithm and encryption technique.

• Journal of Digital Convergence
• /
• 제17권8호
• /
• pp.71-80
• /
• 2019

It is very important to have pre-service teachers enhance actual content development skill for STEAM classes through deep understanding of the concept. Thus the purpose of the study is to explore the educational methodology for improving pre-service teachers' competence of designing STEAM classes. The research performed with 17 pre-service teachers from Y university and 15 from S university in 2015. It includes blended learning methodology mixing online and offline classes. The result revealed that the students' perception on and the materialization skill of the STEAM education was improved by the methods of Lesson Study and blended learning. A positive result also came out in the respect of the perception on teaching with technology.

• Journal of Korea Society of Industrial Information Systems
• /
• 제27권2호
• /
• pp.25-34
• /
• 2022

With the development of online services, the ripple effect of negative comments is increasing, and the damage of cyber violence is rising. Various methods such as filtering based on forbidden words and reporting systems prevent this, but it is challenging to eradicate negative comments. Therefore, this study aimed to increase the accuracy of the classification of negative comments using deep learning and blur the parts corresponding to profanity. Two different conditional training helped decide the number of deep learning layers and filters. The accuracy of 88% confirmed with 90% of the dataset for training and 10% for tests. In addition, Grad-CAM enabled us to find and blur the location of swear words in negative comments. Although the accuracy of classifying comments based on simple forbidden words was 56%, it was found that blurring negative comments through the deep learning model was more effective.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• 제32권3호
• /
• pp.555-564
• /
• 2022

Recently, cyberattacks are using hacking techniques utilizing intelligent and advanced malicious codes for non-face-to-face environments such as telecommuting, telemedicine, and automatic industrial facilities, and the damage is increasing. Traditional information protection systems, such as anti-virus, are a method of detecting known malicious URLs based on signature patterns, so unknown malicious URLs cannot be detected. In addition, the conventional static analysis-based malicious URL detection method is vulnerable to dynamic loading and cryptographic attacks. This study proposes a technique for efficiently detecting malicious URLs by dynamically learning malicious URL data. In the proposed detection technique, malicious codes are classified using machine learning-based feature selection algorithms, and the accuracy is improved by removing obfuscation elements after preprocessing using Weighted Euclidean Distance(WED). According to the experimental results, the proposed machine learning-based malicious URL detection technique shows an accuracy of 89.17%, which is improved by 2.82% compared to the conventional method.

• KIPS Transactions on Software and Data Engineering
• /
• 제10권11호
• /
• pp.513-520
• /
• 2021

Recently, research on edutech, which combines education and technology in the e-learning field called learning, education and training, has been actively conducted, but it is still insufficient to collect and utilize data tailored to individual learners based on learning activity data that can be automatically collected from digital devices. Therefore, this study attempts to detect questions in textbooks or problem papers using artificial intelligence computer vision technology that plays the same role as human eyes. The textbook or questionnaire item detection model proposed in this study can help collect, store, and analyze offline learning activity data in connection with intelligent education services without digital conversion of textbooks or questionnaires to help learners provide personalized learning services even in offline learning.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• 제24권1호
• /
• pp.1-8
• /
• 2024

On-device AI technology, which can operate AI models at the edge devices to support real-time processing and privacy enhancement, is attracting attention. As intelligent IoT is applied to various industries, services utilizing the on-device AI technology are increasing significantly. However, general deep learning models require a lot of computational resources for inference and learning. Therefore, various lightweighting methods such as quantization and pruning have been suggested to operate deep learning models in embedded edge devices. Among the lightweighting methods, we analyze how to lightweight and apply deep learning models to edge computing devices, focusing on pruning technology in this paper. In particular, we utilize dynamic and static pruning techniques to evaluate the inference speed, accuracy, and memory usage of a lightweight AI vision model. The content analyzed in this paper can be used for intelligent video control systems or video security systems in autonomous vehicles, where real-time processing are highly required. In addition, it is expected that the content can be used more effectively in various IoT services and industries.

• The Journal of the Convergence on Culture Technology
• /
• 제10권2호
• /
• pp.517-524
• /
• 2024

This study aims to train and implement a deep learning model for the fusion of website creation and artificial intelligence, in the era known as the AI revolution following the launch of the ChatGPT service. The deep learning model was trained using 3,000 collected web page images, processed based on a system of component and layout classification. This process was divided into three stages. First, prior research on AI models was reviewed to select the most appropriate algorithm for the model we intended to implement. Second, suitable web page and paragraph images were collected, categorized, and processed. Third, the deep learning model was trained, and a serving interface was integrated to verify the actual outcomes of the model. This implemented model will be used to detect multiple paragraphs on a web page, analyzing the number of lines, elements, and features in each paragraph, and deriving meaningful data based on the classification system. This process is expected to evolve, enabling more precise analysis of web pages. Furthermore, it is anticipated that the development of precise analysis techniques will lay the groundwork for research into AI's capability to automatically generate perfect web pages.

• Digital Contents
• /
• 9호통권148호
• /
• pp.112-115
• /
• 2005

한국데이터베이스진흥센터가 운영하고 있는 온엑스포(www.onexpo.or.kr)에서는 9월과 10월 두 달 동안‘2005 캐릭터·애니메이션 온엑스포’를 개최한다. 온엑스포는 국내 디지털콘텐츠 기업의 제품을 온라인상에서 상설 전시하고 해당 기업의 홍보와 마케팅을 지원하는 국내 최대 규모의 사이버 전시장으로, 전시 기업의 홍보를 효과적으로 지원하기 위해 분기별로 주제를 정해 테마전시회를 개최하고 있다. 지난 3월과 4월에는‘이러닝 온엑스포’를, 5월과 6월에는‘게임 온엑스포’를 개최한 바 있으며, 이번에는 국내의 캐릭터·애니메이션의 트랜드를 알아보고 대표적인 기업을 소개하기 위해 ‘2005 캐릭터·애니메이션 온엑스포’를 개최한다. 이번 호에서는‘2005 캐릭터·애니메이션 온엑스포’참가 기업 중 우리나라의 캐릭터·애니메이션 사업을 이끌어 갈 피콤엔터테인 먼트·은아트·스튜디오 짜박을 소개한다.

• The Journal of the Korea Contents Association
• /
• 제5권4호
• /
• pp.197-203
• /
• 2005

Interactivity is very important at ubiquitous e-Learning system oriented multi platform because online study is accomplished by multi media. In this thesis promotion for interactivity is designed at online study. By cyber education with supposed promotion used for a feedback. From now on a special research of study design should be made for interactivity and effectiveness using human sensibility ergonomics.

• Review of KIISC
• /
• 제30권6호
• /
• pp.67-81
• /
• 2020

CHES는 암호 알고리즘의 하드웨어/소프트웨어 구현의 설계 및 분석에 대한 다양한 성과가 발표되는 부채널 분석 분야 최대 규모의 보안 컨퍼런스이다. 본 기고는 CHES 컨퍼런스에 발표된 논문들에 대하여 부채널 공격 관점, 부채널 대응 및 구현 관점, CHES에서 주제로 다루는 암호 알고리즘의 추이 관점으로 구분하여 동향을 분석한다. 이를 위하여 오류주입 공격, 머신러닝 기반 부채널 공격, 캐시공격, 부채널 누출 검증 방법론과 부채널 역공학 기술 등 다양한 부채널 공격을 소개하고 최신 논문 주제의 흐름에 대하여 논의한다. 또한, 소프트웨어 고차 마스킹과 하드웨어 TI, PUF/난수 발생기 등의 부채널 대응기술 및 구현 동향을 분석하며, CHES에 발표된 논문들이 주제로 다루는 대칭키, 공개키 암호 및 화이트박스 암호 추이를 분석한다. 이러한 CHES 컨퍼런스의 주제별 연구 동향 분석 결과는 부채널 분석 연구자에게 유용한 정보를 제공하고 향후 연구 방향에 대한 중요한 지표가 될 수 있을 것이다.