• Smart Structures and Systems
• /
• v.29 no.1
• /
• pp.53-62
• /
• 2022

The deployment of advanced structural health monitoring (SHM) systems in large-scale civil structures collects large amounts of data. Note that these data may contain multiple types of anomalies (e.g., missing, minor, outlier, etc.) caused by harsh environment, sensor faults, transfer omission and other factors. These anomalies seriously affect the evaluation of structural performance. Therefore, the effective analysis and mining of SHM data is an extremely important task. Inspired by the deep learning paradigm, this study develops a novel generative adversarial network (GAN) and convolutional neural network (CNN)-based data anomaly detection approach for SHM. The framework of the proposed approach includes three modules : (a) A three-channel input is established based on fast Fourier transform (FFT) and Gramian angular field (GAF) method; (b) A GANomaly is introduced and trained to extract features from normal samples alone for class-imbalanced problems; (c) Based on the output of GANomaly, a CNN is employed to distinguish the types of anomalies. In addition, a dataset-oriented method (i.e., multistage sampling) is adopted to obtain the optimal sampling ratios between all different samples. The proposed approach is tested with acceleration data from an SHM system of a long-span bridge. The results show that the proposed approach has a higher accuracy in detecting the multi-pattern anomalies of SHM data.

• Hwankyungkyoyuk
• /
• v.21 no.2
• /
• pp.25-39
• /
• 2008

The purpose of the study was to develop cyber in-service training contents regarding environmental literacy for entry-level environmental public servants. The blended type of contents were developed, through literature review, contents analysis of other programs, and expert conferences. The validity of the contents developed was ensured experts in environment. Major research findings were as followings: First, there is a lack of time for entry-level environmental public servants to participate in the environmental in-service training programs. Therefore, cyber training can be a good solution to the problems with environmental training courses. It improves access to educational opportunities as it overcomes the limitations of time and space and provides hands-on experiences through multimedia materials that reflect the real world. Second, directions for developing cyber environmental education contents were represented in three parts; 1) strategies for developing cyber environmental education contents, 2) Models for developing cyber environmental education contents, 3) Contents selection for developing cyber environmental education contents Third, the developed contents for entry-level environmental officers consist of 4 domains: (1) the introduction to environment; (2) the natural scientific understanding of environment; (3) the humanistic understanding of environment; and (4) the social scientific understanding of environment. Fourth, the program developed was evaluated by 7 environmental education experts according to 10 evaluation items of total contents and contents development structure. In result, the validity of the program was ensured. Based on the results, some recommendations were suggested.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.15 no.1
• /
• pp.171-178
• /
• 2015

In these days, the practical training education is getting highlighted in IT curriculum. This study is for the Cloud computing based Virtual Desktop Service Plan of IT education and its efficient operation and management plan. With the implementation of a virtual lab environment system, the training environment which is customized by the curriculum is able to be provided. Also in the case of the limited system, the curriculum is able to be provided for each subject in advance. Therefore if the Cloud Training (or Practicing) Portal system for the multiple cyber universities is implemented according to this study's estimated scale and operation managing policies, the virtual training education service system could be provided in more efficient and more effective ways.

• The Journal of Korean Association of Computer Education
• /
• v.7 no.6
• /
• pp.77-84
• /
• 2004

This study proposed the agent system for educational information sharing using bookmark. In order to search and share the educational information effectively, we designed DAML+OIL-typed bookmark information. Proposed system in this study had the P2P type based on Client-Server type. We implemented the bookmark agent that has the intelligent characteristics, that is, automatic categorization of peers and documents, autonomous communication between agents using DAML, and delicate information searching using the ontology dictionary in Semantic Web environment. Hereafter, this study will contribute to activate sharing and searching educational information as well as proposed system will offer the important technologies for SCORM-based e-learning environment.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.7 no.2
• /
• pp.96-101
• /
• 2007

Neural networks are known as kinds of intelligent strategies since they have learning capability. There are various their applications from intelligent control fields; however, their applications have limits from the point that the stability of the intelligent control systems is not usually guaranteed. In this paper we propose an adaptive tracking control for robot manipulators using the radial basis function network (RBFN) that is e. kind of neural networks. Adaptation laws for parameters of the RBFN are developed based on the Lyapunov stability theory to guarantee the stability of the overall control scheme. Filtered tracking errors between actual outputs and desired outputs are discussed in the sense of the uniformly ultimately boundedness(UUB). Additionally, it is also shown that parameters of the RBFN are bounded. Experimental results for a SCARA-type robot manipulator show that the proposed adaptive tracking controller is adaptable to the environment changes and is more robust than the conventional PID controller and the neuro-controller based on the multilayer perceptron.

• Proceedings of the KIEE Conference
• /
• 1991.07a
• /
• pp.713-716
• /
• 1991

This paper describes a methodology of mobile robot navigation which is designed to carry heavy payloads at high speeds to be used in FMS(Flexible Manufacturing System) without human control. Intelligent control scheme using fuzzy logic is applied to the navigation control. It analyzes sensor readings from multi-sensor system, which is composed of ultrasonic sensors, infrared sensors and odometer, for environment learning, planning, landmark detecting and system control. And it is implemented on a physical robot, AGV(Autonomous Guided Vehicle) which is a two-wheeled, indoor robot. An on-board control software is composed of two subsystems, i.e., AGV control subsystem and Sensor control subsystem. The results show that the navigation of the AGV is robust and flexible, and a real-time control is possible.

• Proceedings of the Korean Information Science Society Conference
• /
• 2012.06d
• /
• pp.35-37
• /
• 2012

원격교육과 e-러닝의 차세대 형태로 모바일 교육에 대한 관심이 급증하고 있다. 이러한 모바일 교육은 스마트폰을 중심으로 전개되고 있으며 사이버 대학교뿐만 아니라 일반 오프라인 대학에서도 적극적인 움직임을 보이고 있다. 본 논문에서는 u-캠퍼스 환경기반에서의 모바일 교육 서비스 시스템을 설계하였다. 모바일 교육 서비스 시스템은 u-캠퍼스 환경기반에서 교육 수요자들인 학생들에게 시공간의 제약 및 디바이스에 제약이 없는 학습 환경 시스템을 제공하고 모바일 캠퍼스 플랫폼 기반의 m-러닝 시스템을 설계한 것이다.

• Journal of Communications and Networks
• /
• v.8 no.4
• /
• pp.432-441
• /
• 2006

As the community antenna television (CATV) networks becomes ubiquitous, instead of constructing an entirely new broadband network infrastructure, it has emerged as one of the rapid and economic technologies to interconnecting heterogeneous network to provide broadband access to subscribers. How to support ubiquitous real-time multimedia applications, especially in a heavy traffic environment, becomes a critical issue in modern CATV networks. In this paper, we propose a time guaranteed and efficient upstream minislots allocation algorithm for supporting quality-of-service (QoS) traffic over data over cable service interface specification (DOCSIS) CATV networks to fulfill the needs of realtime interactive services, such as video telephony, video on demand (VOD), distance learning, and so on. The proposed adaptive fast expansion algorithm and the loading statistics with dynamic swapping algorithm have been shown to perform better than that of the multimedia cable network system (MCNS) DOCSIS.

• Communications of Mathematical Education
• /
• v.18 no.2 s.19
• /
• pp.35-45
• /
• 2004

"2002년 학술진흥재단 대학교육과정개발연구"의 성균관대학교의 9과제 중 하나로 3분야인 "신규교과목 또는 교수학습 방법개발" 과제로 대학에서의 "수학강좌의 효과적인 교수-학습 모델 개발 연구 (선형대수학, 미적분학, 이산수학을 중심으로)" 내용과 그 부산물인 콘텐츠를 소개하고, 이를 효과적으로 이용하기 위하여 개발한 새로운 강의 환경과 교수법을 소개한다. 이어서 현재 국내외에서 활발히 연구가 시작되고 있는 "대학에서의 수학교육" 내용을 소개한 후 대학에서 개발되고 검증된 이런 교수법과 교육환경이 중등학교의 수학 교육 현장에 주는 의미에 대하여 논의한다.

• Journal of Fisheries and Marine Sciences Education
• /
• v.24 no.3
• /
• pp.416-423
• /
• 2012

Smartphone and Tablet PC has become a popular. So, various location-based service applications are being made in the field of advertising, games, and search. However, the location-based services application is lacking in the field of education. Therefore, this study proposes a Location-based service application for Tablet PC, which can be take advantage in school. The application was designed with these considerations in mind. First, the application to increase the participation of the students take the form of play. Second, participating students are influencing each other. Third, through the promotion of the cycle has allowed long-term operations. This application will be used usefully in an environment that students use a individual Tablet PC through the spread of e-textbooks.