• Proceedings of the KIEE Conference
• /
• 1997.07b
• /
• pp.406-408
• /
• 1997

This paper presents the new method of a nondestructive spot welding state inspection system using neural networks. The learning process of neural networks makes the inspection system to adapt the variable welding parameters. The inspecting process is working with on-line real-time after off-line learning process. This neural network based inspection system shows reliable results through the field test for variations of applied voltages, currents, and contact area of the welding electrode.

• Proceedings of the KIEE Conference
• /
• 2000.07d
• /
• pp.2699-2701
• /
• 2000

This paper presents the Runge-Kutta neural networks(RKNN's) using the Runge-Kutta approximation method and the orthogonal function for control of unknown dynamical systems described by ordinary differencial equations in high accuracy. These subnetworks of RKNN's are based on orthogonal function. Computer simulations show the usefulness of the proposed scheme.

• Proceedings of the KIEE Conference
• /
• 1996.11a
• /
• pp.163-165
• /
• 1996

In this paper, we are proposed development of electric energy method and load curve. A daily electric energy is forecasted using artificial neural network. The load curve is obtained by combining forecasted electric energy and typical daily load patterns which are classified using KSOM and Fuzzy system. As a result, we know that we could get more accurate results and easier application than the results from based on the hourly historical data.

• Proceedings of the KIEE Conference
• /
• 2007.07a
• /
• pp.1809-1810
• /
• 2007

본 논문에서는 뇌파인식을 위한 입력패턴을 추출하고 패턴 인식을 위한 뇌파 학습 알고리즘을 설계하였다. 입력패턴의 구성은 일반적인 상황에서 인식률을 더욱 높이기 위하여 기존의 Alpha-wave, Beta-wave, Theta-wave, Delta-wave등의 비율을 비교하는 방식에서 Delta-wave와 Theta-wave의 합, Alpha-wave, Delta-wave와 Theta-wave의 합에 Alpha-wave로 나눈 값, Beta-wave의 4가지 입력패턴으로 구성하였다. 그리고 신경망의 한 종류인 역전파 알고리즘을 이용하여 동일 조건이나 비슷한 조건에서의 수면과 비수면의 구분이 아닌 각기 다른 조건 상태에서의 수면과 비수면에 대한 패턴분류를 시뮬레이션 하였고 일반적인 조건에서도 감성 상태를 분류 할 수 있음을 보였다.

• Educational Technology International
• /
• v.16 no.1
• /
• pp.1-30
• /
• 2015

The purpose of this research is to propose a novel social LMS developed for group collaborative learning with a think-aloud tool integrated for sharing cognitive processes in order to improve group collaborative learning performance. In this developmental research, the system was designed with three critical elements: the think-aloud element supports learners through shared cognition, the social network element improves the quality of collaborative learning by forming a structured social environment, and the learning management element provides a understructure for collaborative learning for student groups. Moreover, the three critical elements were combined in an educational context and applied in three directions.

• Proceedings of the Korea Contents Association Conference
• /
• 2014.06a
• /
• pp.233-234
• /
• 2014

• Journal of Scientific & Technological Knowledge Infrastructure
• /
• s.6
• /
• pp.120-122
• /
• 2001

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.48 no.12
• /
• pp.42-53
• /
• 2011

As IT industry using networks have been developed explosively, online operations that were conducted in offline are increasing rapidly, and even relationship with other people made online. As online crimes are increasing accordingly, building security networks is getting very important. As a result, network separation between business and organization network has been performed recently, but this causes network user inconvenience and efficiency reduction. In this paper, we propose reassociation methods for already separated networks for many public organizations. We implement two reassociation methods using NAT device and shared storage and show their experimental results.

• Journal of Korean Society of Rural Planning
• /
• v.21 no.1
• /
• pp.77-87
• /
• 2015

In this study, we try to quantify resident's conflict by rural development project based on previous researches about community capacities required for residents and social networks in rural village for suggesting efficient project model. we analyzed conflict elements in six category such as 'conflict in residents', 'conflict in residents and leaders', 'conflict in leaders', 'conflict in villages', 'conflict in development fund', 'conflict in village by common income project'. These results also analyzed by personal background(age, role, education, income) of respondent in questionary survey. Results show that 'conflict in residents and leaders', 'conflict in leaders', 'conflict in development fund' are perceived differently by age, role, education, and income in 5% significance level. Especially, relatively young age(below 40 years old) expressed clearly about conflict and high scored in item of 'residents and leaders'. Regression model show statistical significance(F=39.807, P=0.000) in influence relation analysis of conflict, network, leadership, and project fund. In this model, network ${\beta}=-0.237$, leadership ${\beta}=-0.375$, project fund ${\beta}=-0.000$ show network and leadership have negative relation to conflict but project fund is difficult to find relation with conflict. In this study, we defined social vulnerability using conflict, network, and leadership and verified the vulnerability of rural village applying regional community capacity in analysis results; vulnerability increased by the size of region and show inverse correlation to future vision of residents.

• 제어로봇시스템학회:학술대회논문집
• /
• 2002.10a
• /
• pp.120.2-120
• /
• 2002

In this paper auto-tuning scheme of weight function in the neural networks has been suggested by immune algorithm for nonlinear process. A number of structures of the neural networks are considered as learning methods for control system. A general view is provided that they are the special cases of either the membership functions or the modification of network structure in the neural networks. On the other hand, since the immune network system possesses a self organizing and distributed memory, it is thus adaptive to its external environment and allows a PDP (parallel distributed processing) network to complete patterns against the environmental situation. Also. It can provi..