• Proceedings of the Korea Information Processing Society Conference
• /
• 2009.04a
• /
• pp.1006-1008
• /
• 2009

온라인 교육 시스템에서 사용자는 효과적인 학습을 위해 향상된 교육 컨텐츠를 이용하고자 한다. 온라인 교육 시스템은 다양한 알고리즘을 프로그래밍하여 개별 사용자에게 적합한 구성이 가능하다. 이러한 온라인 교육 시스템은 미리 짜여진 프로그램에 의한 체계적인 반복 교육에 적합하다. 사용자의 효과적인 학습을 측정하는데 있어 학습한 내용이 장기기억 되는 방법의 적용은 무엇보다 중요하다. 본 논문에서는 학습한 내용의 기억 추이를 나타내는 에빙하우스 망각 곡선 이론을 기반으로 학습 시스템의 장기 기억 메커니즘을 구현하고자 한다. 본 논문에서 제안한 온라인 교육 시스템의 학습 내용은 학습자의 장기 기억된 정도를 측정함으로써 그 효용성을 나타낸다.

• Journal of Korea Multimedia Society
• /
• v.3 no.4
• /
• pp.416-423
• /
• 2000

The existing self-organizing feature map of Kohonen has weakpoint that need too much input patterns in order to converse into the learning rate and equilibrium state when it trains. Making up for the current weak point, B.Bavarian suggested the method of that distributed the learning rate such as Gaussian function. However, this method has also a disadvantage which can not achieve the right self-organizing. In this paper, we proposed the method of improving the convergence speed and the convergence rate of self-organizing feature map converting the Gaussian function into dynamic approximate curve used in when trains the self-organizing feature map.

• Journal of the Korean School Mathematics Society
• /
• v.18 no.2
• /
• pp.203-221
• /
• 2015

The purpose of this study is to analyze how a peer mentoring method affects students' problem solving abilities and class satisfaction in the context of high school quadratic curves and provide implications for teaching and learning mathematics. For this study, seventy six 11th graders in the natural sciences track participated in the peer mentoring method. After finishing the teaching method, Problem Solving Abilities Questionnaire was collected for analysis of pre-test/post-test experiments and Class Satisfaction Questionnaire was also gathered. The results show that the mentoring method positively impacts on participants' problem solving abilities and class satisfaction because its comfortable learning environments, individualized learning contents, and unconstrained learning processes motivate them through ways to improve their communication. According to the results, it is to address practical implications applied in teaching quadratic curves in high school with the value and importance of mentoring methods.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2004.05a
• /
• pp.427-430
• /
• 2004

최근에 전자상거래 분야에서는 다양한 에이전트를 시스템에 적용함으로써 전자상거래를 보다 활성화시키려는 연구가 늘어나고 있다. 그러나 현재의 이러한 연구들은 판매자의 실제 이익보다는 구매자의 선호도에 따른 물품을 추천하는데 있고, 가격과 이윤을 다룬 연구가 있어도 이 가격이 실제 이윤에 미치는 영향을 파악하기 어려운 문제가 있었다. 따라서 본 논문에서는 이러한 문제를 해결하기 위하여 원가 회계 이론에 기반한 원가 산정법들 중에서 고저점법, 산포도법, 학습 곡선법의 비교 분석을 통하여 원가를 보다 정확히 산정하는 방법을 알아내고, 판매자는 이를 반영하여 입찰가를 결정함으로써 적정 이윤을 얻을 수 있도록 한다. 이를 위해 본 논문에서는 각 원가 산정법을 적용한 에이전트의 성능 실험을 하였고, 비교적 우수한 성능을 보인 학습 곡선법을 통해서 적정 이윤을 보장하면서도 낙찰율을 향상시킬 수 있음을 보인다.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2022.05a
• /
• pp.354-354
• /
• 2022

딥러닝(Deep Learning)은 일반적으로 인공신경망(Artificial Neural Network) 를 의미하는데, 이에 따른 결과는 데이터의 양, 변수, 학습모델의 학습횟수, 은닉층(Hidden Layer)의 개수 등 여러 요소로 인해 결정된다. 본 연구에서는 물리적 장기유출 모형인 SWAT의 결과를 참값으로 LSTM모형의 매개변수인 은닉층 갯수와 학습횟수등의 시나리오를 바탕으로 검보정을 수행하였으며, 최적의 목적함수를 갖는 매개변수를 도출하였다. 이를 이용하여 유량지속곡선을 도출한결과를 SWAT의 결과와 비교해본 결과 매우 높은 상관성을 도출하였으며 이를 통해 수자원분야에서 인공신경망의 활용 가능성을 확인하였다.

• 대한위암학회:학술대회논문집
• /
• 2005.04a
• /
• pp.23-23
• /
• 2005

• Proceedings of the Korea Technology Innovation Society Conference
• /
• 2001.05a
• /
• pp.161-174
• /
• 2001

• The Transactions of the Korean Institute of Electrical Engineers A
• /
• v.53 no.4
• /
• pp.208-213
• /
• 2004

In this paper, a new method for the estimation of the effect of DSM program is proposed. By identifying the learning curve of high efficient induction motor, the effect of DSM program applied to that product can be estimated. The learning curve of normal induction motor, to which no DSM program is applied, is identified also. Both learning curves, which are different shapes, means different teaming ratio. It can be concluded that DSM program makes the learning curve of the product change the shape. It also can be concluded that DSM program has influence on the sale of the product to which it is applied.

• Journal of the Society of Disaster Information
• /
• v.18 no.4
• /
• pp.899-907
• /
• 2022

Purpose: Although many studies on seismic fragility analysis of general bridges have been conducted using machine learning methods, studies on curved bridge structures are insignificant. Therefore, the purpose of this study is to analyze the seismic fragility of bridges with I-shaped curved girders based on the machine learning method considering the material property and geometric uncertainties. Method: Material properties and pier height were considered as uncertainty parameters. Parameters were sampled using the Latin hypercube technique and time history analysis was performed considering the seismic uncertainty. Machine learning data was created by applying artificial neural network and response surface analysis method to the original data. Finally, earthquake fragility analysis was performed using original data and learning data. Result: Parameters were sampled using the Latin hypercube technique, and a total of 160 time history analyzes were performed considering the uncertainty of the earthquake. The analysis result and the predicted value obtained through machine learning were compared, and the coefficient of determination was compared to compare the similarity between the two values. The coefficient of determination of the response surface method was 0.737, which was relatively similar to the observed value. The seismic fragility curve also showed that the predicted value through the response surface method was similar to the observed value. Conclusion: In this study, when the observed value through the finite element analysis and the predicted value through the machine learning method were compared, it was found that the response surface method predicted a result similar to the observed value. However, both machine learning methods were found to underestimate the observed values.

• Korean Journal of Construction Engineering and Management
• /
• v.14 no.6
• /
• pp.38-48
• /
• 2013

Focusing on repetitive works of construction, many research have been conducted about application of the learning curve effect. However, it is still controversial, especially on the high-rise project, since the productivity improvement from the learning curve effects are hard to prove. In the previous research, applicability of the learning curve was mainly derived from the labor productivity data. Although the research were based on the real data, they merely concentrated on the simple conclusion that the labor productivity had improved or not, instead of the process interpretation. Therefore, the purpose of this research is to analyze the influence factors of the learning curve effect in high-rise projects and elucidate the offset factors of the effect. Based on these factors, a model for estimating the labor productivity containing the concept of process learning is suggested. Through our research, traditional learning curve theory could be compensated and re-established with having more appropriateness for high-rise projects.