• Communications for Statistical Applications and Methods
• /
• v.5 no.3
• /
• pp.599-605
• /
• 1998

본 연구에서는 단순구조 순환신경망을 이용한 신경망예측과 전통적인 시계열예측 방법을 이용하여, 순환변동이 있는 시계열자료의 단기예측 오차를 비교한다. 순환신경망모형의 입력자료를 변화시키는 개선된 학습방법을 적용하여 시계열자료를 학습하고, 신경망예측의 결과는 선형 AR(9)모형, 비선형 SETAR모형 그리고 이들의 결합모형을 이용한 예측결과와 비교한다. 실증분석에 적용된 시계열자료는 1700년부터 1987년 까지의 태양흑점 자료이며 예측에 이용된 검정자료는 1980년부터 8년 간의 자료이다.

• Journal of The Korean Association For Science Education
• /
• v.28 no.6
• /
• pp.527-545
• /
• 2008

This paper suggested a 4E&E Learning Cycle Model using learning motivation for students in science education. The model has been developed on the basis of motivational and instructional design. The 4E&E Learning Cycle Model has four phases such as engage, explore, explain and expand, and two subsidiary phases such as evaluate, and feedback provided with at each phase. The model has gone a process of instruction with learning effects evaluation and providing feedback in science classroom, which facilitate to increase the effectiveness of learning activities. Especially, the 4E&E Learning Cycle Model using motivational learning strategies makes the learners be attractive to and immersed in instruction. This model has potentials in educating students in science education.

• Journal of The Korean Association For Science Education
• /
• v.23 no.6
• /
• pp.617-626
• /
• 2003

Although many studies have investigated the effectiveness of concept mapping and the learning cycle, in Korea none have explored the effectiveness of concept mapping and the learning cycle combined. This study explored the effectiveness of concept mapping, the learning cycle, and a combination of concept mapping/learning cycle(CL) in high school biology class. Students' science achievement, the science related attitudes and scientific inquiry ability was measured. The results indicated that concept mapping, the learning cycle, and CL treatment were significantly different from the traditional one in science achievement(p< .05). However, the three treatments were not significantly different from each other. No significant difference exists among different learnings in high and average-ability students. But, concept mapping was the most effective in low-ability students. For the students' scientific inquiry ability, CL and learning cycle were more effective than concept mapping and traditional learning. No significant difference exists among different learnings in high-ability students. CL and learning cycle were more effective than concept mapping and traditional learning in average and low-ability students. For the students' science related attitudes, concept mapping, the learning cycle, and CL were more effective than the traditional learning. But, there was no significant difference among these three groups.

• Journal of The Korean Association For Science Education
• /
• v.28 no.5
• /
• pp.409-423
• /
• 2008

Many researches have reported that it is difficult to solve students' difficulties in learning science with teaching models focused on certain aspects because of various reasons. Recently, in science education research, the integrated perceptive has been to put emphasis on understanding complex situations of real teaching and learning. In this research context, the integrated mental model theory that were considered as a whole factor related to learning has been studied by integrating previous studies that related to students' conceptions and learning in various fields. Thus, it is needed that the teaching model be based on the integrated mental model theory to help students to solve their difficulties. The purpose of this research was to develop a new teaching model based on the integrated mental model theory to address this issue. We reviewed current studies on student difficulties and teaching models. After this, we developed 4M learning cycle teaching model. In this paper, we described the process of developing a new teaching model and discussed how to apply this teaching model to the practices. We also discussed the effects of 4M learning cycle teaching model based on the integrated mental model theory in learning science with its implications.

• 한국과학교육학회:학술대회논문집
• /
• 2008.01a
• /
• pp.126.1-126.1
• /
• 2008

• Journal of The Korean Association For Science Education
• /
• v.28 no.4
• /
• pp.302-315
• /
• 2008

Circular motion has been one of the most difficult concepts for students to understand. To facilitate for students to form scientific mental models about circular motion, this study developed 4M learning cycle teaching model based on the integrated mental model theory and strategies. For this study, fifty-three eleventh graders at a technical high school in Inchon were taught for 3 class hours. We conducted tests of basic physics concept and mental model of circular motion before, after, and two months after instruction. In results, we found that there were statistically significant improvement in the test of basic physics concept and mental model related with circular motion after instruction. Especially, this teaching model affected learning effectiveness of Correctness and Coherence of mental model.

• Journal of Korea Water Resources Association
• /
• v.51 no.12
• /
• pp.1217-1227
• /
• 2018

This paper aims to evaluate the applicability of dam inflow prediction model using recurrent neural network theory. To achieve this goal, the Artificial Neural Network (ANN) model and the Elman Recurrent Neural Network(RNN) model were applied to hydro-meteorological data sets for the Soyanggang dam and the Chungju dam basin during dam operation period. For the model training, inflow, rainfall, temperature, sunshine duration, wind speed were used as input data and daily inflow of dam for 10 days were used for output data. The verification was carried out through dam inflow prediction between July, 2016 and June, 2018. The results showed that there was no significant difference in prediction performance between ANN model and the Elman RNN model in the Soyanggang dam basin but the prediction results of the Elman RNN model are comparatively superior to those of the ANN model in the Chungju dam basin. Consequently, the Elman RNN prediction performance is expected to be similar to or better than the ANN model. The prediction performance of Elman RNN was notable during the low dam inflow period. The performance of the multiple hidden layer structure of Elman RNN looks more effective in prediction than that of a single hidden layer structure.

• Journal of The Korean Association For Science Education
• /
• v.30 no.5
• /
• pp.557-575
• /
• 2010

The purpose of the study was to suggest the characteristics and goals of the science teaching model for use as criteria in selecting the appropriate teaching model for science in secondary schools. These characteristics and the goals have been organized based on the analyses of the literature on the teaching and/or instructional model. The teaching models have been classified into four areas, and the characteristics and goals of each area have been summarized as follows: $\cdot$ Traditional models: teaching of scientific knowledge through lectures, acquisition of scientific knowledge through discovery, acquisition of inquiry process skills through inquiry-based teaching/learning $\cdot$ Transitional models: demonstration and discovery as teaching strategies, acquisition of inquiry process skills through inquiry approach, acquisition and change of scientific knowledge $\cdot$ Modernistic model - conceptual change models: differentiation of scientific knowledge, exchange of misconceptions for scientific concepts - learning cycle models: conceptual differentiation, exchange of misconceptions, acquisition of science process skills Also described in this paper are the model's characteristics and goals that can be used as the criteria for selecting the appropriate teaching model for the subject that will be taught.

• Korean Journal of Child Studies
• /
• v.25 no.3
• /
• pp.1-14
• /
• 2004

This study focused on the development and application of learning cycle model for promoting children's creativity and problem solving ability. The learning cycle approach consists of four phases : awareness, exploration, investigation, and concept application. The program consists of 20 scientific activities. A total of 70 children participated the 10 week program to examine the effectiveness of this model. The experimental design included a pretest, treatment, and posttest. Results showed that the experimental group children scored significantly higher on the creativity and problem solving tests in the posttest than the control group children.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2018.05a
• /
• pp.167-167
• /
• 2018

토양수분은 토양에 포함된 평균 수분량을 나타내며 수문 순환 관점에서 매우 중요한 수문변량 중 하나이다. 본 연구에서는 대표적인 기계학습 방법인 Support Vector Machine (SVM)을 이용한 토양 함수 예측 기법을 개발하고자 하며, 예측인자로서 원격 탐측 기반의 토양함수자료, 강수량, 온도 등을 활용하고자 한다. SVM은 Kernel 함수를 이용하여 복잡한 비선형 관계를 선형 가정을 통해서 해석하는 기계학습 방법으로서 전역모델(global model)로서 다양한 수문기상분야에 적용이 이루어지고 있다. SVM의 장점은 일정 부분의 오차를 허용함으로서 모형의 일반화 측면에서 기존 인공신경망(artificial neural network, ANN)에 비해 우수한 성능을 나타내며, 특히 예측모형으로서 적용성이 매우 크다. 본 연구에서는 과거 토양 함수 자료와 강수, 온도, 위성 관측 기반 정보 등을 이용하여 모형을 적합시키고 이를 미계측 유역으로 확장하는데 연구의 목적이 있으며, 본 연구를 통해 제안된 모형은 용담댐 시험유역을 대상으로 적용되며 기존 ANN 모형 및 다중회귀분석 결과와 비교를 통해 모형의 적합성을 평가하고자한다.