• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2002년도 ITC-CSCC -2
• /
• pp.810-813
• /
• 2002

We present the information theoretic learning based on the Tsallis entropy maximization principle for various q. The Tsallis entropy is one of the generalized entropies and is a canonical entropy in the sense of physics. Further, we consider the dependency of the learning on the parameter $\sigma$, which is a standard deviation of an assumed a priori distribution of samples such as Parzen window.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 1993년도 Fifth International Fuzzy Systems Association World Congress 93
• /
• pp.1009-1012
• /
• 1993

An association memory, solving an optimization problem, a Boltzmann machine scheme learning and a back propagation learning in our chaos neuron models are reviewed and some new results are presented. In each model its microscopicrule (a parameter of a chaos system in a neuron) is subject to its macroscopic state. This feedback and chaos dynamics are essential mechanisms of our model and their roles are briefly discussed.

• 실천공학교육논문지
• /
• 제7권2호
• /
• pp.81-87
• /
• 2015

이 연구는 직접교수법을 적용해 기초공학의 일부인 물리학 수업에서 발생하는 교육장해학생에 대한 교육을 다루었다. 이 직접교육이란 교육자가 수업방향을 분명히 잡고 강력하게 이끄는 것이 중요한 교육요소인 방법론이다. 임의의 학생 100명에 대해 문제해결에 대한 이해력, 추리력, 기억력, 문제해결속도를 측정하여 20명(20%) 학생이 기초공학장애자로 나타났다. 한편, 직접교육을 통해 표본그룹(41명)의 중간고사와 기말고사에서 각각 53.7%와 61.0%의 성적을 거두어서 13.6% 증가를 보여주었으나 성적 50% 이하인 하위 그룹은 각각 29.8%와 28.2%를 거두어 오히려 감소하였다. 그러나 특별히 성적 최하위 20%인 8명의 학생을 학습장애자로 선정하여 별도로 여가의 직접교육을 수행하였고 이들은 중간고사 및 기말고사 평균점수는 각각 18.9%와 25.5% 로써 6.6% 증가를 보여주어 학습장애자들에 대한 직접교육이 실효가 있음을 보여주었다.

• 스마트미디어저널
• /
• 제11권2호
• /
• pp.31-38
• /
• 2022

하천의 염분 변화를 신속히 예측하는 것은 염분 침투로 인한 농업, 생태계의 피해를 예측하고 재해 방지 대책을 수립하기 위해서 중요한 작업이다. 머신러닝 기법은 물리 기반 수리 모델에 비해 계산량이 훨씬 적기 때문에, 비교적 짧은 시간에 염분농도를 예측 가능하여 물리 기반 수리 모델의 보완 기법으로 연구되고 있다. 해외에서는 머신러닝 기법 기반 염분 예측 연구들이 활발히 연구되고 있으나, 대한민국의 공공데이터에 머신러닝 기법을 적용한 연구는 충분치 않다. 낙동강 하구의 환경 정보에 관한 공공데이터와 함께, 본 연구는 여러 종류의 머신러닝 기법의 염분농도에 대한 예측 성능을 측정하였다. 실험 결과에서, 결정 트리 기반의 LightGBM 알고리즘은 평균 RMSE 0.37의 예측 정확도와 타 알고리즘 대비 2-20배 빠른 학습 속도를 보여주었다. 따라서 국내 하천의 염분농도 예측에도 머신러닝 기법을 적용할 수 있다고 판단된다.

• 한국컴퓨터그래픽스학회논문지
• /
• 제29권3호
• /
• pp.149-158
• /
• 2023

최신 기술이 적용된 HMD는 고해상도 디스플레이와 빠른 모션인식으로 멀미를 최소화하며 위치와 동작을 정확히 추적할 수 있다. 이는 가상의 삼차원 공간에 몰입할 수 있는 환경을 제공해 줄 수 있으며 이러한 특징을 활용하여 재난 시뮬레이터나 고위험 장비 학습 공간 등의 가상현실 콘텐츠가 발전하고 있다. 이러한 장점은 기초과학 교육 분야에서도 적용 가능하다. 특히 기존 2차원 자료로 설명되는 물리학의 전기장과 자기장의 개념을 삼차원 공간으로 확장하여 실시간으로 시각화한다면 학습 이해도 향상에 큰 도움이 될 수 있다. 본 논문에서는 삼차원 가상현실 기반의 실감형 물리 교육 환경 및 콘텐츠를 개발하고 개발된 학습 콘텐츠를 실제 학습 대상자에게 체험시켜 효과를 증명한다. 학습 대상자는 총 46명의 중학생과 대학생이며 가상현실 환경에서 삼차원으로 표현되는 전기장과 자기장을 실시간으로 경험하고 학습하였다. 설문 조사 결과 85% 이상의 긍정적인 반응을 얻을 수 있었으며 삼차원 가상공간 기반의 물리 학습이 효과적으로 적용될 수 있다는 긍정적인 결과를 얻었다.

• Nuclear Engineering and Technology
• /
• 제56권4호
• /
• pp.1501-1512
• /
• 2024

Plasma disruption in tokamak experiments is a challenging issue that causes damage to the device. Reliable prediction methods are needed, but the lack of full understanding of plasma disruption limits the effectiveness of physics-driven methods. Data-driven methods based on supervised learning are commonly used, and they rely on labelled training data. However, manual labelling of disruption precursors is a time-consuming and challenging task, as some precursors are difficult to accurately identify. The mainstream labelling methods assume that the precursor onset occurs at a fixed time before disruption, which leads to mislabeled samples and suboptimal prediction performance. In this paper, we present disruption prediction methods based on anomaly detection to address these issues, demonstrating good prediction performance on J-TEXT and EAST. By evaluating precursor onset times using different anomaly detection algorithms, it is found that labelling methods can be improved since the onset times of different shots are not necessarily the same. The study optimizes precursor labelling using the onset times inferred by the anomaly detection predictor and test the optimized labels on supervised learning disruption predictors. The results on J-TEXT and EAST show that the models trained on the optimized labels outperform those trained on fixed onset time labels.

• 한국과학교육학회지
• /
• 제11권2호
• /
• pp.67-77
• /
• 1991

In this paper, current research papers on Physics Problem Solving were analyzed according to the types of research purpose, method, subject and content of Physics, by using 3 Proceedings and 4 kinds of Journal, that is, the International Workshop(1983, Paris, France) and Conference (1983, Utrecht, The Netherlands) and Seminar(1987, Cornell University, U. S. A.) on Physics Education, and Journal of Research in Science Teaching (1984-1990) and Science Education (1986-1990). and Inter national Journal of Science Education(l987-1988) and Cognitive Science(1989-1990). There were 98 research papers on Problem Solving and among them 37 papers on Physics Problem Solving were selected for analyzing. The results of analysis are as follows; 1) The studies on Model of Novice Student were 22(59%), And those on Model of Desired Preformance, on Model of learning and on Model of Teaching were all much the same. 2) The theoretical studies were 10(27%), and the experimental ones 27(73%). Among the experimental studies, there were 16(59%) by using the written test, and 7(26%) by using the thinking aloud method. 3) The studies about university students as subjects were 20(54%). Probably, it seems the reason that most of researchers on Physics Problem Solving were professors of university or graduate students. 4) Among the various fields of Physics, the studies on Mechanics were 24(63%) and those on E1ectromagnetics 6(16%). or graduate students.

• Nuclear Engineering and Technology
• /
• 제54권1호
• /
• pp.310-317
• /
• 2022

The mass attenuation coefficient is the primary physical parameter to model narrow beam gamma-ray attenuation. A new machine learning based approach is proposed to model gamma-ray shielding behavior of composites alternative to theoretical calculations. Two fuzzy logic algorithms and a neural network algorithm were trained and tested with different mixture ratios of vanadium slag/epoxy resin/antimony in the 0.05 MeV-2 MeV energy range. Two of the algorithms showed excellent agreement with testing data after optimizing adjustable parameters, with root mean squared error (RMSE) values down to 0.0001. Those results are remarkable because mass attenuation coefficients are often presented with four significant figures. Different training data sizes were tried to determine the least number of data points required to train sufficient models. Data set size more than 1000 is seen to be required to model in above 0.05 MeV energy. Below this energy, more data points with finer energy resolution might be required. Neuro-fuzzy models were three times faster to train than neural network models, while neural network models depicted low RMSE. Fuzzy logic algorithms are overlooked in complex function approximation, yet grid partitioned fuzzy algorithms showed excellent calculation efficiency and good convergence in predicting mass attenuation coefficient.

• 한국과학교육학회지
• /
• 제27권6호
• /
• pp.497-509
• /
• 2007

Among many remedial approaches against the increasing unfavorableness toward school science, one of the prevalent findings studied by affective experts is that students' achievement in science and their attitude toward it has a relatively weak relationship. In contrast, cognitive experts assert that the conceptual change involves more than cognitive aspects, and may be influenced by affective factors such as beliefs, motivation, learning attitudes, and sociocultural contexts. The latter regards continuous conceptual change as leading to better student understanding of science with variables of students' attitude toward science. As an initial step toward illuminating the affective-cognitive learning aspects of science, the purpose of this study is to develop an instrument for analyzing the relationship between students' conceptual understanding and affective factors. Cognitive questionnaires from the database of distribution in students' misconceptions of physics (DMP project), and affective questionnaires from the Relevance of Science Education (ROSE project) are integrated into our instrument. The respondents are high school students in Okayama prefecture, Japan. Through the pilot test, the authors integrated attitude toward science (AS) and interest inventory (II) from ROSE into cognitive understanding (CD) from DMP. Statistical methodologies such as factor analysis and item total correlation theoretically discerned the effective sixty-three items from the two original item pools. Having discussed two validity issues, the authors suggest ongoing research associated with our affective-cognitive research perspective.

• 한국초등과학교육학회지:초등과학교육
• /
• 제28권3호
• /
• pp.331-339
• /
• 2009

The purpose of this study is to make a list of scientific terms to decrease students' difficulties of science learning. By using inductive method, database has established from elementary school science textbooks and laboratory observation books. All terms from physics area of science textbooks and laboratory observation books at the levels of grade 3 to 6 were analyzed based on the Standard Korean Dictionary (1999) and Book of Physics Terminology (2005). As a result, we made a list of 204 scientific terms by grade level. Those were 51 words for grade 3, 55 words for grade 4, 56 words for grade 5, and 42 words for grade 6. And there were some incongruities among textbooks, the Standard Korean Dictionary and the Book of Physics Terminology.