• Proceedings of the IEEK Conference
• /
• 2002.07b
• /
• 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.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1993.06a
• /
• 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.

• Journal of Practical Engineering Education
• /
• v.7 no.2
• /
• pp.81-87
• /
• 2015

The Direct Instruction (DI) was applied to the learning-disabled in the basic engineering education (especially, physics education). The DI is specified as an educational method in which the instructor strongly controls during the whole process of the entire course. The tests of understanding, reasoning, memory, and problem-solving speed showed that 20 students (20%) out of random 100 students are learning-disabled. The average points of mid-term and final exams were 53.7% and 61.0% respectively for a certain 41-students class. However, in this class, for the lower point students who obtained less than 50% points, the average points of mid-term and final exams were 29.8% and 28.2% respectively, which showed decreased. From this lower point group, the 8 students (20% students of 41 students) were selected as the learning-disabled. With additional DI studies provided, the average points of mid-term and final exams for the learning-disabled were 18.9% and 25.5% respectively, which showed 6.6% increase that means the DI for the learning-disabled was effective.

• Smart Media Journal
• /
• v.11 no.2
• /
• pp.31-38
• /
• 2022

Promptly predicting changes in the salinity in rivers is an important task to predict the damage to agriculture and ecosystems caused by salinity infiltration and to establish disaster prevention measures. Because machine learning(ML) methods show much less computation cost than physics-based hydraulic models, they can predict the river salinity in a relatively short time. Due to shorter training time, ML methods have been studied as a complementary technique to physics-based hydraulic model. Many studies on salinity prediction based on machine learning have been studied actively around the world, but there are few studies in South Korea. With a massive number of datasets available publicly, we evaluated the performance of various kinds of machine learning techniques that predict the salinity of the Nakdong River Estuary Basin. As a result, LightGBM algorithm shows average 0.37 in RMSE as prediction performance and 2-20 times faster learning speed than other algorithms. This indicates that machine learning techniques can be applied to predict the salinity of rivers in Korea.

• Journal of the Korea Computer Graphics Society
• /
• v.29 no.3
• /
• pp.149-158
• /
• 2023

HMD, which is applied with the latest technology, minimizes motion sickness with high-resolution displays and fast motion recognition, and can accurately track location and motion. This can provide an environment where you can immerse yourself in a virtual three-dimensional space, and virtual reality contents such as disaster simulators and high-risk equipment learning spaces are developing using these characteristics. These advantages are also applicable in the field of basic science education. In particular, expanding the concepts of electric and magnetic fields in physics described by existing two-dimensional data into three-dimensional spaces and visualizing them in real time can greatly help improve learning understanding. In this paper, realistic physical education environments and contents based on three-dimensional virtual reality are developed and the developed learning contents are experienced by actual learning subjects to prove their effectiveness. A total of 46 middle school and college students were taught and experienced in real time the electric and magnetic fields expressed in three dimensions in a virtual reality environment. As a result of the survey, more than 85% of positive responses were obtained, and positive results were obtained that three-dimensional virtual space-based physical learning could be effectively applied.

• Nuclear Engineering and Technology
• /
• v.56 no.4
• /
• 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.

• Journal of The Korean Association For Science Education
• /
• v.11 no.2
• /
• 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
• /
• v.54 no.1
• /
• 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.

• Journal of The Korean Association For Science Education
• /
• v.27 no.6
• /
• 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.

• Journal of Korean Elementary Science Education
• /
• v.28 no.3
• /
• 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.