• Transactions of Materials Processing
• /
• v.30 no.4
• /
• pp.186-194
• /
• 2021

Finite element simulation is a widely applied method for practical purpose in various metal forming process. However, in the simulation of elasto-plastic behavior of porous material or in crystal plasticity coupled multi-scale simulation, it requires much calculation time, which is a limitation in its application in practical situations. A machine learning model that directly outputs the constitutive equation without iterative calculations would greatly reduce the calculation time of the simulation. In this study, we examined the possibility of artificial intelligence based constitutive equation with the input of existing state variables and current velocity filed. To introduce the methodology, we described the process of obtaining the training data, machine learning process and the coupling of machine learning model with commercial software DEFROM^TM, as a preliminary study, via rigid plastic finite element simulation.

• Journal of the Korea Convergence Society
• /
• v.12 no.9
• /
• pp.93-98
• /
• 2021

The change of programming language learning experience on learning motivation was analyzed. Learning a programming language is generally evaluated as a difficult process even for majors. Measuring psychological changes related to programming learning at this point in expanding to non-majors is necessary for learner analysis. The overall learner attitude change was investigated by measuring achievement goals, academic interest, academic self-efficacy, cognitive involvement, and academic self-regulation, which are motivation-related factors. All factors related to learning attitude showed a decrease in the post-test results. This result is interpreted that the difficulty of the learning process decreased the motivation to learn programming. It was found that the greater the difficulty perceived by the learner, the greater the decrease in the motivation to learn. Based on the results of this study, it has implications that a learning environment and learning process that can give feedback and a situation that can reduce the level of learning difficulty felt by learners should be systematically given.

• The Journal of the Korea Contents Association
• /
• v.14 no.6
• /
• pp.491-498
• /
• 2014

Programming learning tend to improve the high thinking ability by experiencing problem solving process through programming recently, There are the previous studies that small group cooperative learning has the effect of the learning that is based logical thinking and creativity, while programming learning has relied on individual learner's thinking and principles traditionally. In this paper, it was verified the effect on improving the problem solving ability to perform by the small cooperative learning group in a problem solving process of programming learning. For this, it was developed and applied a model that include small cooperative learning group based on the problem solving 5 steps. The results of this study showed that the small cooperative learning group has positive effect of the problem solving ability in programming learning and has no relationship with cognitive style.

• 전기의세계
• /
• v.17 no.1
• /
• pp.48-50
• /
• 1968

The convergence rate of Bayes' learning process is investigated for a binomial random variable. A measure of the rate of convergence is proposed and it is found that such a measure can be approximated by an exponential function of the number of observations.

• Journal of Korean Home Economics Education Association
• /
• v.24 no.3
• /
• pp.101-122
• /
• 2012

The purpose of this study is to develop teaching learning process plans with problem-based learning using book-making applying to the "Dressing and Self Expression" unit and evaluate its effect in middle school home economics for first grade. We developed teaching learning process plans with problem-based learning using book-making including 9 teaching materials for teachers and 15 learning materials for students. Further, we conducted and investigated pre- and post-tests in a form of questionnaires in 167 students from a girls' middle school in Pusan. Teaching learning process plans with problem-based learning using book-making showed positive results in body satisfaction, such as reduction in distortion or less dissatisfaction regarding students' body images. Also, they were found to be less affected by sociocultural attitude towards appearance. The estimation of students included the positive contents that the class was interested with various materials and it provided them with a chance to understand their body. Meanwhile, minor comments pointed out lack of time and complained of the amount of assignments. With these results, we found that teaching learning process plans with problem-based learning using book-making was an appropriate model to achieve the purpose of this study and we suggested that this class might be applied to other units of middle school home economics.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.14 no.4
• /
• pp.207-218
• /
• 2019

The purpose of this study is to develop a model that can systematically study the whole learning process of machine learning. Since the existing model describes the learning process with minimum coding, it can learn the progress of machine learning sequentially through the new model, and can visualize each process using the tensor flow. The new model used all of the existing model algorithms and confirmed the importance of the variables that affect the target variable, survival. The used to classification training data into training and verification, and to evaluate the performance of the model with test data. As a result of the final analysis, the ensemble techniques is the all tutorial model showed high performance, and the maximum performance of the model was improved by maximum 5.2% when compared with the existing model using. In future research, it is necessary to construct an environment in which machine learning can be learned regardless of the data preprocessing method and OS that can learn a model that is better than the existing performance.

• The Journal of Korea Robotics Society
• /
• v.14 no.2
• /
• pp.81-86
• /
• 2019

Robots are used in various industrial sites, but traditional methods of operating a robot are limited at some kind of tasks. In order for a robot to accomplish a task, it is needed to find and solve accurate formula between a robot and environment and that is complicated work. Accordingly, reinforcement learning of robots is actively studied to overcome this difficulties. This study describes the process and results of learning and solving which applied reinforcement learning. The mission that the robot is going to learn is bottle flipping. Bottle flipping is an activity that involves throwing a plastic bottle in an attempt to land it upright on its bottom. Complexity of movement of liquid in the bottle when it thrown in the air, makes this task difficult to solve in traditional ways. Reinforcement learning process makes it easier. After 3-DOF robotic arm being instructed how to throwing the bottle, the robot find the better motion that make successful with the task. Two reward functions are designed and compared the result of learning. Finite difference method is used to obtain policy gradient. This paper focuses on the process of designing an efficient reward function to improve bottle flipping motion.

• Asia pacific journal of information systems
• /
• v.29 no.4
• /
• pp.789-816
• /
• 2019

Text classification is a challenging task, especially when dealing with a huge amount of text data. The performance of a classification model can be varied depending on what type of words contained in the document corpus and what type of features generated for classification. Aside from proposing a new modified version of the existing algorithm or creating a new algorithm, we attempt to modify the use of data. The classifier performance is usually affected by the quality of learning data as the classifier is built based on these training data. We assume that the data from different domains might have different characteristics of noise, which can be utilized in the process of learning the classifier. Therefore, we attempt to enhance the robustness of the classifier by injecting the heterogeneous data artificially into the learning process in order to improve the classification accuracy. Semi-supervised approach was applied for utilizing the heterogeneous data in the process of learning the document classifier. However, the performance of document classifier might be degraded by the unlabeled data. Therefore, we further proposed an algorithm to extract only the documents that contribute to the accuracy improvement of the classifier.

• The Journal of the Korea Contents Association
• /
• v.16 no.10
• /
• pp.617-626
• /
• 2016

This study was a descriptive research investigating the impact of simulation-based learning on the problem solving process and clinical competence of new nurses. The 202 participants were new nurses who have provided nursing care for less than 12 months have experienced simulation-based learning more than once in their undergraduate courses. This study found that the number of times participants have experienced the simulation-based learning had no correlation with their problem solving process and clinical competence, but simulation design features correlated with their problem solving process and clinical competence. The results of clustering analysis that examined differences in the effects on problem solving process and clinical competence by classifying simulation design features by clustering also showed significant differences. This study has confirmed the importance of simulation design to simulation-based learning in nursing education. We hope that the findings of the study will be used for effective operation of simulation-based learning. In the future, objective assessment methods will be required to evaluate the effects of simulation-based learning provided in undergraduate courses on nurses' clinical competence.

• Journal of The Korean Association of Information Education
• /
• v.4 no.1
• /
• pp.40-56
• /
• 2000

Web based learning has been used for many educational systems by aid of the development of internet technique. The true process of education includes not only learning contents but also learning process and the evaluation. So far, Web-based evaluation mainly consists of the evaluation of the learning products or the evaluation of the cognitive domain. But, there is lack of the appropriate feedback for learning effects. In this paper, we design and implement an evaluation system for Web-based instruction. In our system, the learners are evaluated during the process of Web-based learning. Our system provides learner-centered instruction for students with instant feedback. The questions made up by teachers are stored in the database and can be searched by a keyword, grade, semester or unit. The evaluation system can also provide the feedback to right or wrong answer for each question. Our system provides the learners with instant feedback after solving the questions and also can improve the quality of learning process using the Web.