• Journal of the Semiconductor & Display Technology
• /
• v.22 no.1
• /
• pp.113-117
• /
• 2023

As sputter equipment becomes more complex, it becomes increasingly difficult to understand the parameters that affect the thickness uniformity of thin metal film deposited by sputter. To address this issue, we verified a deep learning model that can predict complex relationships. Specifically, we trained the model to predict the height of 36 magnets based on the thickness of the material, using Support Vector Machine (SVM), Multilayer Perceptron (MLP), 1D-Convolutional Neural Network (1D-CNN), and 2D-Convolutional Neural Network (2D-CNN) algorithms. After evaluating each model, we found that the MLP model exhibited the best performance, especially when the dataset was constructed regardless of the thin film material. In conclusion, our study suggests that it is possible to predict the sputter equipment source using film thickness data through a deep learning model, which makes it easier to understand the relationship between film thickness and sputter equipment.

• Annual Conference on Human and Language Technology
• /
• 2022.10a
• /
• pp.320-323
• /
• 2022

상호참조해결은 문서에서 명사, 대명사, 명사구 등의 멘션 후보를 식별하고 동일한 개체를 의미하는 멘션들을 찾아 그룹화하는 태스크이다. 딥러닝 기반의 한국어 상호참조해결 연구들에서는 BERT를 이용하여 단어의 문맥 표현을 얻은 후 멘션 탐지와 상호참조해결을 동시에 수행하는 End-to-End 모델이 주로 연구가 되었으며, 최근에는 스팬 표현을 사용하지 않고 시작과 끝 표현식을 통해 상호참조해결을 빠르게 수행하는 Start-to-End 방식의 한국어 상호참조해결 모델이 연구되었다. 최근에 한국어 상호참조해결을 위해 구축된 ETRI 데이터셋은 WIKI, QA, CONVERSATION 등 다양한 도메인으로 이루어져 있으며, 신규 도메인의 데이터가 추가될 경우 신규 데이터가 추가된 전체 학습데이터로 모델을 다시 학습해야 하며, 이때 많은 시간이 걸리는 문제가 있다. 본 논문에서는 이러한 상호참조해결 모델의 도메인 적응에 Continual learning을 적용해 각기 다른 도메인의 데이터로 모델을 학습 시킬 때 이전에 학습했던 정보를 망각하는 Catastrophic forgetting 현상을 억제할 수 있음을 보인다. 또한, Continual learning의 성능 향상을 위해 2가지 Transfer Techniques을 함께 적용한 실험을 진행한다. 실험 결과, 본 논문에서 제안한 모델이 베이스라인 모델보다 개발 셋에서 3.6%p, 테스트 셋에서 2.1%p의 성능 향상을 보였다.

• Journal of Digital Convergence
• /
• v.13 no.9
• /
• pp.49-56
• /
• 2015

Korea government has established clear cost estimation standard based on a survey of e-learning contents development cost and presented 'e-Learning Contents Development Cost Estimation Guidelines' that reflect the characteristics of the e-learning industry. However, if there is no institutional support, this guideline and system fails to achieve the purposes and objectives. And it is likely to be facing a dead document. Therefore, the policy foundation is required. This study suggested the following policy; stepwise activation of cost estimation standard, enact announcement and periodically adjustment of cost estimation standard, installation and operation of cost estimation standard operational committee, conjunction with the e-learning industry survey, cultural diffusion of co-owned copyright, systematic monitoring of the e-learning contents development process, research on activating policy of cost estimation standard, conjunction with the standard contract for enhancing policy effectiveness.

• Journal of Digital Convergence
• /
• v.12 no.3
• /
• pp.383-390
• /
• 2014

In recent years, the convergence of IT and IT sightseeing tour has emerged as a fusion of academic disciplines in the future. Convergence study of social data analysis, raising the heat. Social Network Services (SNS) being utilized in many areas of marketing and to apply the case study is also increasing. This study is based u-smart tourist information systems for mobile learning content design. This is the pattern of things in the template library for things to increase the effectiveness of the learning content to mobile learning content to be converted to a. Design of mobile learning content using u-smart things smart phone app (App) and XMI to go through the design process of utilizing the heat. Future through the design process by implementing a mobile learning content to meet information quality tourist information content to create mobile learning content and learning things that can be content to live it up advantage.

• Journal of the Korea Convergence Society
• /
• v.9 no.3
• /
• pp.23-29
• /
• 2018

There is a growing interest in computer based learning system that can learn a new concept of epistemic frames in response to the demands of $21^{st}$ century Skills. However, there is little research on the theoretical models for the epistemic frames applicable in the changing educational environment and the measurement theories (Psychometric theory, Learning Analytics) that can be evaluated. Therefore, in this study, we propose the core elements of the learning system prototype that can educate the epistemic frames in the practical community. Furthermore, this study explores and suggests an appropriate psychometric measurement theory (learning analytics) that allows us to measure, infer, and evaluate a learner.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.24 no.3
• /
• pp.15-20
• /
• 2024

Path planning for unmanned aerial vehicles (UAV) is crucial in avoiding collisions with obstacles in complex environments that include both static and dynamic obstacles. Path planning algorithms like RRT and A^* are effectively handle static obstacle avoidance but have limitations with increasing computational complexity in high-dimensional environments. Reinforcement learning-based algorithms can accommodate complex environments, but like traditional path planning algorithms, they struggle with training complexity and convergence in higher-dimensional environment. In this paper, we proposed a reinforcement learning model utilizing a cell decomposition algorithm. The proposed model reduces the complexity of the environment by decomposing the learning environment in detail, and improves the obstacle avoidance performance by establishing the valid action of the agent. This solves the exploration problem of reinforcement learning and improves the convergence of learning. Simulation results show that the proposed model improves learning speed and efficient path planning compared to reinforcement learning models in general environments.

• Journal of Digital Convergence
• /
• v.14 no.3
• /
• pp.135-141
• /
• 2016

This paper was conducted to verify the relationship of understanding of learning, service quality, efficiency of convergence e-business valuation. For this paper, it surveyed 179 students and the data were collected Nov. 2~30, 2015. This research analyzed all the samples through ANOVA, t-test utilized by SPSS 22.0 The results as follow. First, understanding of learning, service quality, efficiency had statistically significant difference according to gender. Second, understanding of learning, service quality, efficiency showed statistically significant difference according to grade. The results of this study reveal the fact that the general characteristics like gender and grade made difference to the understanding of learning, service quality, efficiency. Furthermore, this paper may need to include various variables of understanding of learning, service quality, efficiency and suggest research about several university.

• Journal of the Korean Data and Information Science Society
• /
• v.27 no.4
• /
• pp.993-1000
• /
• 2016

Semi-supervised learning makes it easy to use an unlabeled data in the supervised learning such as classification. Applying the semi-supervised learning on the regression analysis, we propose two methods for a better regression function estimation. The proposed methods have been assumed different marginal densities of independent variables and different smoothing parameters in unlabeled and labeled data. We shows that the overfitted pilot estimator should be used to achieve the fastest convergence rate and unlabeled data may help to improve the convergence rate with well estimated smoothing parameters. We also find the conditions of smoothing parameters to achieve optimal convergence rate.

• Journal of the Korea Convergence Society
• /
• v.9 no.12
• /
• pp.475-483
• /
• 2018

The purpose of this study based on descriptive research is to examine the convergent relationship of interpersonal competence, self-determination motivation and self-regulated learning ability in nursing students. Data collected from 251 nursing students at a university located in C province from June, 2018 to July, 2018 are analyzed using SPSS/WIN 21.0. As a result, there are positive correlation between interpersonal competence(r=.361, p<.001) and self-determination motivation(r=.466, p<.001) and self-regulated-learning-ability. Interpersonal competence and self-determination motivation have not meaningful relationship(r=.091, p=.148). It is turned out that interpersonal competence and self-determination motivation are influenced on the self-regulated learning ability respectively. Based on these results, research should be continued on the developing new educational methods through convergence of factors by analyzing relevant factors to enhance interpersonal competence and self-determination motivation that affect self-regulated learning ability.

• Journal of Convergence for Information Technology
• /
• v.8 no.6
• /
• pp.67-74
• /
• 2018

The purpose of this study was to examine the difference between communicative competence and problem solving ability by applying project - based instruction in the community dental hygienic subject. For this purpose, we measured 30 students' communication ability and problem solving ability using the same questionnaire before and after experiencing project learning. The data were Collected from 30 undergraduate students and analyzed by paired t-test with SPSS. The result demonstrated that project-based learning method has an significant effect on improvement of communication skill and problem solving ability of undergraduate students. Based on the results of this study, in order to improve the practical ability, it is necessary to activate the self-directed active learning method such as Project-based learning for community dental hygiene major study.