• 제어로봇시스템학회:학술대회논문집
• /
• 1992.10b
• /
• pp.550-554
• /
• 1992

In this paper the issue of convergence rate is introduced for a learning control scheme we have developed and applied for tracking of unknown linear systems. A sufficient condition under which the output trajectory converges exponentially fast is obtained using the controllability grammian of controllable linear systems. Under the same condition it is also shown that the learning control input converges exponentially with the same rate as the rate of output convergence. A numerical example with computer simulation results is presented to show the feasibility of the scheme.

• International Journal of Control, Automation, and Systems
• /
• v.6 no.2
• /
• pp.194-203
• /
• 2008

Iterative learning control (ILC) is a simple and effective method for the control of systems that perform the same task repetitively. ILC algorithm uses the repetitiveness of the task to track the desired trajectory. In this paper, we propose a PID (proportional plus integral and derivative) type ILC update law for control discrete-time single input single-output (SISO) linear time-invariant (LTI) systems, performing repetitive tasks. In this approach, the input of controlled system in current cycle is modified by applying the PID strategy on the error achieved between the system output and the desired trajectory in a last previous iteration. The convergence of the presented scheme is analyzed and its convergence condition is obtained in terms of the PID coefficients. An optimal design method is proposed to determine the PID coefficients. It is also shown that under some given conditions, this optimal iterative learning controller can guarantee the monotonic convergence. An illustrative example is given to demonstrate the effectiveness of the proposed technique.

• Journal of Korea Multimedia Society
• /
• v.24 no.10
• /
• pp.1326-1335
• /
• 2021

As part of the cell division method, we proposed a method for segmenting images generated by topography microscopes through deep learning-based feature generation and graph segmentation. Hybrid vector shapes preserve the overall shape and boundary information of cells, so most cell shapes can be captured without any post-processing burden. NIH-3T3 and Hela-S3 cells have satisfactory results in cell description preservation. Compared to other deep learning methods, the proposed cell image segmentation method does not require postprocessing. It is also effective in preserving the overall morphology of cells and has shown better results in terms of cell boundary preservation.

• ETRI Journal
• /
• v.44 no.2
• /
• pp.232-243
• /
• 2022

Changes in household composition and the residential environment have had a considerable impact on the features of postal delivery regions in recent years, resulting in a large increase in the overall workload of domestic postal delivery services. In this paper, we provide complex analysis results for postal delivery areas using various unsupervised learning approaches. First, we extract highly influential features using several feature-engineering methods. Then, using quantitative and qualitative cluster analyses, we find the distinctive traits and semantics of postal delivery zones. Unsupervised learning approaches are useful for successfully grouping postal service zones, according to our findings. Furthermore, by comparing a postal delivery region to other areas in the same group, workload balancing was achieved.

• Journal of Digital Convergence
• /
• v.13 no.9
• /
• pp.29-37
• /
• 2015

This study investigated the effectiveness of the learning community for the development of convergence on self-directed learning and problem-solving. One hundred ninety-nine university students participated in the study. In specific, one hundred twenty-three among them participated learning community program at the center for teaching and learning for nine weeks while the others were are not as a control group. Pre-post survey with 62 items was conducted regarding self-directed learning(35 items) and problem-solving(27 items). To analyze the data statistically, ANCOVA(Analysis of Covariate) was used. As results, university students in learning community program showed significant difference in all areas of the survey. In other words, university students in learning community program improved self-directed learning and problem solving more than those who were in the control group. Suggestions and ideas of further studies were discussed.

• Journal of Convergence for Information Technology
• /
• v.9 no.12
• /
• pp.252-263
• /
• 2019

This study attempted to apply flip-learning and to evaluate college students' awareness and academic achievements. Twenty-seven students in single-group dental hygiene were applied to the dental radiology class for four weeks. Data collection was done after the flipped-learning and collected data were analyzed using frequency, average and content analysis using SPSS 18.0. As a result, awareness of overall class was a positive response, and academic achievement evaluation was not statistically significant. It was found to be an effective educational program. However, the academic achievement evaluation was not statistically significant and it was considered that the evaluation system needs to be different according to the learning method.

• Annual Conference on Human and Language Technology
• /
• 2021.10a
• /
• pp.609-611
• /
• 2021

기계 독해는 주어진 지문 내에서 질문에 대한 답을 기계가 찾아 답하는 문제이다. 딥러닝에서는 여러 데이터셋을 학습시킬 때에 이전에 학습했던 데이터의 weight값이 점차 사라지고 사라진 데이터에 대해 테스트 하였을때 성능이 떨어진 결과를 보인다. 이를 과거에 학습시킨 데이터의 정보를 계속 가진 채로 새로운 데이터를 학습할 수 있는 Continual learning을 통해 해결할 수 있고, 본 논문에서는 이 방법을 MRC에 적용시켜 학습시킨 후 한국어 자연어처리 Task인 Korquad 1.0의 MRC dev set을 통해 성능을 측정하였다. 세 개의 데이터셋중에서 랜덤하게 5만개를 추출하여 10stage를 학습시킨 50K 모델에서 추가로 Continual Learning의 Learning without Forgetting를 사용하여 학습시킨 50K-LWF 모델이 F1 92.57, EM 80.14의 성능을 보였고, BERT 베이스라인 모델의 성능 F1 91.68, EM 79.92에 비교하였을 때 F1, EM 각 0.89, 0.22의 향상이 있었다.

• Journal of Digital Convergence
• /
• v.13 no.1
• /
• pp.77-83
• /
• 2015

This study, according as the limits on learning and unsatisfaction about e-learning are emerging and the structural contradictions of the e-learning industry are continuing, was carried out to present the policy alternatives for solving these. As a means for overcoming the limitations of e-learning and the healthy growth of e-learning industry, this study presents the application of Bigdata in e-learning and proposes several practical challenges of policy. Policy action plans are technology development support, professional manpower support, SME application support, legal improvement.

• Journal of Engineering Education Research
• /
• v.17 no.2
• /
• pp.11-24
• /
• 2014

The purpose of this study is to develop a teaching-learning model of convergence project based on team teaching. Based on development research methodology which explored a university case, the teaching-learning model was developed including three phases such as preparation, planning, and implementation & evaluation. The preparation phase has three steps as follows: to organize team teaching faculty; to develop convergence projects cooperated by industry and university; and to design instructions based on supporting convergence projects. The last step of preparation phase consists of five design activities of: (1) instructions and teaching contents; (2) communication channel among faculty members; (3) feedback system on students' performance; (4) tools to support learners' activity; and (5) evaluation system. The planning phase has two steps to analyze learners and to introduce and modify instruction and themes of convergence projects. The implementation & evaluation phase includes five steps as bellow: (1) to organize project teams and match teams with faculty members; (2) to do team building and assign duties to students of a team; (3) to provide instruction and consulting to teams; (4) to help teams to conduct projects through creative problem solving; and (5) to design mid-term/final presentation and evaluation. Lastly, the research implications and limitations were discussed for future studies.

• Journal of the Korea Convergence Society
• /
• v.9 no.11
• /
• pp.509-517
• /
• 2018

The present study is a convergence study aimed at investigating the effects of the blended learning method on self-directed learning and learning satisfaction of nursing students. A nonequivalent control group was designed to conduct a pre-post test for this study. The participants were assigned to the experimental(n=70) or control group(n=68). Data was analyzed using ${\chi}^2$-test, independent t-tset, and ANCOVA. The results of this study showed that self-directed learning(F=4.122, p=.044), learning satisfaction (F=4.714, p=.032) were significantly higher in the experimental group with blended learning applied than in the control group that received lecture courses for the subject adult health nursing. In other words, this study found that the blended learning method, which was designed to enable students to learn given tasks on their own outside teaching-centered lectures, can enhance the learning ability of nursing students. The results of this study indicate the need to conduct repeated studies regarding blended learning in various subjects and to develop content considering self-directed learning and learning satisfaction of learners.