• The KIPS Transactions:PartB
• /
• v.13B no.4 s.107
• /
• pp.383-392
• /
• 2006

In this paper, we propose a new relevance feedback algorithm using Probabilistic Neural Networks(PNN) while supporting multi-class learning. Then, to validate the effectiveness of our feedback approach, we incorporate the proposed algorithm into our region-based image retrieval tool, FRIP(Finding Regions In the Pictures). In our feedback approach, there is no need to assume that feature vectors are independent, and as well as it allows the system to insert additional classes for detail classification. In addition, it does not have a long computation time for training because it only has four layers. In the PNN classification process, we store the user's entire past feedback actions as a history in order to improve performance for future iterations. By using a history, our approach can capture the user's subjective intension more precisely and prevent retrieval performance errors which originate from fluctuating or degrading in the next iteration. The efficacy of our method is validated using a set of 3000 images derived from a Corel-photo CD.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.11
• /
• pp.1559-1565
• /
• 2021

In this paper, an antenna selection scheme is proposed in massive multi-user multiple input multiple output (MU-MIMO) systems. The proposed antenna selection scheme can achieve almost the same performance as a conventional scheme while significantly reducing the overhead of feedback by using deep reinforcement learning (DRL). Each user compares the channel gains of massive antennas in base station (BS) to the L-largest channel gain, converts them to one-bit binary numbers, and feed them back to BS. Thus, the feedback overhead can be significantly reduced. In the proposed scheme, DRL is adopted to prevent the performance loss that might be caused by the reduced feedback information. We carried out extensive Monte-Carlo simulations to analyze the performance of the proposed scheme and it was shown that the proposed scheme can achieve almost the same average sum-rates as a conventional scheme that is almost optimal.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2001.04b
• /
• pp.1041-1044
• /
• 2001

현재 웹 상에서 이루어지는 교육은 개별 학습자의 학습 기대 수준에 따라 주문형(customization)과 맞춤형(personalization)교육이 요구되고 있으나 대부분 웹을 통한 교육이 획일적 커리큘럼에 따라 진행되고, 동일한 형태의 피드백을 제공하고 있어 학습자 개개인의 수준에 맞는 컨텐츠의 제공과 적절한 피드백이 이루어지지 못하고 있다. 따라서 학습 효과를 높이기 위해서는 학습자 수준에 맞는 차별화된 컨텐츠를 구성하여 제공하여야 한다. 본 연구에서는 수준별 학습, 맞춤형 교육 서비스를 제공하기 위한 컨텐츠 구성방법에 관하여 논의한다. 양질의 맞춤형 컨텐츠를 구성하기 위해 컨텐츠를 영역별로 분류하여 모듈화하고, 맞춤형 컨텐츠를 효율적으로 관리하여 학습자의 지식영역별 습득정도를 파악하고, 학습자의 수준에 맞게 융통성이 있으며 동적으로 컨텐츠를 재구성함으로써 학습자에게 가장 적절한 컨텐츠를 추출하여, 반복 학습을 통한 교육의 질적 제고를 기대한다.

• 한국정보교육학회:학술대회논문집
• /
• 2008.01a
• /
• pp.211-216
• /
• 2008

프로그래밍 교육은 학습자의 창의적이고 논리적인 사고력을 함양시키고 문제해결능력을 신장시킬 수 있는 ICT 교육의 한 분야로서 많은 교육적 가치를 가지고 있다. 프로그래밍과 관련된 초등학교 교육내용은 7차 교육과정에서 누락되었지만 2005년 12월에 개정된 초 중등학교 정보통신기술 운영 지침에 따라 초등학교에도 프로그래밍 교육과정이 도입되었다. 따라서 본 논문은 5, 6학년 '정보처리의 이해' 영역의 프로그래밍에 관련된 학습내용을 학년별 연계성을 고려하여 재구성하고 학습 성취에 대한 피드백을 강화하는 프로그래밍 교육을 위한 웹 코스웨어를 설계 하였다. 웹을 기반으로 설계된 이 시스템은 학교나 가정에서의 프로그래밍 교육 기회를 확대시키는 역할을 하며, 학습자가 학습 성취도를 직접 확인하여 자신의 능력에 맞게 학습속도를 조절할 수 있어 자기 주도적 학습 능력이 향상될 것으로 기대된다. 또한 학습자에게 다양한 동기유발 자료와 학습 결과에 대한 적절한 피드백을 제공함으로써 프로그래밍 교육에 대한 흥미와 학습 성취도를 높일 것으로 기대된다.

• The KIPS Transactions:PartB
• /
• v.17B no.2
• /
• pp.139-148
• /
• 2010

This paper shows a reinforcement post-processing method and feedback algorithm for improvement of assigning method in classification. Especially, we focused on complex documents that are generally considered to be hard to classify. A basis factors in traditional classification system are training methodology, classification models and features of documents. The classification problem of the documents containing shared features and multiple meanings, should be deeply mined or analyzed than general formatted data. To address the problems of these document, we proposed a method to expand classification scheme using decision boundary detected automatically in our previous studies. The assigning method that a document simply decides to the top ranked category, is a main factor that we focus on. In this paper, we propose a post-processing method and feedback algorithm to analyze the relevance of ranked list. In experiments, we applied our post-processing method and one time feedback algorithm to complex documents. The experimental results show that our system does not need to change the classification algorithm itself to improve the accuracy and flexibility.

• Journal of Digital Convergence
• /
• v.14 no.6
• /
• pp.285-294
• /
• 2016

The purpose of this study was to examine the effectiveness(knowledge of core fundamental nursing skills, clinical competency, self-efficacy and learning motivation) of education program for core fundamental nursing skills focusing on endotracheal suctioning using recording video with smartphone and formative feedback for nursing school students. Subjects consisted of 54 sophomore nursing students, an experimental group(n=27) and a control group(n=27). The education for core fundamental nursing skills using recording video to smartphone and individual formative feedback was provided to students in an experimental group. The traditional method with self-directed practice for 4 hours was offered to a control group. The education program for core fundamental nursing skills using recording video with smartphone and formative feedback was effective in promoting knowledge of core fundamental nursing skills, clinical competency, self-efficacy and learning motivation. Based on our results, this program can be recommended as an effective educational program for the nursing students to improve their core fundamental nursing skills.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.21 no.6
• /
• pp.9-15
• /
• 2021

The current study examined the cyber learners' perceptions of the educational usefulness of Grammarly, an online grammar checker, after it was used to provide feedback to cyber university students in a situation where the instructor could not provide sufficient feedback on their written work in English. The survey results, revealed that the majority of learners had positive attitudes to the usefulness of Grammarly. In particular, the feedback immediately available whenever needed was regarded as helpful in improving English sentences, and most learners were highly satisfied with the amount of the feedback provided by Grammarly. It was also found that Grammarly had positive effects in terms of the affective domains, helping learners to improve their interest and confidence in English writing. In particular, Grammarly was found to be effective in reducing writing anxiety in English, one of the main factors negatively affecting writing performance in English. However, along with these positive results, limitations such as inaccurate feedback and inadequate explanation of errors were also found. Therefore, when Grammarly is used for English education, it is necessary to conduct multifaceted research to develop effective teaching methods that can minimize the problems that may arise from these limitations.

• Proceedings of the Korean Information Science Society Conference
• /
• 2005.07a
• /
• pp.88-90
• /
• 2005

컴퓨터 개별적응 검사(CAT: Computerized Adaptive Testing)란 각 학습자 수준에 적절한 형태의 검사를 개별적으로 실시함으로써 짧은 시간 안에 적은 수의 문항으로도 측정하고자 하는 제 특성을 보다 정확하고 효율적으로 측정할 수 있게 하는 기법이다. 이는 학습자 중심의 수준별 교육을 위한 학습 도구로서 이용될 수 있다. 본 연구에서는 문항반응이론 기반의 CAT를 학습에 적용시킴으로써 학습자의 평가결과에 따라 즉각적인 피드백을 통한 개별학습을 할 수 있고 일정수준의 성취단계에 이를 때까지 스스로 부족한 부분에 대한 평가를 계속 실시하여 완전학습에 도달할 수 있는 새로운 형태의 CAT 기반 학습시스템을 제시한다.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.12 no.8
• /
• pp.3486-3491
• /
• 2011

This study aims to identify the effect of neurofeedback training by observing the pre and post brainwave measurement results of about 60(experimental group 30, control group 30) subjects who have shown self directed learning ability. The study took place at neuro-training center B, in between the months of Jan. 2010 and Jul. 2010. As the brainwaves are adjusted by timeseries linear analysis. The result confirmed the differences of both self regulation quotient, training protocol, and questionnaire. The result of the study suggest neurofeedback technique's possibility in positively affecting the subjects' self directed learning ability.

• Journal of the Korean Chemical Society
• /
• v.51 no.2
• /
• pp.193-200
• /
• 2007

This study investigated the effects of situational context feedback in CAI upon students' conceptual understanding, science learning motivation, and the perception of CAI. Seventh graders (N = 114) from a coed middle school in Incheon were assigned to the situational context feedback CAI (SCF-CAI), the feedback CAI (F-CAI) and the CAI groups, and were taught about ‘three states of matter' and ‘motion of molecules' for 8 class hours. Prior science achievement test score used as a blocking variable. Two-way ANCOVA results revealed that the conceptual understanding test scores of the SCF-CAI group were significantly higher than those of the other groups. For the higher achievers, the scores of the F-CAI group in science learning motivation test were significantly higher than those of the CAI group. However, there was no significant difference among the lower achievers of three groups. The higher achievers in the SCFCAI and the F-CAI groups perceived the CAI more positively than those of the CAI group. The lower achievers in the FCAI group perceived the CAI more negatively than those of the other groups. Educational implications are discussed.