• 천문학회지
• /
• 제53권6호
• /
• pp.139-147
• /
• 2020

The sunspot area is a critical physical quantity for assessing the solar activity level; forecasts of the sunspot area are of great importance for studies of the solar activity and space weather. We developed an innovative hybrid model prediction method by integrating the complementary ensemble empirical mode decomposition (CEEMD) and extreme learning machine (ELM). The time series is first decomposed into intrinsic mode functions (IMFs) with different frequencies by CEEMD; these IMFs can be divided into three groups, a high-frequency group, a low-frequency group, and a trend group. The ELM forecasting models are established to forecast the three groups separately. The final forecast results are obtained by summing up the forecast values of each group. The proposed hybrid model is applied to the smoothed monthly mean sunspot area archived at NASA's Marshall Space Flight Center (MSFC). We find a mean absolute percentage error (MAPE) and a root mean square error (RMSE) of 1.80% and 9.75, respectively, which indicates that: (1) for the CEEMD-ELM model, the predicted sunspot area is in good agreement with the observed one; (2) the proposed model outperforms previous approaches in terms of prediction accuracy and operational efficiency.

• 한국인터넷방송통신학회논문지
• /
• 제10권6호
• /
• pp.125-130
• /
• 2010

협동학습이란 서로 다른 능력을 갖는 학생들이 주어진 주제에 대한 이해를 증진하기 위하여 다양한 학습 방법을 사용하여 단지 무엇을 배울 것인지 뿐 아니라 팀 구성원들의 학습을 도움으로서 보다 높은 성취도를 갖게 하는 학습방법이다. 본 논문에서는 협동학습 교육프로그램 활용을 위한 효율적인 팀 구성 방법에 대해서 기술한다. 이를 위해 초등학교 학생들을 위한 영어와, 수학 협동학습 프로그램을 구현하였다. 이 협동학습 교육프로그램을 활용하여 학습자들은 협동학습을 수행하였으며 성적, 성별, 친밀도 별 실험을 실시하였다. 결과로 혼성이며 성적이 상호보완적인 팀이 가장 효율적임을 알 수 있었다.

• International Journal of Contents
• /
• 제12권2호
• /
• pp.49-57
• /
• 2016

This paper aims to explore instructional design of a cyber classroom for secondary students' basic English language competence. A paucity of support for low or under achieving students' English learning exists particularly at the secondary level. In order to bridge the gap, there has been demand for online educational resources considered to be an effective tool in improving students' self-directed learning and motivation. This study employs a comprehensive approach to instructional design for the asynchronous cyber classroom with the underlying premise that different learning theories can be applied in a complementary manner to serve different pedagogical purposes best. Gagné's conditions of learning theory, Bruner's constructivist theory, Carroll's minimalist theory, and Vygotsky's social cognitive development theory serve as the basis for designing instruction and selecting appropriate media. The ADDIE model is used to develop online teaching and learning materials. Twenty-five key grammatical features were selected through the analysis of the national curriculum of English, being grouped into five units. Each feature is covered in one cyber asynchronous class. An Integration Class is given at the end of every five classes for synthesis, where students can practice grammatical features in a communicative context. Related theories, pedagogical practices, and practical web-design strategies for cyber Basic English classes are discussed with suggestions for research, practice and policy to support self-directed learning through a cyber class.

• Asia pacific journal of information systems
• /
• 제33권3호
• /
• pp.737-767
• /
• 2023

With the availability of big customer data and advances in machine learning techniques, the prediction of customer behavior at the session-level has attracted considerable attention from marketing practitioners and scholars. This study aims to predict customer purchase conversion at the session-level by employing customer profile, transaction, and clickstream data. For this purpose, we develop a multimodal deep learning fusion model with dynamic and static features (i.e., DS-fusion). Specifically, we base page views within focal visist and recency, frequency, monetary value, and clumpiness (RFMC) for dynamic and static features, respectively, to comprehensively capture customer characteristics for buying behaviors. Our model with deep learning architectures combines these features for conversion prediction. We validate the proposed model using real-world e-commerce data. The experimental results reveal that our model outperforms unimodal classifiers with each feature and the classical machine learning models with dynamic and static features, including random forest and logistic regression. In this regard, this study sheds light on the promise of the machine learning approach with the complementary method for different modalities in predicting customer behaviors.

• International journal of advanced smart convergence
• /
• 제9권2호
• /
• pp.90-104
• /
• 2020

It is difficult for non-experts to build machine learning (ML) models at the level that satisfies their needs. Deep learning models are even more challenging because it is unclear how to improve the model, and a trial-and-error approach is not feasible since training these models are time-consuming. To assist these novice users, we examined how interactive and explainable feedback while training a deep learning network can contribute to model performance and users' satisfaction, focusing on the data preparation process. We conducted a user study with 31 participants without expertise, where they were asked to improve the accuracy of a deep learning model, varying feedback conditions. While no significant performance gain was observed, we identified potential barriers during the process and found that interactive and explainable feedback provide complementary benefits for improving users' understanding of ML. We conclude with implications for designing an interface for building ML models for novice users.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제7권4호
• /
• pp.819-833
• /
• 2013

Computing global features based on local features using a bio-inspired framework has shown promising performance. However, for some tough applications with large intra-class variances, a single local feature is inadequate to represent all the attributes of the images. To integrate the complementary abilities of multiple local features, in this paper we have extended the efficacy of the bio-inspired framework, HMAX, to adapt heterogeneous features for global feature extraction. Given multiple global features, we propose an approach, designated as parameterized metric learning, for high dimensional feature fusion. The fusion parameters are solved by maximizing the canonical correlation with respect to the parameters. Experimental results show that our method achieves significant improvements over the benchmark bio-inspired framework, HMAX, and other related methods on the Caltech dataset, under varying numbers of training samples and feature elements.

• 지식경영연구
• /
• 제6권2호
• /
• pp.67-90
• /
• 2005

Attention has been focused recently on the concept of shared cognition which encompasses the notion that effective team members hold knowledge that is overlapping and complementary with teammates. This shared cognition is expected to improve team effectiveness. In contrast to the continued efforts in developing theoretical approach of shared cognition, empirical studies are meager. Thus, we conducted an empirical study to investigate the role of shared cognition on team effectiveness. This study classifies shared cognition into two types, team mental model and transactive memory system, by shared meaning. A total of 121 new product development teams in the IT industry were surveyed for the data collection. The results of analysis can be summarized as follows: first, team mental model has a positive influence on team performance, team innovative behavior and team learning effect. And the relation with team mental model and team performance is moderated by the similarity of knowledge structure among the expert. Second, transactive memory system has a positive influence on team performance, team innovative behavior and team learning effect.

• Educational Technology International
• /
• 제23권1호
• /
• pp.1-39
• /
• 2022

We study emotion regulation in a distant CABLe (Collaborative Argumentation Based-Learning) setting at university. We analyze how students achieve the group task of synthesizing the literature on a topic through scientific argumentation on the institutional Moodle's forum. Distinguishing anticipatory from reactive emotional regulation shows how essential it is to establish and maintain a constructive working climate in order to make the best out of disagreement both on social and cognitive planes. We operationalize the analysis of anticipatory emotional regulation through an analytical grid applied to the data of two groups of students facing similar disagreement. Thanks to sharp anticipatory regulation, group 1 solved the conflict both on the social and the cognitive plane, while group 2 had to call out for external regulation by the teacher, stuck in a cyclically resurfacing dispute. While the institutional digital environment did afford anticipatory emotional regulation, reactive emotional regulation rather occurred through complementary informal and synchronous communication tools. Based on these qualitative case studies, we draw recommendations for fostering distant CABLe at university.

• 한국학교수학회논문집
• /
• 제17권4호
• /
• pp.465-492
• /
• 2014

본 연구에서는 수학과 수업에 적용할 수 있는 지도 방법으로서 수준별 협동학습 학습지를 활용한 수준별 수업과 소집단 협동학습에서 그 효과를 알아보는데 목적이 있다. 이를 위해서 구체적인 연구문제를 살펴보면 다음과 같다. 첫째, 수준별 협동학습 학습지를 활용한 학급 내 수준별 협동학습으로 학생들의 수학의 학업성취도를 향상시킬 수 있는가? 둘째, 수준별 협동학습 학습지를 활용한 학급 내 수준별 협동학습으로 수학 교과에 대한 흥미와 자신감을 갖도록 하여 협동학습 태도를 향상시킬 수 있는가? 셋째, 수준별 협동학습 학습지를 활용한 학급 내 수준별 협동학습에 대한 학생들의 반응은 어떠한가? 이다. 연구결과로는 첫째, 실험집단은 비교집단에 비하여 학업성취도에 향상을 보여 주었다. 둘째, 실험집단은 비교집단에 비하여 협동학습 태도의 변화에 도움이 되었다. 셋째, 수준별 협동학습 학습지를 활용한 학급 내 수준별 협동학습으로 실험집단은 비교집단에 비하여 의미 있는 반응을 나타내었다.

• 한국측량학회지
• /
• 제38권6호
• /
• pp.499-509
• /
• 2020

본 연구에서는 최근 영상판독 분야에서 활발히 연구되고, 활용성이 발전하고 있는 인공지능 기반 객체분류 학습 데이터 구축에 관한 내용을 다룬다. 영상판독분야에서 인공지능을 활용하여 정확도 높은 객체를 인식, 추출하기 위해서는 알고리즘에 적용할 많은 양의 학습데이터가 필수적으로 요구된다. 하지만, 현재 공동활용 가능한 데이터 셋이 부족할 뿐만 아니라 데이터 생성을 위해서는 많은 시간과 인력 및 고비용을 필요로 하는 것이 현실이다. 따라서 본 연구에서는 소량의 초기 항공영상 학습데이터를 GAN (Generative Adversarial Network) 기반의 생성기 신경망을 활용하여 오버샘플 영상 학습데이터를 구축하고, 품질을 평가함으로써 추가적 학습 데이터 셋으로 활용하기 위한 실험을 진행하였다. GAN을 이용하여 오버샘플 학습데이터를 생성하는 기법은 딥러닝 성능에 매우 중요한 영향을 미치는 학습데이터의 양을 획기적으로 보완할 수 있으므로 초기 데이터가 부족한 경우에 효과적으로 활용될 수 있을 것으로 기대한다.