• East Asian mathematical journal
• /
• v.38 no.4
• /
• pp.533-547
• /
• 2022

This study investigated the Influence of self-regulation and self-efficacy on academic procrastination of middle school students. For this investigation, 384 middle school students who are in completed the questionnaires including self-regulation, self-efficacy, and academic procrastination in Math Learning. The results were as follows: First, self-regulation and self-efficacy had significant correlations with academic procrastination. Also as a result of hierarchical regression analysis, self-regulation moderated the mediation effect of self-regulation between self-efficacy and academic procrastination. Implications of these results were discussed.

• Journal of Digital Convergence
• /
• v.15 no.6
• /
• pp.273-282
• /
• 2017

The objective of this study was to verify the mediating effects of self-efficacy between metacognition and learning flow in college students in healthcare field. Participants were 300 college students. Self-administered questionnaire data were collected from November 21 to December 2, 2016. Data were analyzed using descriptive statistics, t-test, ANOVA, Pearson correlation coefficients and hierarchical regression analysis with the SPSS/WIN 23.0 program. Results are as follows. Metacognition had positive effects on learning flow(${\beta}=.678$, p<.001). Self-efficacy had a partial mediating effect on the relationship between metacognition and learning flow. The findings of study showed that metacognition was very important for enhancing learning flow and self-efficacy influenced these relationship. This study suggested that it is important to develop and implement teaching and learning strategies with improved metacognition in healthcare field.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.23 no.1
• /
• pp.191-201
• /
• 2023

As Edutech arises which is integrating IT technology into education, many related attempts have been tried on music education area. The focus has been shifted from the teachers to the learners, and this makes the personalized learning emerge. The learner's proficiency is an essential factor to support the personalized learning. The chord fingering is an important technique in piano learning. In this paper, a personalized learning tool for piano chords has been suggested. And then, several utilization ways have been described by analyzing the chords patterns. Specifically, the difficulty of the chords and the proficiency of the learner are derived from the accumulated practicing log data of the users. More effective learning way of the chords has been presented through hierarchical clustering based on chords similarity. Furthermore, the suggested approach where only the practicing log data are used lessens the learner's burden to measure the proficiency and the chord's difficulty without additional efforts like taking tests.

• The Transactions of the Korean Institute of Electrical Engineers
• /
• v.39 no.10
• /
• pp.1121-1232
• /
• 1990

A hierarchical neural network structure is described for robot PTP trajectory planning. In the first level, the multi-layered Perceptron neural network is used for the inverse kinematics with the back-propagation learning procedure. In the second level, a saccade generation model based joint trajectory planning model in proposed and analyzed with several features. Various simulations are performed to investigate the characteristics of the proposed neural networks.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2018.07a
• /
• pp.360-363
• /
• 2018

본 논문에서는 계층적 RNN의 성능 향상을 위하여 강화학습을 통한 계층적 RNN 내 파라미터를 효율적으로 찾는 방법을 제안한다. 계층적 RNN 내 임의의 파라미터에서 학습을 진행하고 얻는 분류 정확도를 보상으로 하여 간소화된 강화학습 네트워크에서 보상을 최대화하도록 강화학습 내부 파라미터를 수정한다. 기존의 강화학습을 통한 내부 구조를 찾는 네트워크는 많은 자원과 시간을 소모하므로 이를 해결하기 위해 간소화된 강화학습 구조를 적용하였고 이를 통해 적은 컴퓨터 자원에서 학습속도를 증가시킬 수 있었다. 간소화된 강화학습을 통해 계층적 RNN의 파라미터를 수정하고 이를 행동 인식 데이터 세트에 적용한 결과 기존 알고리즘 대비 높은 성능을 얻을 수 있었다.

• Management Science and Financial Engineering
• /
• v.19 no.1
• /
• pp.1-10
• /
• 2013

Hierarchical forecasting strategy does not always outperform direct forecasting strategy. The performance generally depends on demand features. This research guides the use of the alternative forecasting strategies according to demand features. This paper developed and evaluated various classification models such as logistic regression (LR), artificial neural networks (ANN), decision trees (DT), boosted trees (BT), and random forests (RF) for predicting the relative performance of the alternative forecasting strategies for the South Korean navy's spare parts demand which has non-normal characteristics. ANN minimized classification errors and inventory costs, whereas LR minimized the Brier scores and the sum of forecasting errors.

• ETRI Journal
• /
• v.41 no.5
• /
• pp.574-584
• /
• 2019

A new Mirai variant found recently was equipped with a dynamic update ability, which increases the level of difficulty for DDoS mitigation. Continuous development of 5G technology and an increasing number of Internet of Things (IoT) devices connected to the network pose serious threats to cyber security. Therefore, researchers have tried to develop better DDoS mitigation systems. However, the majority of the existing models provide centralized solutions either by deploying the system with additional servers at the host site, on the cloud, or at third party locations, which may cause latency. Since Internet service providers (ISP) are links between the internet and users, deploying the defense system within the ISP domain is the panacea for delivering an efficient solution. To cope with the dynamic nature of the new DDoS attacks, we utilized an unsupervised artificial neural network to develop a hierarchical two-layered self-organizing map equipped with a twofold feature selection for DDoS mitigation within the ISP domain.

• KIISE Transactions on Computing Practices
• /
• v.23 no.9
• /
• pp.542-549
• /
• 2017

Sequence-to-sequence models and similar pointer networks suffer from performance degradation when an input is composed of multiple sentences or when the length of the input sentence is long. To solve this problem, this paper proposes a hierarchical pointer network model that uses both the word level and sentence level information to encode input sequences composed of several sentences at the word level and sentence level. We propose a hierarchical pointer network based coreference resolution that performs a coreference resolution for all mentions. The experimental results show that the proposed model has a precision of 87.07%, recall of 65.39% and CoNLL F1 74.61%, which is an improvement of 21.83% compared to an existing rule-based model.

• Journal of Computing Science and Engineering
• /
• v.3 no.3
• /
• pp.165-180
• /
• 2009

The HKIB, or Hankookilbo, test collections are two archives of Korean newswire stories manually categorized with semi-hierarchical or hierarchical category taxonomies. The base newswire stories were made available by the Hankook Ilbo (The Korea Daily) for research purposes. At first, Chungnam National University and KISTI collaborated to manually tag 40,075 news stories with categories by semi-hierarchical and balanced three-level classification scheme, where each news story has only one level-3 category (single-labeling). We refer to this original data set as HKIB-40075 test collection. And then Yonsei University and KISTI collaborated to select 20,000 newswire stories from the HKIB-40075 test collection, to rearrange the classification scheme to be fully hierarchical but unbalanced, and to assign one or more categories to each news story (multi-labeling). We refer to this modified data set as HKIB-20000 test collection. We benchmark a k-NN categorization algorithm both on HKIB-20000 and on HKIB-40075, illustrating properties of the collections, providing baseline results for future studies, and suggesting new directions for further research on Korean text categorization problem.

• Journal of Information Technology Services
• /
• v.7 no.4
• /
• pp.231-246
• /
• 2008

This paper suggests an e-learning system model, a goal-driven personalized e-learning system, which increase the effectiveness of learning. An e-learning system following this model makes the learner choose the learning goal. The learner's choice would lead learning. Therefore, the system enables a personalized adaptive learning, which will raise the effectiveness of learning. Moreover, this paper proposes a SCORM standard, which modifies SCORM 2004 that has been insufficient to implement the "goal driven personalized e-learning system." We add a data model representing the goal that motivates learning, and propose a standard for statistics on learning objects usage. We propose each standard for contents model and sequencing information model which are parts of "goal driven personalized e-learning system." We also propose that manifest file should be added for the standard for contents model, and the file which represents the information of hierarchical structure and general learning paths should be added for the standard for sequencing information model. As a result, the system could sequence and search learning objects. We proposed an e-learning system and modified SCORM standards by considering the many factors of adaptive learning. We expect that the system enables us to optimally design personalized e-learning system.