• The Korean Journal of Applied Statistics
• /
• v.32 no.1
• /
• pp.41-68
• /
• 2019

Multi-view learning considers data from various viewpoints as well as attempts to integrate various information from data. Multi-view learning has been studied recently and has showed superior performance to a model learned from only a single view. With the introduction of deep learning techniques to a multi-view learning approach, it has showed good results in various fields such as image, text, voice, and video. In this study, we introduce how multi-view learning methods solve various problems faced in human behavior recognition, medical areas, information retrieval and facial expression recognition. In addition, we review data integration principles of multi-view learning methods by classifying traditional multi-view learning methods into data integration, classifiers integration, and representation integration. Finally, we examine how CNN, RNN, RBM, Autoencoder, and GAN, which are commonly used among various deep learning methods, are applied to multi-view learning algorithms. We categorize CNN and RNN-based learning methods as supervised learning, and RBM, Autoencoder, and GAN-based learning methods as unsupervised learning.

• The Journal of Society for e-Business Studies
• /
• v.6 no.3
• /
• pp.115-126
• /
• 2001

In constructive view, acquiring knowledge is made by experiences among members or elements. The knowledge in e-learning system can be extended up to knowledge of teachers and knowledge. of operating managers. We have many difficult problems to develop and manage e-1earning system because demanders on e-learning system have various. requirements. In traditional education system demanders are learners but in constructive view demanders can be extended to learners and teachers, operating mangers on e-learning system., In this study, we design and implement e-learning system named kedu V.1. Kedu V.1 is developed considering interactions of extended demanders of e-learning system in constructive view. And this system based on Linux operation system and MySQL, PHP. Also this system have efficient transplantation and portability capabilities and reduced cost and labor in implementation of real e-learning system

• Journal of Korea Game Society
• /
• v.11 no.3
• /
• pp.3-8
• /
• 2011

The learning by computer games, is in the spotlight as an effective education method for the game generation. The educational games need to provide additionally an omniscient view of the learning as an objective viewpoint for storytelling of learning. The omniscient viewpoint needs good readability in real-time, and to provide systematically overall and detailed informations of learning. In this paper, we propose the visual learning map as the omniscient view for storytelling of learning. The proposed learning map is composed of the district map, the topic map, and the progress map for the omniscient view of the learning. The proposed learning map is represented by several visual diagrams for real-time readability. The proposed learning map can apply to all the educational games which provide the game minimaps.

• Journal of the Korean Data and Information Science Society
• /
• v.27 no.2
• /
• pp.295-304
• /
• 2016

This study investigates significant factors in mathematical learning and examines the inter-grade and gender-based differences of elementary students. Five factors that are counted to affect the view of mathematical learning are (1) confidence, (2) utility, (3) aversion, (4) practical ability, and (5) traditional view of mathematical learning. The factor analyses on third graders and sixth graders each illustrate the features of inter-grade factors. The result also indicates that the factors may vary depending on the traits and circumstances of students surveyed. Third graders are more likely to be positive compared to sixth graders in terms of confidence and practical ability, which calls for implementing 'doing mathematics' and reinforcing the method of mathematical learning in the general educational field.

• Journal of the Korean Chemical Society
• /
• v.58 no.1
• /
• pp.105-117
• /
• 2014

The purpose of this study was to analyze pre-service chemistry teachers' view of learning focused on the influence of science education courses that pre-service chemistry teachers had learned. Three pre-service chemistry teachers were selected for this study. Documents related to science education courses, survey data about their view of learning and interview data were collected, transcribed and analyzed. According to this study, pre-service chemistry teachers had changed, modified, maintained and strengthened their view of learning while they took the science education courses. Pre-service teacher K and P had changed their traditional view to the constructive view and then had modified their view by adding the reality. And pre-service teacher H had modified his constructive view with some traditional view. All Pre-service teachers had modified their own view of learning because of the science education course that emphasized the real field situation. As discussed above, science education courses focused on the applying the theory to real teaching situation gave the opportunity to modify pre-service teachers' own view of learning. It implied that the science education courses learned in the teachers college have to include contents based on real teaching situation and pre-service teachers' reflective thinking processes for establishing their view of learning and customized teaching activities.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.9
• /
• pp.4317-4335
• /
• 2018

Semi-supervised multi-view latent space learning is gaining considerable popularity recently in many machine learning applications due to the high cost and difficulty to obtain the large amount of label information of data. Although some semi-supervised multi-view latent space learning methods have been presented, there is still much space for improvement: 1) How to learn latent discriminant intact feature representations by employing data of multiple views; 2) How to exploit the manifold structure of both labeled and unlabeled point in the learned latent intact space effectively. To address the above issues, we propose an approach called semi-supervised multi-view manifold discriminant intact space learning ($SM^2DIS$) for image classification in this paper. $SM^2DIS$ aims to seek a manifold discriminant intact space for data of different views by making use of both the discriminant information of labeled data and the manifold structure of both labeled and unlabeled data. Experimental results on MNIST, COIL-20, Multi-PIE, and Caltech-101 databases demonstrate the effectiveness and robustness of our proposed approach.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.11
• /
• pp.5546-5559
• /
• 2019

Facial action units (AUs) have recently drawn increased attention because they can be used to recognize facial expressions. A variety of methods have been designed for frontal-view AU detection, but few have been able to handle multi-view face images. In this paper we propose a method for multi-view facial AU detection using a fused multilayer, multi-task, and multi-label deep learning network. The network can complete two tasks: AU detection and facial view detection. AU detection is a multi-label problem and facial view detection is a single-label problem. A residual network and multilayer fusion are applied to obtain more representative features. Our method is effective and performs well. The F1 score on FERA 2017 is 13.1% higher than the baseline. The facial view recognition accuracy is 0.991. This shows that our multi-task, multi-label model could achieve good performance on the two tasks.

• Journal of the Korean Chemical Society
• /
• v.57 no.6
• /
• pp.830-844
• /
• 2013

The purpose of this study were to analyze characteristics of pre-service chemistry teachers' practice teaching and to investigate the relationship between their practice teaching characteristics and the view of learning. Three pre-service chemistry teachers were selected for this study. Their 9 practice teaching videos that recorded during practice teaching were observed, transcribed, and analyzed. Responses of questionnaires about their view of learning and interviews were transcribed and analyzed. Almost all of the characteristics of pre-service teachers' practice teaching seemed to be reflected in their view of learning. Pre-service teacher K had a lot of constructive view of learning, so comparatively many features of constructivism was presented in practice teaching. Pre-service teacher M had a lot of traditional view of learning, so many traditional features appeared in practice teaching. However, sometimes pre-service teachers' view of learning did not appear to their practice teaching because of several factors. In particular, a few cases that constructive view of learning was not reflected in the practice teaching appeared, especially pre-service teacher H. Factors were the practice school's conditions and the effects of tutors.

• Journal of Information Processing Systems
• /
• v.15 no.5
• /
• pp.1179-1191
• /
• 2019

We design an ingenious view-pooling method named learning-based multiple pooling fusion (LMPF), and apply it to multi-view convolutional neural network (MVCNN) for 3D model classification or retrieval. By this means, multi-view feature maps projected from a 3D model can be compiled as a simple and effective feature descriptor. The LMPF method fuses the max pooling method and the mean pooling method by learning a set of optimal weights. Compared with the hand-crafted approaches such as max pooling and mean pooling, the LMPF method can decrease the information loss effectively because of its "learning" ability. Experiments on ModelNet40 dataset and McGill dataset are presented and the results verify that LMPF can outperform those previous methods to a great extent.

• Journal of Elementary Mathematics Education in Korea
• /
• v.24 no.3
• /
• pp.259-277
• /
• 2020

The purpose of this study was to develop and validate a scale of Korean elementary teachers' mathematics beliefs. We examined 299 elementary teachers' mathematical beliefs using 30 items, out of which 12 items covered beliefs about the nature of mathematics and 18 items covered beliefs about mathematics teaching and learning. In the first stage, we performed exploratory factor analysis using 149 survey data to examine the factor structure. In the second stage, we performed confirmatory factor analysis using 150 survey data. Building upon previous studies, we examined the construct validity of three different models to find the best factor structure. The study results indicate that the four-factor model with 14 items provides the best fit for the data: transmissive view of mathematics, constructivist view of mathematics, transmissive view of teaching and learning, and constructivist view of teaching and learning. The findings of the study reveal that each factor has adequate internal consistency and reliability. These results confirm that the beliefs scale is a reliable and valid measurement tool to measure Korean elementary teachers' mathematical beliefs. The implications of the study are discussed.