• Database Research
• /
• v.34 no.3
• /
• pp.3-13
• /
• 2018

Text classification is one of the text mining technologies that classifies a given textual document into its appropriate categories and is used in various fields such as spam email detection, news classification, question answering, emotional analysis, and chat bot. In general, the text classification system utilizes machine learning algorithms, and among a number of algorithms, naïve Bayes and support vector machine, which are suitable for text data, are known to have reasonable performance. Recently, with the development of deep learning technology, several researches on applying deep neural networks such as recurrent neural networks (RNN) and convolutional neural networks (CNN) have been introduced to improve the performance of text classification system. However, the current text classification techniques have not yet reached the perfect level of text classification. This paper focuses on the fact that the text data is expressed as a vector only with the word dimensions, which impairs the semantic information inherent in the text, and proposes a neural network architecture based upon the semantic tensor space model.

• Journal of the Korea Society of Computer and Information
• /
• v.14 no.3
• /
• pp.139-147
• /
• 2009

The memory based reasoning just stores in the memory in the form of the training pattern of the representative pattern. And it classifies through the distance calculation with the test pattern. Because it uses the techniques which stores the training pattern whole in the memory or in which it replaces training patterns with the representative pattern. Due to this, the memory in which it is a lot for the other machine learning techniques is required. And as the moreover stored training pattern increases, the time required for a classification is very much required. In this paper, We propose the EAS(Evaluation And Selection) algorithm in order to minimize memory usage and to improve classification performance. After partitioning the training space, this evaluates each partitioned space as MDL and PM method. The partitioned space in which the evaluation result is most excellent makes into the representative pattern. Remainder partitioned spaces again partitions and repeat the evaluation. We verify the performance of Proposed algorithm using benchmark data sets from UCI Machine Learning Repository.

• The Bulletin of The Korean Astronomical Society
• /
• v.41 no.2
• /
• pp.54.2-54.2
• /
• 2016

We present a machine learning approach to estimating stellar atmospheric parameters, effective temperature (Teff), surface gravity (log g), and metallicity ([Fe/H]) for stars observed during the course of the Sloan Digital Sky Survey (SDSS). For training a neural network, we randomly sampled the SDSS data with stellar parameters available from SEGUE Stellar Parameter Pipeline (SSPP) to cover the parameter space as wide as possible. We selected stars that are not included in the training sample as validation sample to determine the accuracy and precision of each parameter. We also divided the training and validation samples into four groups that cover signal-to-noise ratio (S/N) of 10-20, 20-30, 30-50, and over 50 to assess the effect of S/N on the parameter estimation. We find from the comparison of the network-driven parameters with the SSPP ones the range of the uncertainties of 73~123 K in Teff, 0.18~0.42 dex in log g, and 0.12~0.25 dex in [Fe/H], respectively, depending on the S/N range adopted. We conclude that these precisions are high enough to study the chemical and kinematic properties of the Galactic disk and halo stars, and we will attempt to apply this technique to Large Sky Area Multi-Object Fiber Spectroscopic Telescope (LAMOST), which plans to obtain about 8 million stellar spectra, in order to estimate stellar parameters.

• The Bulletin of The Korean Astronomical Society
• /
• v.44 no.1
• /
• pp.81.3-81.3
• /
• 2019

In this study, we apply conditional Generative Adversarial Network, which is one of the deep learning method, to the image-to-image translation from solar magentograms to solar UV and EUV images. For this, we train a model using pairs of SDO/AIA 9 wavelength UV and EUV images and their corresponding SDO/HMI line-of-sight magnetograms from 2011 to 2017 except August and September each year. We evaluate the model by comparing pairs of SDO/AIA images and corresponding generated ones in August and September. Our results from this study are as follows. First, we successfully generate SDO/AIA like solar UV and EUV images from SDO/HMI magnetograms. Second, our model has pixel-to-pixel correlation coefficients (CC) higher than 0.8 except 171. Third, our model slightly underestimates the pixel values in the view of Relative Error (RE), but the values are quite small. Fourth, considering CC and RE together, 1600 and 1700 photospheric UV line images, which have quite similar structures to the corresponding magnetogram, have the best results compared to other lines. This methodology can be applicable to many scientific fields that use several different filter images.

• Journal of Christian Education in Korea
• /
• v.62
• /
• pp.313-334
• /
• 2020

As an element of education, the educational space cannot be separated from the purpose of education. The place of education is not only the passage to deliver actual curriculum, but also the purpose itself that can be accomplished through educational content. That is because the purpose of education cannot be achieved only with instructors, students, curriculum, and methods, but requires a change in the perception of the educational space that represents the goal and the place where it all can be implemented. Nevertheless, the problem that lies with educational space is easy to be overlooked and it has been rather considered as an issue related to the finances or scale of the church. The church educational space gives birth to faith and growth, where spiritual development and experience may occur. However, the reality follows the drawbacks of conventional school classroom arrangements and structures. In addition, even if the church educational space can be arranged according to the needs of its students, it cannot deviate much from the standard uniform format. In particular, the basic environment of church educational space is similar to that of standard school system in terms of arrangement of furniture such as chairs, desks, and its physical structure. As the school system was originally designed and tailored for the purpose of delivering knowledge and standardization, the space for church education must stay away from it. Humans are born and die in a space, where encounter with God also happens. Also, communication with God causes spacial conversion to humans, changing the place of their visitation. So the church educational space must be more meticulously designed and comprehensive than that of school which pursues physical, educational, psychological, social, and artistic purposes because the church educational space pursues the liturgical elements, as well. Therefore, the Christian learning environmental arrangements must seek liturgical elements, which is the major Christian value, by placing Christian artwork or symbols for church visitors. So in this research, I want to stress the role of Christian educational space for spiritual growth and pursue intrinsic and extrinsic changes in learning environment, leading to a greater awareness of the Christian educational space.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.13 no.1
• /
• pp.213-227
• /
• 2017

The recent entry into information society as well as the development and universalization of the Internet through rapid development of ICT technology produced a new educational method called PMP learning. PMP learning overcomes restrictions of previous education methods in terms of time and space and allows the learners to customize their learning environments according to their leads, providing voluntary education that centers on the learners. This study aims to verify the causal relationship in academic achievement of PMP learners through the theory of basic psychological desire, learning satisfaction, and learning metastasis. In order to accomplish this, a study model which applies perceived autonomy, perceived competence, and perceived relationship, which are major variables of the theory of basic psychological desire, was presented. For practical verification of the study model, survey analysis was conducted for students of R High School in Hamyang. Through this, the study aims to provide basic materials for improving the academic achievement of learners in PMP learning. It also plans to suggest educational effects that can be obtained by supporting intrinsic motivation of learners.

• Proceedings of the Korea Association of Information Systems Conference
• /
• 1997.10a
• /
• pp.635-696
• /
• 1997

• The Journal of Sustainable Design and Educational Environment Research
• /
• v.3 no.1
• /
• pp.24-34
• /
• 2003

The architectural design of student circulation space has a pronounced influence on the educational function of a school building. Recent curriculum and new teaching methods have required the sufficient space provided for circulation and various circulation spaces in a school building, such as elevator, pilotis, bridge, atrium, deck, lobby and locker room. However excessive circulation space is wasteful form the standpoint of both initial investment and operation. This study aims to investigate new circulation patterns and functions, and to propose the adequate size in planning a school corridor. For this purpose, it explores the recent trends of the corridor planning represented in the excellent school facilities in 2002. and analyzes the newly-added functions In the school corridor : architectural in-between space, dwelling space for ordinary activities, space for educational media and auxiliary learning space. This research recommends that the corridor width be carefully planned according to the supposed functions in order to achieve the efficiency in the design of school facilities.

• Journal of The Korean Association of Information Education
• /
• v.9 no.3
• /
• pp.523-532
• /
• 2005

Moving figures and piling up some boxes are newly the introduced studying contents in the 7th curriculum of mathematics and it will be able to form the sense of space of the students. Against the studying contents for the sense of space formation, the teachers of site speak instruction is very difficult and the student's scores are low. Elementary school mathematics studying which inclusive of figure studying is the most effective when they operate the actual object. But in the school site, the instruction with actual object is very difficult because many reasons. And web based studying data system which is for forming the sense of space the students is not abundant because it started initially. From this dissertation, studying contents will be taken out and web base figure studying system will be designed and embodied. The interaction will be active in the system. Student will be able to understand the principle by the medium of the animation from the system and they can improve their sense of space by the interesting game.

• Journal of KIISE:Computing Practices and Letters
• /
• v.14 no.1
• /
• pp.106-110
• /
• 2008

The requirement for customized learning environments is increasing with the development of Web 2.0 technology To personalize services in E-learning, there are various functions available to the user. However, some components have fixed or inflexible functionality that limits what can be changed, and customization information has not been used for other purposes. In this paper, we propose an e-Space manager for the dynamic customization of learning environment control units. The proposed method can confirm which areas users have customized and how they have customized them. The advantage is that users can control their own learning environments, including not only the format, but also the content within the limits of the underlying system. The customization information is captured to confirm the competency model.