• Journal of the Semiconductor & Display Technology
• /
• v.22 no.1
• /
• pp.129-133
• /
• 2023

Image compression is a fundamental technique in the field of digital image processing, which will help to decrease the storage space and to transmit the files efficiently. Recently many deep learning techniques have been proposed to promise results on image compression field. Since many image compression techniques have artifact problems, this paper has compared two deep learning approaches to verify their performance experimentally to solve the problems. One of the approaches is a deep autoencoder technique, and another is a deep convolutional neural network (CNN). For those results in the performance of peak signal-to-noise and root mean square error, this paper shows that deep autoencoder method has more advantages than deep CNN approach.

• Educational Technology International
• /
• v.18 no.1
• /
• pp.49-71
• /
• 2017

The purpose of the study was to identify key design features of virtual reality with head-mounted displays (HMD) and touchless interface for the hearing-impaired and hard-of-hearing learners. The virtual reality based training program was aimed to help hearing-impaired learners in machine operating learning, which requires spatial understanding to operate. We developed an immersive virtual learning environment prototype with an HMD (Oculus Rift) and a touchless natural user interface (Leap Motion) to identify the key design features required to enhance virtual reality for the hearing-impaired and hard-of-hearing learners. Two usability tests of the prototype were conducted, which revealed that several features in the system need revision and that the technology presents an enormous potential to help hearing-impaired learners by providing realistic and immersive learning experiences. After the usability tests of hearing-impaired students' exploring the 3D virtual space, interviews were conducted, which also established that further revision of the system is needed, which would take into account the learners' physical as well as cognitive characteristics.

• Proceedings of the Korean Institute of Interior Design Conference
• /
• 2002.04a
• /
• pp.91-98
• /
• 2002

This thesis is aimed to suggest the efficiency at the education space for job-rehabilitation through grasping the characteristics of behavior and attitude of the handicapped and analyzing their loaming behavior as an employment promotion for the disabled. For that purpose, the demand of the handicapped and some overlooked space problems we searched by survey, interview, observation and investigation to offer basic data for interior design planning. It resulted firstly that the inconvenience of narrow space was pointed out in many responses implying users suffer from the stress and inconvenience caused by an unconsidered space planning to their behavior. And secondly further difficulties are added when medical appliances for the disabled are not appropriate to common furniture. Finally, without identification of the behavior and attitude of the handicapped the minimum or optimum space needed for them could not be suggested and it may cause to decrease the efficiency in their learning.

• The Bulletin of The Korean Astronomical Society
• /
• v.44 no.1
• /
• pp.52.2-52.2
• /
• 2019

Global map of solar surface magnetic field, such as the synoptic map or daily synchronic frame, does not tell us real-time information about the far side of the Sun. A deep-learning technique based on Conditional Generative Adversarial Network (cGAN) is used to generate farside magnetograms from EUVI $304{\AA}$ of STEREO spacecrafts by training SDO spacecraft's data pairs of HMI and AIA $304{\AA}$. Farside(or backside) data of daily synchronic frames are replaced by the Ai-generated magnetograms. The new type of data is used to calculate the Potential Field Source Surface (PFSS) model. We compare the results of the global field with observations as well as those of the conventional method. We will discuss advantage and disadvantage of the new method and future works.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2001.11a
• /
• pp.807-813
• /
• 2001

본 논문에서는 기업교육에 있어서 e-Learning을 효과적으로 실현하기 위해 Information Filtering을 제안하고자 한다. 사용자 profile에 기반하여 지식 경영상 시스템을 기업교육에 도입함으로써 정보 검색 시 term space에서 모든 단어를 vector로 나타내어, 사용자 profile과 비교 측정하여 다음 유사한 측정을 통해서 원하는 정보 문서를 사용자에게 제공한다. Information Filtering의 도입으로 사용자의 흥미 변화에 맞춰 다이나믹하게 공급되는 학습 문서속에서 기업을 위한 e-Learning으로 경영성과를 높이는 하나의 전력을 제시한다.

• Tunnel and Underground Space
• /
• v.6 no.4
• /
• pp.316-325
• /
• 1996

A new accelerated neural network adopting modified sigmoid function was developed and applied to estimate engineering properties of rock from insufficient geological data. Developed network was tested on the well-known XOR and character recognition problems to verify the validity of the algorithms. Both learning speed and recognition rate were improved. Test learn on the Lee and Sterling's problems showed that learning time was reduced from tens of hours to a few minutes, while the output pattern was almost the same as other studies. Application to the various case studies showed exact coincidence with original data or measured results.

• The Bulletin of The Korean Astronomical Society
• /
• v.42 no.2
• /
• pp.64.3-64.3
• /
• 2017

For the detection of transient sources in optical wide field surveys like KMTNet Supernova Project, difference imaging technique is commonly used. As this method produces a fair amount of false positives, it is also common to utilize machine learning algorithms to screen likely true positives. While deep learning methods such as a convolutional neural network has been successfully applied recently, its application can be limited if the size of the training sample is small. I will discuss a variation of more conventional method that adopts the wavelet transform for feature engineering and its performance.

• Journal of the Korean Statistical Society
• /
• v.36 no.3
• /
• pp.367-372
• /
• 2007

Classification as a tool to extract information from data plays an important role in science and engineering. Among various classification methodologies, support vector machine has recently seen significant developments. The central problem this paper addresses is the accuracy of support vector machine. In particular, we are interested in the situations where fast rates of convergence to the Bayes risk can be achieved by support vector machine. Through learning examples, we illustrate that support vector machine may yield fast rates if the space spanned by an adopted kernel is sufficiently large.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1993.06a
• /
• pp.761-764
• /
• 1993

In this paper we consider techniques for reducing the generated number of rules in learning fuzzy controllers of the state-space action-reinforcement type that can be simply implemented and that behave well in the presence of process noise. Fewer rules lead to better performance, less contradiction in controller action estimation, smaller required execution-time and make it easier for a human to comprehend the generated rules and possibly intervene.

• Journal of The Korean Association of Information Education
• /
• v.11 no.1
• /
• pp.79-89
• /
• 2007

Considering the continuous increase of teenagers' Internet use and the high rate of their participation in online communities, educators need to devote efforts to minimize the negative function of teenagers' Internet use and to guide them to experience positive aspects of Internet. Through activities in online communities, teenagers can experience various socialities and explore their self-consciousness. However, on the other hand many communities do not provide teenagers with considerate care. This may cause conflict in their sense of value and mislead them. Through this study, online learning community is designed and developed, which can reflect teenagers' various needs and connect their needs with learning experiences. The community consists of the following categories: 'about e-Tivity'(community vision, general information, list of activities, Q&A), 'activity space for teens'(event hall, data park, e-Tivity center), 'administrative space for teachers and managers'(research room, management room), and 'teen's private space'(my room, my avatar).