• Proceedings of the Safety Management and Science Conference
• /
• 2000.05a
• /
• pp.111-123
• /
• 2000

The recycling cell formation problem means that disposal products are classified into recycling part families using group technology in their end of life phase. Disposal products have the uncertainties of product status by usage influences. Recycling cells are formed considering design, process and usage attributes. In this paper, a novel approach to the design of cellular recycling system is proposed, which deals with the recycling cell formation and assignment of identical products concurrently. Fuzzy clustering algorithm and Fuzzy-ART neural network are applied to describe the states of disposal product with the membership functions and to make recycling cell formation. This approach leads to recycling and reuse of the materials, components, and subassemblies and can evaluate the value at each cell of disposal products. Application examples are illustrated by disposal refrigerators, compared fuzzy clustering with Fuzzy-ART neural network performance in cell formation.

• Proceedings of the Korea Contents Association Conference
• /
• 2008.05a
• /
• pp.176-181
• /
• 2008

This study aims at providing developmental process for art and cultural space putting into an alternative in pursue of territorial arts and applicable tourist resources by bridging connectivity between arts and tourism. It overviews art promotional policies by a variety of associations since the end of 1990s, focusing on studios for art creation, while attempting to develop effective and practical operational process by analytically identifying in detail various touch points possibly occurrently in the field of arts and culture.

• ETRI Journal
• /
• v.44 no.3
• /
• pp.476-490
• /
• 2022

With the recent advances in technology, automatic speech recognition (ASR) has been widely used in real-world applications. The efficiency of converting large amounts of speech into text accurately with limited resources has become more vital than ever. In this study, we propose a method to rapidly recognize a large speech database via a transformer-based end-to-end model. Transformers have improved the state-of-the-art performance in many fields. However, they are not easy to use for long sequences. In this study, various techniques to accelerate the recognition of real-world speeches are proposed and tested, including decoding via multiple-utterance-batched beam search, detecting end of speech based on a connectionist temporal classification (CTC), restricting the CTC-prefix score, and splitting long speeches into short segments. Experiments are conducted with the Librispeech dataset and the real-world Korean ASR tasks to verify the proposed methods. From the experiments, the proposed system can convert 8 h of speeches spoken at real-world meetings into text in less than 3 min with a 10.73% character error rate, which is 27.1% relatively lower than that of conventional systems.

• Korean Institute of Interior Design Journal
• /
• v.19 no.3
• /
• pp.38-45
• /
• 2010

Surface has been an important issue in contemporary architecture. That originates in structural freedom of surface since the end of modern architecture and the current stream of surface becoming an identity of building. Development of digital-media has brought a great change to our society in general. Digital-media is characterized by use of digital-information and interactive communication. Digital-media has been applied on surface in contemporary architecture lately. It is a purpose of the study to analyze the characteristics of digital-media application on surface based on the related characteristics of installation art. The categories and the contents for the frame of case analysis were arranged through document research. The foreign and domestic cases of digital-media application were analyzed based on the frame of analysis. Digital-media, which is installed on surface, is interacted with human and surroundings. It enhances emotional communication between human and architecture. Surface is not any more a simple fixture but an interactive creature. It makes surface more dynamically and fluidly that the course of light and human movement affect on digital-media. Surface itself is also turned into an object of art. It reflects the interweaving characteristics between contemporary architecture and installation art. It was analyzed through the study that emotional level of people is the important issue shared in digital-media application on surface and installation art. The complementary relationship between surface of contemporary architecture and installation art can be manipulated by the application of digital-media on surface.

• Journal of Science of Art and Design
• /
• v.7
• /
• pp.150-172
• /
• 2005

This is the one concept of the Korea paintings which defines the korea Art sprite. The line of korea painting is very important. It is impressions, korea artist had mastered the difficult art line of representing movement. That offers the important motive, that is discovery of Identity. this korea painting's line is like to meditation. To meditate is to think and ponder about the same holy truth for many hours on end, to fix an idea in one's mind and to look at it from all sides without letting go of it. That is the purpose behind the greatest of the korean landscape paintings Futhermore that is the purpose Shui-Mo paintings. This is the most important. What the korean value most highly in art. There is something wonderful in this restraint of Korea art, in its deliberate limitation to a few simple motifs of nature. But today, anyone did not interested in this motif. So that Shui-Mo paintings did not concerned too. Therefore, we consider it childish to look for details in pictures and then to compare them with the real world. We masters to acquire such a facility in the handling of brush and ink that write down their vision while their inspiration was still fresh.

• The Journal of the Convergence on Culture Technology
• /
• v.8 no.6
• /
• pp.215-222
• /
• 2022

This study summarizes the basic concepts of NFT art and analyzes trends in the domestic and international NFT market to provide a better understanding of the art form to suggest various ways to utilize the art in near future when social interests in technologies such as metaverse, block chain, and NFTs are continuously increasing. In addition, by examining the rapid development and process of blockchain technology in overseas markets, and confirming cases of information transfer to various metaverses such as cryptocurrency and NFT technology, the aim is to present a foothold for the future direction of national arts in general. To this end, in order to analyze consumers' perceptions and preferences, and to draw conclusions about current NFT arts at home and abroad, a survey was conducted on NFT awareness among participants of an art fair in Gwangjin-gu, Seoul. It is hoped that this study will become a cornerstone of research on NFT works and NFT art industry, which is becoming a global issue.

• Journal of Korea Multimedia Society
• /
• v.24 no.10
• /
• pp.1380-1390
• /
• 2021

The video face recognition (FR) is one of the most popular researches in the field of computer vision due to a variety of applications. In particular, research using the attention mechanism is being actively conducted. In video face recognition, attention represents where to focus on by using the input value of the whole or a specific region, or which frame to focus on when there are many frames. In this paper, we propose a novel attention based deep learning method. Main novelties of our method are (1) the use of combining two loss functions, namely weighted Softmax loss function and a Triplet loss function and (2) the feasibility of end-to-end learning which includes the feature embedding network and attention weight computation. The feature embedding network has a positive effect on the attention weight computation by using combined loss function and end-to-end learning. To demonstrate the effectiveness of our proposed method, extensive and comparative experiments have been carried out to evaluate our method on IJB-A dataset with their standard evaluation protocols. Our proposed method represented better or comparable recognition rate compared to other state-of-the-art video FR methods.

• Journal of Digital Convergence
• /
• v.17 no.11
• /
• pp.61-70
• /
• 2019

The The government has recently announced its mid- to long-term plans for promoting art. With the advent of the 4th industrial revolution, contemporary art contents that are integrated with Intelligent Information Technologies such as Artificial Intelligence (AI), Virtual Reality (VR), and Big Data are being introduced, and social interest in humanities and creative convergence is rising. In addition, the industrialization of the art market is expanding amid the rising popularity of art among the general public and the growing interest of art as an investment replacement system, along with the strengthening of the creative personality education of our Education Ministry. Therefore, it is necessary to establish a strategy for transparency and revitalization of the art market by providing comprehensive information such as search functions, analysis data, and criticism by writer and price. This paper has established an information system plan for the establishment of an online supply system for art transaction information, providing auction transaction information for art market, providing report and news for art market, providing public relations platform, and providing art market analysis service and membership relationship management service. To this end, the future model was established through environmental analysis and focus analysis of the art market, and strategic tasks and implementation plans were established accordingly.

• Korean Journal of Human Ecology
• /
• v.16 no.6
• /
• pp.1069-1082
• /
• 2007

The purpose of this study is to examine how integrative art therapy affected the interaction of children with developmental disorder with their mothers from the viewpoint of object-relation theory that accentuated mother role for the promotion of mother-child interaction, and based on earlier studies on mother-child interaction and the interaction of children with developmental disorder with their mothers. The subjects in this study are five selected children and their mothers who used B and G social welfare agencies in Gyeonggi province. They are at the age of five and six in Western age, and have difficulties interacting with their parents. When a social maturity test is conducted, their social age ranged from 2.1 to 3.9, and as Portage Test is implemented, their developmental levels of sociability, cognition and language were identical to those of younger children who were at the age of one to 3.5. The major findings of the study are as follows. First, the children who suffered from developmental disorder and participated in this study showed a positive change in their interaction with their mothers. Second, as for connections between each session and mother-child interaction, most of them came to interact with their mothers better as the program came to an end.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.15 no.2
• /
• pp.51-60
• /
• 2020

Optical character recognition (OCR) has been studied for decades because it is very useful in a variety of places. Nowadays, OCR's performance has improved significantly due to outstanding deep learning technology. Thus, there is an increasing demand for commercial-grade but affordable OCR systems. We have developed a low-cost, high-performance OCR system for the industry with the cheapest embedded developer kit that supports GPU acceleration. To achieve high accuracy for industrial use on limited computing resources, we chose a state-of-the-art text recognition algorithm that uses an end-to-end deep learning network as a baseline model. The model was then improved by replacing the feature extraction network with the best one suited to our conditions. Among the various candidate networks, EfficientNet-B3 has shown the best performance: excellent recognition accuracy with relatively low memory consumption. Besides, we have optimized the model written in TensorFlow's Python API using TensorFlow-TensorRT integration and TensorFlow's C++ API, respectively.