• Proceedings of the KAIS Fall Conference
• /
• 2003.11a
• /
• pp.84-87
• /
• 2003

This paper proposes the enhanced REF network, which arbitrates learning rate and momentum dynamically by using the fuzzy system, to arbitrate the connected weight effectively between the middle layer of REF network and the output layer of REF network. ART2 is applied to as the learning structure between the input layer and the middle layer and the proposed auto-turning method of arbitrating the learning rate as the method of arbitrating the connected weight between the middle layer and the output layer. The enhancement of proposed method in terms of learning speed and convergence is verified as a result of comparing it with the conventional delta-bar-delta algorithm and the REF network on the basis of the ART2 to evaluate the efficiency of learning of the proposed method.

• Journal of Digital Convergence
• /
• v.18 no.9
• /
• pp.337-342
• /
• 2020

Art work based on computer and internet media technologies such as digital art, computer art, internet art, interactive art. Through examples, we studied the interaction and communication method between the audience and the exhibition objects. It was confirmed that the new media works are expressed in a new form by fusion with various technologies of experimental propensity, and research and analysis of overseas media-related exhibition cases and interactive media use cases of works exhibited at the 'Media City Exhibition' in Korea were conducted. Was able to confirm the main characteristics of new media art. I think it will be a more meaningful study by setting specific criteria and focusing on the fields of application of new media art and comparing and analyzing the future values of the times.

• Trans-
• /
• v.13
• /
• pp.117-140
• /
• 2022

Recently, artificial intelligence technology is being used throughout the industry. Currently, Currently, AI art generators are used in the NFT industry, and works using them have been exhibited and sold. AI art generators in the art field include Gated Photos, Google Deep Dream, Sketch-RNN, and Auto Draw. AI art generators in the music field are Beat Blender, Google Doodle Bach, AIVA, Duet, and Neural Synth. The characteristics of AI art generators are as follows. First, AI art generator in the art field are being used to create new works based on existing work data. Second, it is possible to quickly and quickly derive creative results to provide ideas to creators, or to implement various creative materials. In the future, AI art generators are expected to have a great influence on content planning and production such as visual art, music composition, literature, and movie.

• The Journal of the Convergence on Culture Technology
• /
• v.10 no.3
• /
• pp.901-907
• /
• 2024

The desire to be beautiful naturally focuses on aesthetics, and the beauty industry is growing significantly accordingly. Among them, art makeup is developing in the beauty field as a creative and experimental art field that breaks away from the fixed framework centered on color and expression. Art makeup is a field that requires research on a new artistic form of art makeup that applies formative principles through design ideas based on integrated arts such as fashion, architecture, and art according to formative principles. Formative principles were classified into balance, unity, emphasis, and rhythm, and practical cases based on his applied integrated arts were divided into landscaping, architecture, flowers, painting, fashion, and interior design, and art makeup design using formative principles was analyzed. Accordingly, we aim to contribute to the development of new designs by explaining how makeup design forms that apply formative principles are being applied in the field of art makeup, exploring expansion into creative areas, and providing academic theoretical foundations and basic materials for the development of art makeup.

• Journal of the Korea Convergence Society
• /
• v.11 no.10
• /
• pp.171-179
• /
• 2020

This study was attempted to identify the media preferences and the reasons of cancer patients. The data collection was conducted on 76 people. and they are 6 men, 70 women with 38 breast cancer patients, and 38 patients with other cancers. For measuring tools, self-written questionnaires and Mandala paintings were used for single-time art therapy. The data analysis compared the results of technical statistics, independence verification and chi verification using the SPSS WIN ver.25.0 with the Mandala painting. There were no significant differences in media preference by age and duration of the disease, and there were significant differences in media preference by disease. In the Mandala painting, the characteristics of the medium and the factors of specific disease showed that there were reasons and effects of preference media choice. This study is meaningful in that it concentrated on the art therapy access and support in terms of the cancer outpatients, which have been concentrated on inpatients so that they shed light to the support and intervention needed by the outpatients, and can be used as basic data for the development of art therapy programs to help stabilize the mind of cancer patients in the future.

• Journal of information and communication convergence engineering
• /
• v.8 no.5
• /
• pp.595-601
• /
• 2010

The strategy through visual sense is one of the ways that subject builds the outside world and communicates. The visual sense seems higher level of dependence than the other senses and contributes to intercommunication. For this reason, the desire of image dates back to primitive art and visual image(visual media and visual culture) has dialectically developed in the history of mankind. Visual subject, based on perspective of Renaissance, was moved from God to human beings. Andre Bazin's 'la genese automatique' through technical art has epochally changed the paradigm of visual art and visual culture. From primitive art to photo and film, the image, based on visual sense, has reflected human wish, appealed visual desire and led to evolution of image. In the late 20 century, without dialectical evolution of technology and culture, rapidly progressive digital image has changed social and cultural implication over rational strategy of production and distribution and it strengthened authority of image through visual approach of endless desire. The goal of this study is to analyze the value change of digital image developing a new Renaissance through production, reading, communication, and implication of evolution due to digitalized image, which has evolved as object and tool of desire.

• Journal of Digital Convergence
• /
• v.17 no.11
• /
• pp.251-258
• /
• 2019

This study was aimed to evaluate the effects of art and craft activities on anxiety and stress of stroke patients. Patients diagnosed with stroke were selected according to select the study target, 9 patients with experimental group receive art and craft activities, 9 patients with control group receive traditional occupational therapy for 30 minutes per each session 3 times a week for total 8 weeks. Art and craft activities were structured through a group of occupational therapy practitioners interview. A comparison of two groups after the intervention showed that the experimental group had a more significant on the anxiety and stress(p<.05). These result demonstrate that art and craft activities decrease anxiety and stress for stroke patients, therefore is expected to be useful in clinics.

• Journal of Digital Convergence
• /
• v.13 no.2
• /
• pp.333-341
• /
• 2015

The purpose of this research is to study possibilities of animation education in art centered STEAM. We suggest not the animation education contents model of a functional skills of the past but the one for STEAM. In order to suggest the role of animation education, we should first study the convergence values of animation. And this study make a curriculum of animation for the creativity by convergence thinking. Finally, this study build the animation class model applied in STEAM by Fogarty's integrated education method. By studying, we can get the result that animation has the convergence characteristics and it has the effective role of art centered STEAM education for the convergence thinking. Also, it is expected that the results of this study will contribute to education and training of convergence of the global talent with creativity in STEAM.

• The Journal of the Convergence on Culture Technology
• /
• v.8 no.1
• /
• pp.523-529
• /
• 2022

Art sponsorship contributed to the development of culture and art by supporting art activities to be financially stable. Various problems in the non-fungible tokens (NFTs) market, such as speculative transactions, are also expected to be improved through sound art sponsorship. This study proposes methods of implementing art sponsorship using NFTs and smart contracts. First, we propose a method of posting the acknowledgement of art sponsorship using NFT metadata. Second, we propose a method to remit sponsorship funds according to the project schedule using time-locked wallets. Third, we propose a method to remit sponsorship funds when major events of the project occur or requirements are met using Event-Driven Execution. The proposed methods can be used to share the fact about art sponsorship and safely fund it. However, many decisions about art projects must be made based on information generated outside the blockchain, which can lead to Oracle problems, so further research is needed.

• Journal of Information Processing Systems
• /
• v.16 no.5
• /
• pp.1015-1033
• /
• 2020

With promising results and enormous capability, deep learning technology has attracted more and more attention to both theoretical research and applications for a variety of image processing and computer vision tasks. In this paper, we investigate 32 research contributions that apply deep learning techniques to the agriculture domain. Different types of deep neural network architectures in agriculture are surveyed and the current state-of-the-art methods are summarized. This paper ends with a discussion of the advantages and disadvantages of deep learning and future research topics. The survey shows that deep learning-based research has superior performance in terms of accuracy, which is beyond the standard machine learning techniques nowadays.