• International Journal of Computer Science & Network Security
• /
• 제22권9호
• /
• pp.343-347
• /
• 2022

To date, the use of artificial intelligence has already brought certain results in such areas of art as poetry, painting, and music. The development of AI and its application in the creative process opens up new perspectives, expanding the capabilities of authors and attracting a new audience. The purpose of the article is to analyze the essential, artistic, and technological limitations of AI art. The article discusses the methods of attracting AI to artistic practices, carried out a comparative analysis of the methods of using AI in visual art and in the process of writing music, identified typical features in the creative interaction of the author of a work of art with AI. The basic principles of working with AI have been determined based on the analysis of ways of using AI in visual art and music. The importance of neurobiology mechanisms in the course of working with AI has been determined. The authors conclude that art remains an area in which AI still cannot replace humans, but AI contributes to the further formation of methods for modifying and rethinking the data obtained into innovative art projects.

• 한국실내디자인학회:학술대회논문집
• /
• 한국실내디자인학회 2006년도 추계학술발표대회 논문집
• /
• pp.141-145
• /
• 2006

The development of information & communication technology in 21st century along with the mass media In 20th century, the influence of state-of-art culture in our society rapidly increased in these days. This state-of-art culture makes the world becomes single-channeled by network, and there is a big change not only in human life but also in concept and understand for art and space. The development of digital paradigm and media technology is exerting a strong influence on the Ubiquitous computing environment that is being drawn great interest. The ubiquitous is concerned as expansion of media art, and the interactive art which is part of media art has the similarity with the ubiquitous computing environment. In this study, the possibility of connection between the territory of ubiquitous environment which is recently focused and has strong interrelation feature, and the territory of interacting will be examined. Furthermore, possibility of new space design work through seeking the possibility of connection between two territories will be estimated.

• International Journal of Advanced Culture Technology
• /
• 제10권2호
• /
• pp.116-121
• /
• 2022

Digital technology has now pervaded and become an inseparable part of our daily life. The art museum sector is evolving into a business model that adapts to the new digital format due to the requirement for survival and development. This study examines the development state of China's art museum industry and investigates the current business model innovation trend in the art museum industry from three perspectives: reorganization and development of the art museum industry's business model theory; reconstruction of the art museum industry's display and marketing logic; and innovation of the art museum industry's operation mechanism, based on a systematic assessment of domestic and international research. This research can provide reference value for digital technology to drive the innovation of business model in art museum industry. Moreover, the study has important reference significance for the development strategy of art museum industry.

• 한국지능정보시스템학회:학술대회논문집
• /
• 한국지능정보시스템학회 2001년도 The Pacific Aisan Confrence On Intelligent Systems 2001
• /
• pp.25-29
• /
• 2001

There are so many researches about the search method for the most compatible dispatching rule to a manufacturing system state. Most of researches select the dispatching rule using simulation results. This paper touches upon two research topics: the clustering method for manufacturing system states using simulation, and the search method for the most compatible dispatching rule to a manufacturing system state. The manufacturing system state variables are given to ART II neural network as input. The ART II neural network is trained to cluster the system state. After being trained, the ART II neural network classifies any system state as one state of some clustered states. The simulation results using clustered system state information and those of various dispatching rules are compared and the most compatible dispatching rule to the system state is defined. Finally there are made two knowledge bases. The simulation experiments are given to compare the proposed methods with other scheduling methods. The result shows the superiority of the proposed knowledge base.

• Architectural research
• /
• 제7권2호
• /
• pp.69-79
• /
• 2005

There are no formal decision tools or guidelines to assist owners and contractors in choosing delivery systems and project strategies that would allow for a radical reduction in project cycle time - from the preplanning phase through project start up. Therefore, it is important to identify the state-of-practice and the state-of-art on methods of achieving radical reduction defined as a reduction of 25% or more in overall project cycle time. A comprehensive literature review, three questionnaire surveys, and the seven case studies were conducted and the data obtained from them were analyzed to establish the state-of-practice and state-of-art for project cycle time reduction techniques.

• 한국가구학회지
• /
• 제25권3호
• /
• pp.188-197
• /
• 2014

This study aimed to develop organic design and propose references on an origin and developing factors of the organic design as looking into previous researches on furniture design. Expressive features with curves observed in the furniture design have been interpreted as organic meanings, and the study also approached grounds for the organic design elements while talking about developments of new materials and digital technology. In addition, the study presented a possibility explaining that these organic design elements might have been derived and developed from Art Nouveau. State-of-the art technology of the digital era in the 21st century has been built upon more creative concepts, and as this technology gets combined with the digital technology, it is, now, changing but also improving both morphological aspects and design methodologies. In the midst of this change, when it comes to factors to develop the organic design, creation of various new materials and state-of-the art digital technology are considered to be immediate factors to changes in the design. As morphological thinking using digital media develops, geometric thinking and such form are realized which eventually would lead us to furniture design of a new concept.

• Structural Engineering and Mechanics
• /
• 제6권1호
• /
• pp.41-61
• /
• 1998

A state-of-the-art report on the new finite elements formulated by the addition of nonconforming displacement modes has been presented. The development of a series improved nonconforming finite elements for the analysis of plate and shell structures is described in the first part of this paper. These new plate and shell finite elements are established by the combined use of different improvement schemes such as; the addition of nonconforming modes, the reduced (or selective) integration, and the construction of the substitute shear strain fields. The improvement achieved may be attributable to the fact that the merits of these improvement techniques are merged into the formation of the new elements in a complementary manner. It is shown that the results obtained by the new elements give significantly improved solutions without any serious defects such as; the shear locking, spurious zero energy mode for the linear as well as nonlinear benchmark problems. Recent developments in the transition elements that have a variable number of mid-side nodes and can be effectively used in the adaptive mesh refinement are presented in the second part. Finally, the nonconforming transition flat shell elements with drilling degrees of freedom are also presented.

• Nuclear Engineering and Technology
• /
• 제53권12호
• /
• pp.4072-4079
• /
• 2021

This article presents a study on the state-of-the-art methods for automated radioactive material detection and identification, using gamma-ray spectra and modern machine learning methods. The recent developments inspired this in deep learning algorithms, and the proposed method provided better performance than the current state-of-the-art models. Machine learning models such as: fully connected, recurrent, convolutional, and gradient boosted decision trees, are applied under a wide variety of testing conditions, and their advantage and disadvantage are discussed. Furthermore, a hybrid model is developed by combining the fully-connected and convolutional neural network, which shows the best performance among the different machine learning models. These improvements are represented by the model's test performance metric (i.e., F1 score) of 93.33% with an improvement of 2%-12% than the state-of-the-art model at various conditions. The experimental results show that fusion of classical neural networks and modern deep learning architecture is a suitable choice for interpreting gamma spectra data where real-time and remote detection is necessary.

• 한국어업기술학회:학술대회논문집
• /
• 한국어업기술학회 2002년도 춘계 수산관련학회 공둥학술발표회
• /
• pp.38-42
• /
• 2002

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권11호
• /
• pp.5555-5567
• /
• 2018

State-of-art instance segmentation networks are successful at generating 2D segmentation mask for region proposals with highest classification score, yet 3D object segmentation task is limited to geocentric embedding or detector of Sliding Shapes. To this end, we propose an amodal 3D instance segmentation network called A3IS-CNN, which extends the detector of Deep Sliding Shapes to amodal 3D instance segmentation by adding a new branch of 3D ConvNet called A3IS-branch. The A3IS-branch which takes 3D amodal ROI as input and 3D semantic instances as output is a fully convolution network(FCN) sharing convolutional layers with existing 3d RPN which takes 3D scene as input and 3D amodal proposals as output. For two branches share computation with each other, our 3D instance segmentation network adds only a small overhead of 0.25 fps to Deep Sliding Shapes, trading off accurate detection and point-to-point segmentation of instances. Experiments show that our 3D instance segmentation network achieves at least 10% to 50% improvement over the state-of-art network in running time, and outperforms the state-of-art 3D detectors by at least 16.1 AP.