• 복식
• /
• 제58권4호
• /
• pp.113-127
• /
• 2008

Artificial lights have effected the changes of art and fashion concepts as well as human life since the invention of electric light bulb in late 19th century. Artist and designer have had more interested in these artificial lights as the development of digital technology and the change of millennium and they have tried to apply the lights into their works. The purpose of this study is to analyze the aesthetic characteristics of contemporary fashion design using artificial light as a medium. Artificial light for fashion design means the light using luminescent material like phosphorescent and fluorescent materials or in combination with electroluminescent digital technology or the light that can be perceived as images when light projects from media using a light projector or other digital equipment. Fashion design using this light type can change colors or form temporarily and it can playa role as a gadget for hm or as equipment to provide information much as a computer monitor does. And designer can create virtual patterns on the surface of clothes, or virtual fashion like a 3-dimensional holography in empty space. In these fashion designs, the virtual image of light is substituted for physical formative elements in fashion, and the viewer can experience an ambiguity between reality and virtuality. The results of the study were as follow; The formative characteristics of those fashion designs were identified as visibility, indeterminacy, integration and virtuality. And they reflected the internal meanings; the persue of protection and safety, the search for experiment and innovation, the will for interaction and communication and the desire for the deviation and fun.

• 한국콘텐츠학회논문지
• /
• 제18권5호
• /
• pp.311-318
• /
• 2018

본 논문에서는 대화형 인공지능 인터랙티브 아트인 "진화하는 신, 가이아" 작품을 중심으로 예술 의미적인 배경과 작품이 구현된 기술적 구조에 대해 제시한다. 최근 여러 분야에서 인공지능의 기술을 사용하면서 예술 분야에도 이러한 시도가 접목되고 있다. 또한 과학의 발달로 생체모방 기술이나 인공생명 기술이 발달하면서 기계와 인간의 구분이 모호해지고 있다. 본 논문에서는 이러한 기계 생명의 은유를 담고 있는 예술 작품 사례를 제시하고, 본 작품에서 차별적으로 구현된 대화 시스템에 대해 상세히 부각한다. 본 작품에서는 로봇이 관객과의 자연스러운 소통을 위해 관객을 인식하여 바라보고 눈을 맞추며, 관객의 음성을 직접 인식하고 이에 따른 적절한 응답을 음성 합성으로 출력한다. 본 작품의 대화 시스템은 작품 내에 내장된 안드로이드 클라이언트와 질문-대답 사전을 내장한 서버로 구성된 질의응답시스템으로 구현되었다. 본 작품은 이러한 인터랙션을 통해 넓은 의미에서의 생명에 대한 의미를 논하며 관객과의 공감을 이끌어낸다. 본 논문에서는 작품의 기계적 구조와 대화 시스템 등의 제작 방법 및 관객 반응을 살펴봄으로써 인공지능 예술 작품의 제작 및 전시 기획에 기여하고자 한다.

• 문화기술의 융합
• /
• 제5권2호
• /
• pp.177-182
• /
• 2019

기술의 발전으로 인공지능은 계속해서 그 모습을 달리하며 금융, 제조, 의료, 서비스, 예술과 같은 다양한 산업 분야에 새롭게 적용되고 있다. 항상 발전하는 분야인 만큼 인공지능이 현대의 인간사회에 어떠한 변화를 가져오고 있는지 알 필요가 있다. 본 논문에서는 인공지능의 개념과 인공지능 기술이 현대의 산업분야에 구현된 방식에 대한 분석을 통해 사회에 미치는 긍정적인 영향과 부정적인 영향을 연구하였다. 이러한 연구를 통해 인공지능이 우리의 삶에 얼마나 가까이 다가왔는지를 알고 이에 대응하기 위한 초석을 마련하고자 한다.

• 한국의상디자인학회지
• /
• 제4권1호
• /
• pp.173-183
• /
• 2002

The orchid has a very elegant color and various forms in the nature or the ground for human life and the mother of life, The purpose of this study is to express some creative formative art by using the orchid as motive, and thereby, suggest the possibility of an artistic modern costume design by reviewing the texture of the materials. The results of this study can be summarized as follows; First, it was confirmed through this study that the orchid with diverse forms and colors can be used as design motive in almost infinitely diverse ways, and that all the artificial forms or structures contain the elements of natural beauty. Second, the luxurious and rich sense of orchid‘s color can be maximized by using the complementary contrast effect of the dyeing technique and the color gradation effect through harmony among similar colors. Third, a high value-added costume can be created to meet modern men’s aesthetic desire by using such embroidery techniques as crochet, weaving, dyeing, beads embroidery and art flower. Fourth, different effects of texture can be rendered by using different materials of various textures and characteristics. In addition, the possibility of creative expression for costume as formative art can be enhanced by expanding the expressions of the materials.

• 한국정보과학회:학술대회논문집
• /
• 한국정보과학회 2003년도 가을 학술발표논문집 Vol.30 No.2 (2)
• /
• pp.511-513
• /
• 2003

본 연구는 인공생명의 알고리즘을 응용해서 기존 영상작품과 엔터테인먼트(컴퓨터 게임)와는 전혀 다른 형태의 작품을 구현하는데 그 목적이 있다. 기존의 영상작품과 엔터테인먼트는 제한된 상호 작용성(기존 영상작품이나 컴퓨터 게임은 장면의 진행과 시나리오가 정해진 틀에서만 표현된다)을 갖는데, 인공생명 알고리즘을 응용한 작품은 무한한 상호 작용성(interactivity)을 표현할 수 있다. 본 연구는 인공생명 알고리즘 L-system을 응용해 우리 전통미술인 사군자를 인 실리코(컴퓨터 속의 세계)에서 구현 하였다 이 사군자는 여백을 클릭할 때마다 성장과 소멸하면서 무한히 변형된 형태의 모습을 창조한다.

• 한국화예디자인학연구
• /
• 제42호
• /
• pp.23-35
• /
• 2020

스탠다드형 카네이션은 매스플라워로써 플라워디자인에 많이 이용되고 있으나 화색이 다양하지 못해 이용에 한계가 있다. 본 연구는 이용에 한계가 있는 스탠다드형 카네이션을 사용하여 최적 염색 상태의 처리 조건을 찾고 더 나아가 염색 카네이션의 화훼장식에서 활용도를 높이고자 수행하였다. 스탠다드형 카네이션 'White Liberty'를 이용하여 6가지 염료별로 4가지 화합물 처리에 따른 염색실험을 수행하였다. 실험은 염료 6가지 색[black(2012), lavender(2200), lime Green(2315), light blue(2386), christmas red(2506), yellow(2375) (Robert Koch Industries INC, USA)]과 4가지 화합물 처리(증류수, 4% 에탄올, 3% 설탕, 100mg·L^-1 구연산)를 사용하였다. 결과적으로 6가지 염료 모두 3% 설탕과 100mg·L^-1 구연산 처리가 빠른 염색과 염색정도에 우수한 경향을 나타냈다. 그러나 절화수명은 black과 lavender 염료를 제외한 나머지 염료에서 대조구(7일)와 유사한 경향을 보였다.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2022년도 춘계학술대회
• /
• pp.47-49
• /
• 2022

Robot navigation has seen a major improvement since the the rediscovery of the potential of Artificial Intelligence (AI) and the attention it has garnered in research circles. A notable achievement in the area was Deep Learning (DL) application in computer vision with outstanding daily life applications such as face-recognition, object detection, and more. However, robotics in general still depend on human inputs in certain areas such as localization, navigation, etc. In this paper, we propose a study case of robot navigation based on deep reinforcement technology. We look into the benefits of switching from traditional ROS-based navigation algorithms towards machine learning approaches and methods. We describe the state-of-the-art technology by introducing the concepts of Reinforcement Learning (RL), Deep Learning (DL) and DRL before before focusing on visual navigation based on DRL. The case study preludes further real life deployment in which mobile navigational agent learns to navigate unbeknownst areas.

• 한국조경학회지
• /
• 제34권5호
• /
• pp.1-13
• /
• 2006

The Attention Restoration Theory (ART) developed by Kaplan and Kaplan proposes that effortful directed attention required in normal life can be fatigued. Restoration can occur in a setting that has restorative qualities. The restorative quality described by the ART involves four concepts: being away, fascination extent, and compatibility. The purpose of this study was to investigate how the restorative quality of landscape influenced the preferences and satisfaction of visitors to an heritage landscape. Four kinds of heritage landscapes of Kyongju were used as environmental surrogates and 150 americans participated in the study. Hartig et al.'s Revised Perceived Restorativeness Scale (RPRS) was used as the psychological measure for the restorative quality, along with other measurement constructs such as cultural uniqueness and novelty. The results showed that RPRS was a reliable measurement tool for assessing the restorative quality of artificial landscapes. Factor analysis identified three valid factors: escape-fascination compatibility, anti-extent. Among the three factors, only two, escape-fascination and compatibility, were found to have important effects on visiting preference and satisfaction. Specifically, higher levels of preference and satisfaction were associated with higher levels of escape-fascination and compatibility. The results indicate that the restorative quality has a high possibility to be used as a frame of reference for assessing various types of landscapes, from natural to artificial. It was also proposed that restorative quality could better explain the experience of the landscape strongly related to specific purpose or motivation.

• 한국멀티미디어학회논문지
• /
• 제24권7호
• /
• pp.880-889
• /
• 2021

In everyday life, recognizing people's emotions from their frames is essential and is a popular research domain in the area of computer vision. Visual emotion has a severe class imbalance in which most of the data are distributed in specific categories. The existing methods do not consider class imbalance and used accuracy as the performance metric, which is not suitable for evaluating the performance of the imbalanced dataset. Therefore, we proposed a method for recognizing visual emotion using balanced data augmentation to address the class imbalance. The proposed method generates a balanced dataset by adopting the random over-sampling and image transformation methods. Also, the proposed method uses the Focal loss as a loss function, which can mitigate the class imbalance by down weighting the well-classified samples. EfficientNet, which is the state-of-the-art method for image classification is used to recognize visual emotion. We compare the performance of the proposed method with that of conventional methods by using a public dataset. The experimental results show that the proposed method increases the F1 score by 40% compared with the method without data augmentation, mitigating class imbalance without loss of classification accuracy.

• Journal of Information Processing Systems
• /
• 제17권6호
• /
• pp.1115-1126
• /
• 2021

Plant disease is one of the most irritating problems for agriculture growers. Thus, timely detection of plant diseases is of high importance to practical value, and corresponding measures can be taken at the early stage of plant diseases. Therefore, numerous researchers have made unremitting efforts in plant disease identification. However, this problem was not solved effectively until the development of artificial intelligence and big data technologies, especially the wide application of deep learning models in different fields. Since the symptoms of plant diseases mainly appear visually on leaves, computer vision and machine learning technologies are effective and rapid methods for identifying various kinds of plant diseases. As one of the fruits with the highest nutritional value, apple production directly affects the quality of life, and it is important to prevent disease intrusion in advance for yield and taste. In this study, an improved deep residual network is proposed for apple leaf disease identification in a novel way, a global residual connection is added to the original residual network, and the local residual connection architecture is optimized. Including that 1,977 apple leaf disease images with three categories that are collected in this study, experimental results show that the proposed method has achieved 98.74% top-1 accuracy on the test set, outperforming the existing state-of-the-art models in apple leaf disease identification tasks, and proving the effectiveness of the proposed method.