• Annual Conference of KIPS
• /
• 2020.05a
• /
• pp.530-531
• /
• 2020

최근 인공지능을 활용하여 예술 작품에 몰입할 수 있도록 무대 효과를 디자인하는 연구가 진행되고 있다. 무대 효과 중에서 무대 배경은 공연의 분위기를 형성한다. 춤의 장르별로 무대 배경에 사용되는 이미지를 생성하기 위해 소셜 미디어 기반 무대 배경 생성 시스템이 있다. 하지만 같은 장르 춤은 동일한 무대 배경 이미지가 제공되는 문제가 있다. 같은 장르의 춤이지만 노래의 분위기를 반영하여 차별된 무대 배경 이미지를 제공하는 것이 필요하다. 본 논문은 노래 가사의 감정을 활용하여 Generative Adversarial Network(GAN)을 통해 각 노래의 분위기를 고려한 무대 배경 이미지를 생성하는 방법을 제안한다. GAN은 노래에 포함된 단락별 감정 단어를 추출하여 스타일을 생성하도록 학습된다. 학습된 GAN은 노래 가사에 포함된 감정 단어를 활용하여 곡의 분위기를 반영한 무대 배경 이미지를 생성한다. 노래 가사를 고려하여 무대 배경 이미지를 생성함으로써 곡의 분위기가 고려된 무대 배경 이미지 생성이 가능하다.

• Journal of the Semiconductor & Display Technology
• /
• v.22 no.2
• /
• pp.128-132
• /
• 2023

Recently, with the development of deep learning technology, research on pedestrian attribute recognition technology using deep neural networks has been actively conducted. Existing pedestrian attribute recognition techniques can be obtained in such a way as global-based, regional-area-based, visual attention-based, sequential prediction-based, and newly designed loss function-based, depending on how pedestrian attributes are detected. It is known that the performance of these pedestrian attribute recognition technologies varies greatly depending on the type of backbone network that constitutes the deep neural networks model. Therefore, in this paper, several backbone networks are applied to the baseline pedestrian attribute recognition model and the performance changes of the model are analyzed. In this paper, the analysis is conducted using Resnet34, Resnet50, Resnet101, Swin-tiny, and Swinv2-tiny, which are representative backbone networks used in the fields of image classification, object detection, etc. Furthermore, this paper analyzes the change in time complexity when inferencing each backbone network using a CPU and a GPU.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2022.07a
• /
• pp.697-699
• /
• 2022

Based on the integrated analysis of the existing literature, this study combined with S-O-R model to explore the impact of e-commerce live broadcast characteristics on consumers' impulse purchase intention. Among them, interactive, entertaining, economical and visual features are selected as the features of e-commerce live broadcast; Select pleasure and arousal to measure consumer sentiment, and build a theoretical model among e-commerce live broadcast features, consumer sentiment and consumers' impulsive purchase intention to specifically explore the impact of each feature on emotion and the further impact of emotion on impulsive purchase intention.

• Annual Conference of KIPS
• /
• 2022.11a
• /
• pp.452-454
• /
• 2022

최근 기술의 발전에 따라 다양한 IT 장비에서 사용자 인증을 위해 다양한 방식의 생체인증을 사용하고 있다. 일반적인 비밀번호를 통한 인증은 비밀번호와 입력 데이터가 완전히 동일해야만 인증을 통과하는 반면, 생체인증의 경우 인증을 위해 등록되어있는 데이터와 입력 데이터가 얼마나 유사한지를 통해 인증이 이루어져 데이터가 비슷하다면 인증이 통과되는 방식이라는 문제점이 있다. 본 논문에서는 인증 시간, 위치, 방식 등과 같은 사용자의 인증 패턴을 분석하여 점수를 책정하고 현재 인증자가 기존의 인증자와 동일한지에 대한 질문을 기존의 생체인증 방식에 더하는 방식을 제안한다.

• Advances in materials Research
• /
• v.13 no.3
• /
• pp.203-210
• /
• 2024

Science mapping is a visual representation of the structure and dynamics of scholarly knowledge. Gas adsorption on catalyst supports is a crucial process in many catalytic reactions. The R package "Bibliometrix" and VosViewer software were employed for science mapping analysis. The results show that the upward trend but fluctuates from year to year for both annual scientific production and average article citations per year. Co-occurrence of the keywords were used to identify the primary fields of study and to map the existing state of research. Trending topics reveal some interesting features that support the growth of research in this field and are associated with emerging disciplines or areas of study that have not been extensively explored.

• International Journal of Internet, Broadcasting and Communication
• /
• v.16 no.3
• /
• pp.113-120
• /
• 2024

Recently, case presentations using AI functions such as ChatGPT are increasing in many industrial fields. As AI-based results emerge even in the areas of images and videos, traditional animation production tools are in need of significant changes. Unreal Engine is the tool that adapts most quickly to these changes, proposing a new animation production workflow by integrating tools such as Metahuman and Marvelous Designer. Working with realistic metahumans allows for the production of realistic and natural movements, such as those captured through motion capture data. Implementing this approach presents many challenges for production tools that adhere to traditional methods. In this study, we investigated the differences between the cell animation workflow and the computer graphics animation production workflow. We compared and analyzed whether these differences could be reduced by creating sample movements using character rigs in Maya and Cascadeur tools. Our results showed that a similar cell animation workflow could be constructed using the Cascadeur tool. To improve the accuracy of our conclusions, we created large, action-packed short animations to demonstrate and validate our findings.

• Advances in materials Research
• /
• v.13 no.4
• /
• pp.285-297
• /
• 2024

The theory of nonlinear elastic wave propagation is important in multiple scientific and engineering fields. In this study, we present a comprehensive examination of nonlinear elastic wave profiles through a contemporary approach of successive approximation. This research is related to nonlinear elastic wave models along different types of nonlinearities. Murnaghan potential is used due to the assumption of the hyper-elastic materials. We explore the complication of the governing equations and go through the behaviors of nonlinear waves in one dimension. The comparative aspect of our study is a distinctive feature, as we evaluate and contrast the results obtained using successive approximation along different nonlinearities. Additionally, we present graphical representations of our findings, enhancing the visual comprehension of the wave profiles and their evolution. This study contributes to the nonlinear elastic wave analysis and comparison.

• International conference on construction engineering and project management
• /
• 2024.07a
• /
• pp.167-177
• /
• 2024

Given increasing concerns regarding environmental issues, environmentally responsible behavior during the construction of cross-sea bridge projects becomes critical. However, a systematic investigation of the topic remains absent. To bridge the knowledge gap, this study first defines environmentally responsible behavior from four perspectives: purposes, means, contents and influencing factors. Then, the study uses a grounded theory approach to code and analyze 101 documentations retrieved from 30 cross-sea bridge projects carried out by Chinese construction companies worldwide. Results show that environmentally responsible behaviors in cross-sea bridge projects are highly influenced by four factors, namely government policies, public opinions, goals of the projects, and construction companies'philosophy of environmental protection. Results also indicate that Chinese construction companies have used managerial, technical, and ecological means to ensure that the goals of environmentally responsible behaviors, namely minimization of damage to marine ecology; prevention of air, noise and visual pollution; and reduction of resource consumptions, are achieved. Lastly, suggestions for promoting and governing environmentally responsible behavior are proposed.

• Journal of Mechanical Science and Technology
• /
• v.20 no.1
• /
• pp.29-41
• /
• 2006

Nowadays, with the advancement of computers, computer simulation linked with VR (Virtual Reality) technology has become a useful method for designing the automotive driving system. In this paper, the VR simulation system was developed to investigate the driving performances of the ASV (Advanced Safety Vehicle) equipped with an ACC (Adaptive Cruise Control) system. For this purpose, VR environment which generates visual and sound information of the vehicle, road, facilities, and terrain was organized for the realistic driving situation. Mathematical models of vehicle dynamic analysis, which includes the ACC algorithm, have been constructed for computer simulation. The ACC algorithm modulates the throttle and the brake functions of vehicles to regulate their speeds so that the vehicles can keep proper spacing. Also, the real-time simulation algorithm synchronizes vehicle dynamics simulation with VR rendering. With the developed VR simulation system, several scenarios are applied to evaluate the adaptive cruise controlled vehicle for various driving situations.

• Journal of muscle and joint health
• /
• v.22 no.2
• /
• pp.67-77
• /
• 2015

Purpose: This study was a qualitative research using focus group interviews to collect data on the health care providers' perceptions of physical function in older adults with arthroplasty from hip fracture. Methods: A total of 12 subjects participated in this study. In order to conduct focus group interviews, structured manuscript, field notes, visual recording, and debriefing notes were referred and thematic analysis was used in analysis phase. Results: The six themes were raised: 'burdensome client', 'health care providers' perception of functional decline in older adults after surgery', 'health care providers' perception of caregiver', 'medical environment perceived as affecting physical function', 'crucial components perceived as encouraging functional restoration', and 'difficulty of pain management' with 18 subthemes. Conclusion: Healthcare providers perceived functional decline of elderly after arthroplasty and identified points facilitating or disturbing physical function Moreover, various perspectives on pain management related to physical function were represented.