• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2022년도 춘계학술대회
• /
• pp.2-5
• /
• 2022

딥러닝의 등장과 ICT(Information and Communication Technology)의 급속한 발전으로 정치, 경제, 문화 등 사회의 다양한 분야에서 인공지능을 활용한 연구가 활발히 진행되고 있다. 딥러닝 기반 인공지능 기술은 자연어 처리, 영상 처리, 음성 처리, 추천 시스템 등 다양한 영역으로 세분화된다. 특히, 산업이 고도화됨에 따라 시장 동향 및 개인의 특성을 분석하여 소비자에게 추천하는 추천 시스템의 필요성이 점점 더 요구되고 있다. 이러한 기술 발전에 발맞추어, 본 논문에서는 딥러닝 기반 '언어처리지능' 과 '영상처리지능'의 기술개발을 통해 정형 또는 비정형 텍스트 및 이미지 빅데이터로부터 속성 정보를 추출 추출하고, 분류하여 패션시장의 트랜드나 신규소재 등을 분석하고 소비자의 취향 분석을 통하여 '시장-소비자' 인사이트를 발굴하여, 스타일 추천, 가상 피팅, 및 디자인지원 등이 가능한 인공지능 기반 '맞춤형 패션 어드바이저' 서비스 통합 시스템을 제안한다.

• 한국의류산업학회지
• /
• 제25권1호
• /
• pp.11-23
• /
• 2023

With the proliferation of the "Untact" culture (non-face-to-face society), advanced technologies have accelerated the cashierless systems in the retail context. Cashierless fashion stores are expected to grow rapidly in the same way automated convenience stores grew in popularity. Applying the extended technology acceptance theory, this study aims to investigate how the attributes of cashierless fashion store influence consumers' acceptance of it and to examine how consumer's technology readiness moderates the model. Two online surveys-preliminary and secondary-were conducted to collect data from consumers in their 20s and 30s who had experienced cashierless stores over the past year. To analyze a total of 423 responses, this study conducted a confirmatory factor analysis, a multi-group factor analysis, a multi-group structure equation modeling, and a descriptive analysis. The results demonstrate that convenience, trustworthiness, and price had a positive impact on perceived ease of use, while service quality had a negative one. Enjoyment, convenience, trustworthiness, and price positively influenced perceived usefulness. Both perceived ease of use and usefulness increased the intention to use. Furthermore, the multi-group comparison confirmed that the positive dimensions of consumer's technology readiness played a moderating role in the model. This study provides a research foundation for consumer acceptance of technologically advanced stores and offers practical implications to companies planning cashierless fashion stores.

• 한국조경학회지
• /
• 제28권5호
• /
• pp.58-67
• /
• 2000

This study is mainly focus on the satisfaction degree of programs which were been held in city park. The case study of this study is Tokyo metropolitan city park which planed programs and have managed them for approximately 20 years. For the purpose, this study used the questionnaire about the satisfaction degree of programs in 2 Tokyo metropolitan city parks which are held nature observation programs, after analysis of programs of city parks. This study used analysis method of cross-tab, factor analysis and multi-regression. The result are as follows: 1. As the result of factor analysis, 6 factors which are determined the satisfaction degree of programs are found. Also as the regression result between satisfaction degree and 6 factor, the satisfaction degree is positively affected by first factor which is identified program contents and forth factor which is identified marketing part of program. 2. On the organization of managing program, the sponsorship privately-managed citizen group is more favorable than the sponsorship by volunteer. 3. In the participant attribute, participants who are older than 50 showed high distribution, and there is no difference between sex.

• 한국IT서비스학회지
• /
• 제19권2호
• /
• pp.93-107
• /
• 2020

Recently, artificial intelligence (AI) technologies has been widely used in various fields such as finance, and distribution. Accordingly, Korea has also announced its AI R&D strategy for the realization of i-Korea 4.0 in May 2018. However, Korea's AI technology is inferior to major competitors such as the US, Canada, and Japan Therefore, in order to cope with the 4th industrial revolution, it is necessary to allocate AI R&D budgets efficiently through selection and concentration so as to gain competitive advantage under a limited budget. In this study, the importance of each AI technology was evaluated in multi-dimensional way through the questionnaire of expert group using the evaluation index derived from the literature review From the results of this study, we draw the following implication. In order to successfully establish the AI technology development strategies, it is necessary to prioritize the cognitive computing technology that has great market growth potential, ripple effect of technology development, and the urgency of technology development according to the principle of selection and concentration. To this end, it is necessary to find creative ideas, manage assessments, converge multidisciplinary systems and strengthen core competencies. In addition, since AI technology has a large impact on socioeconomic development, it is necessary to comprehensively grasp and manage scientific and technological regulations in order to systematically promote AI technology development.

• Computers and Concrete
• /
• 제32권1호
• /
• pp.87-97
• /
• 2023

The bending of a porous FG plate is discussed in this study using a novel higher quasi-3D hyperbolic shear deformation theory with four unknowns. The proposed theory takes into consideration the normal and transverse shear deformation effect and ensures the parabolic distribution of the transverse stresses through the thickness direction with zero-traction at the top and the bottom surfaces of the structure. Innovative porous functionally graded materials (FGM) have through-thickness porosity as a unique attribute that gradually varies with their qualities. An analytical solution of the static response of the perfect and imperfect FG plate was derived based on the virtual work principle and solved using Navier's procedure. The validity and the efficiency of the current model is confirmed by comparing the results with those obtained by others solutions. The comparisons showed that the present model is very efficient and simple in terms of computation time and exactness. The impact of the porosity parameter, aspect ratio, and thickness ratio on the bending of porous FG plate is shown through a discussion of several numerical results.

• 대한인간공학회지
• /
• 제17권1호
• /
• pp.37-46
• /
• 1998

A human sensibility ergonomics design supporting system was applied to the product development for the customer's satisfaction based on ergonomics technology. The system is composed of three major subsystems such as customer's sensibility analysis, inference mechanism, and presentation technology. The main approaches of the system are to analyze customer's sensibilities and to translate them into product design elements. The purpose of this paper is to develop a design supporting system in which the relationship between customer's sensibility and product design elements is reasoned by a MADM(Multi-Attribute Decision Making) fuzzy model. In this model, three variables such as multiple correlation coefficients, partial correlation coefficients, and category scores were used in reasoning process. The weighted value of the words were also considered in fuzzy decision process. As a case study, the design supporting system with the MADM fuzzy model was applied to the personnel computer design.

• 한국경영과학회:학술대회논문집
• /
• 한국경영과학회/대한산업공학회 2003년도 춘계공동학술대회
• /
• pp.923-930
• /
• 2003

최근의 정보기술의 급속한 발전과 더불어 대형사업의 성공 및 실패할 확률을 고려한 프로젝트 위험분석 연구가 널리 연구되고 있다. 특히 정보시스템을 기반으로 발전되고 있는 SCM(Supply Chain Management)의 구축사업은 복잡하고 대형프로젝트들로서 계획 초기부터 운영단계에 이르기까지 사업의 성공 및 실패할 확률을 예측함은 매우 중요하다. 본 연구에서는 이러한 SCM구축사업의 위험분석을 위하여 다 속성(Multi-Attribute)구조를 가지는 분석 방법과, 구축사업의 비용, 기간 및 고객 서비스능력 등을 고려한 위험 분석모델을 개발하였으며, 두 가지 방법을 사용하였다. : 1) AHP 방법을 이용한 가중치 방법, 2) SCM 네트웍을 구축하고 방법을 사용하였다. 또한 이를 위한 전산프로그램을 개발하고 실례를 들고 그 결과를 보였다.

• 산업경영시스템학회지
• /
• 제19권38호
• /
• pp.51-60
• /
• 1996

There is a general challenge offered to the field of engineering economics by the introduction of advanced technologies. A survey of the existing literature on evaluation of advanced information and manufacturing system indicate that the traditional approaches are inadequate for economic evaluation techniques used in its appraisal, difficulty in evaluating the potential benefits and criteria used to assess management performance. In this paper, an attempt has been made to overcome the above deficiencies by presenting an approach to account for the justification and selection of the Local Area Network(LAN) architectures. This is based on the Analytic Hierarchy Process(AHP) and is capable of taking into account many intangible factors as well. The usefulness of the proposed approach is demonstrated through a case situation and sensitivity analysis. Finally, some research directions for future work are identified.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송공학회 2009년도 IWAIT
• /
• pp.703-708
• /
• 2009

The present paper describes the application of an improved impression transfer vector method (Sakurai et al., 2007) to transform the three basic dimensions (Evaluation, Activity, and Potency) of higher-order impression. First, a set of shapes and surface textures of faces was represented by multi-dimensional vectors. Second, the variation among faces was coded in reduced parameters derived by applying principal component analysis. Third, a facial attribute along a given impression dimension was analyzed to select discriminative parameters from among principal components with higher sensitivity to impressions, and obtain an impression transfer vector. Finally, the parametric coordinates were changed by adding or subtracting the impression transfer vector and the image was manipulated so that its facial appearance clearly exhibits the transformed impression. A psychological rating experiment confirmed that the impression transfer vector modulated three dimensions of higher-order impression. We discussed the versatility of the impression transfer vector method.

• 한국산학기술학회논문지
• /
• 제5권1호
• /
• pp.38-43
• /
• 2004

We designed and implemented a medical image query system, including a relational database and DBMS (database management system), which can visualize image data and can achieve spatial, attribute, and mixed queries. Image data used in querying can be visualized in slice, MPR(multi-planner reformat), volume rendering, and overlapping on the query system. To reduce spatial cost and processing time in the system. brain images are spatially clustered, by an adaptive Hilbert curve filling, encoded, and stored to its database without loss for spatial query. Because the query is often applied to small image regions of interest(ROI's), the technique provides higher compression rate and less processing time in the cases.