• 한국감성과학회:학술대회논문집
• /
• 한국감성과학회 2002년도 춘계학술대회 논문집
• /
• pp.195-200
• /
• 2002

ART (Adaptive Resonance Theory [1]) neural network and its variations perform non-hierarchical clustering by unsupervised learning. We propose a scheme "arboART" for hierarchical clustering by using several ART1.5-SSS networks. It classifies multidimensional vectors as a cluster tree, and finds features of clusters. The Basic idea of arboART is to use the prototype formed in an ART network as an input to other ART network that has looser distance criteria (Ishihara, et al., [2,3]). By sending prototype vectors made by ART to one after another, many small categories are combined into larger and more generalized categories. We can draw a dendrogram using classification records of sample and categories. We have confirmed its ability using standard test data commonly used in pattern recognition community. The clustering result is better than traditional computing methods, on separation of outliers, smaller error (diameter) of clusters and causes no chaining. This methodology is applied to Kansei evaluation experiment data analysis.

• 한국감성과학회:학술대회논문집
• /
• 한국감성과학회 2000년도 춘계 학술대회 및 국제 감성공학 심포지움 논문집 Proceeding of the 2000 Spring Conference of KOSES and International Sensibility Ergonomics Symposium
• /
• pp.301-305
• /
• 2000

The present study is part of the Special Research Project for the Construction of a Kansei Sensory Evaluation Model that is currently underway at the University of Tsukuba. In this study, a robot was operated by remote control at an actual art museum as part of a preliminary experiment. The results obtained therefrom were used to consider how people might view exhibits. In a previous study, a standard lens and s wide-angle lens were used to analyze differences in sensory-based movements, while VRML was used to analyze differences in these movements between a virtual and an actual museum. In the present study, the time delay in remote operation, which is currently unavoidable, placed some restrictions on the degree of freedom with which exhibits could be viewed, but it was apparent that sensory evaluation could be possible depending on the search behavior and viewing time. Furthermore specific viewing behaviors using the robot were observed, suggesting that new Kansei sensory perceptions were derived from these behaviors.

• 한국감성과학회:학술대회논문집
• /
• 한국감성과학회 2002년도 춘계학술대회 논문집
• /
• pp.34-38
• /
• 2002

A virtual human which can evaluate Kansei such as comfort, pain, etc. when the virtual human uses some product is developed. In this paper, method of the evaluation of Kansei by the virtual human is presented. The body of our virtual human is modeled as an uniform non-linear elastic one with a skeleton. The deformation of the body on the contact with some product is simulated using a FEM analysis, and by using of the simulated results (load distribution, strain, etc.) on the contact surface the Kansei is predicted. As examples of the application, comfort of buttocks on seating and pain of arm on hanging of bag are shown. This virtual human can apply for the design of virtual products and also the simulation of medical care.

• 대한인간공학회지
• /
• 제25권2호
• /
• pp.187-196
• /
• 2006

This study aims to develop luxuriousness models based on both users' subjective feelings and objective material characteristics of automobile crash pad using Kansei engineering approach. Based on the results of literature survey and FGI, 12 Kansei variables describing look-and-feel and touch feel and crash pad design variables were extracted for systematically developing both a conceptual model of luxuriousness and a questionnaire for Kansei evaluation. A total of 41 various crash pad samples and 60 participants(customers: 30, designers: 30) were employed to evaluate the crash pad samples using the questionnaire with 9-point semantic differential scale and 100-point modified magnitude estimate scale. Based on the survey results, luxuriousness models were developed by using regression and quantification I method. In addition, they were compared and contrasted with respect to the relative importance of Kansei variables. Consequently, the developed luxurious model could suggest the preferred combination of material properties of crash pad.

• 한국감성과학회:학술대회논문집
• /
• 한국감성과학회 2000년도 춘계 학술대회 및 국제 감성공학 심포지움 논문집 Proceeding of the 2000 Spring Conference of KOSES and International Sensibility Ergonomics Symposium
• /
• pp.240-243
• /
• 2000

An apparel products retrieval system was proposed in which users can refer to products using Kansei evaluation values. The system adopts relevance feedback using history of the retrieval to learn the tendency of user evaluation. The system is based on a vector space retrieval model using products images expression as semantic scales. The system makes a query from user inputting information and retrieves closest products from the database. Revising algorithms of the difference method. linear multiple regression performed to investigate the effectiveness and criteria of the search. As a result of evaluation of the accuracy, it was found that the linear multiple regression and the neural network models are effective for the retrieval considering the individual Kansei.

• 한국감성과학회:학술대회논문집
• /
• 한국감성과학회 2011년도 춘계학술대회
• /
• pp.25-26
• /
• 2011

• 한국디자인학회:학술대회논문집
• /
• 한국디자인학회 2001년도 Bulletin of The 5th Asian Design Conference International Symposium on Design Science
• /
• pp.7.2-7
• /
• 2001

• 대한교통학회지
• /
• 제28권3호
• /
• pp.39-49
• /
• 2010

본 연구에서는 감성공학적 분석방법론을 이용하여 운전자가 감성적인 측면에서 효과적으로 반응할 수 있는 교통안전 경고정보 제공방식 도출을 위한 연구를 수행하였다. 교통안전 경고정보는 운전자에게 전방의 위험요소를 미리 알려주어 사고회피를 위한 적절한 반응을 유도하는 역할을 하며 네비게이션과 같은 차내단말기를 통해 제공될 수 있다. 경고정보는 정보 제공방식들의 조합으로 구성되며 9개 시나리오를 설정하고 두 번의 설문조사를 시행하였다. 의미미분법, 상관분석, 수량화I류 이론을 이용한 감성공학I류 분석방법을 통해 연구를 진행하였으며, 성별차이에 따른 운전자 감성특성을 분석하였다. 분석결과 성별차이에 따라 각 정보의 제공방식에 대해 운전자가 느끼는 감성정도가 전체적으로 차이가 나는 것으로 분석되었다. 제공방식의 조합은 '청각적 요소: Beep음+음성안내', '메시지창: Text+픽토그램', '배경점멸: 빨간색 점멸'이 운전자의 감성정도와 선호도가 높게 나타났다. 본 연구의 결과는 운전자의 감성특성을 고려한 효과적인 교통안전 경고정보 설계 및 제공을 위한 유용한 자료로 활용될 것으로 기대된다.

• 대한산업공학회지
• /
• 제33권4호
• /
• pp.393-401
• /
• 2007

Affective aspects of design attributes such as color, Pattern, and texture are important to the overall impression and the success of interior products. Among all the interior materials, wallpapers and flooring materials take up largest construction area and they are main components in creating affective impression for customers. This study aims to investigate the relationship between luxuriousness and related affective variables and design elements of wallpapers and flooring materials. The approach consists of 3 steps: (1) selecting related affective features and product design attributes through a literature survey, opinion of expert panel, and focus group interview, (2) conducting evaluation experiments, and (3) developing Kansei models using multivariate statistical analysis and analyzing critical attributes. Evaluation experiment was conducted using a questionnaire made up of 7-point scale and 100-point scale and 30 housewives and 20 interior designers participated in the evaluation experiment. The result of evaluation was analyzed through principal component regression and quantification I analysis. As a result of analyzing the survey data, the relationship between luxuriousness and related affective features and product design attributes was identified, moreover a optimal combination of the design component was identified. Consequently, it is expected that the results of the study would be a basis of the concept of emotion-based design by giving insights about how customers perceive the luxuriousness and suggesting the optimal combination, and providing specific quantitative design guidelines.

• 감성과학
• /
• 제12권1호
• /
• pp.77-86
• /
• 2009

자동차는 첨단공업 기술이 고도로 집적되어 있는 인간-기계 시스템(man machine system)이다. 자동차에 대한 새로운 감성요구를 실현하기 위해서는 인체와 오랜 시간 접촉해 있는 시트 표피재의 분석이 반드시 필요하다. 본 연구에서는 자동차 시트 표피재의 역학적 특성과 감성을 고려한 고급감을 예측하여 고감성 내장 표피재 개발에 기여하고자 한다. 감성용어는 Softness(유연한), Elasticity(탱글탱글한), Volume(풍성한), Stickiness (끈끈한)를 설정하였으며, 이와 대응하는 표피재의 역학적 특성 치를 측정하였다. 피혁의 특성평가에 의한 결과로 resilience, bending moment, thickness와 friction 값을 얻을 수 있었으며, 이러한 역학적 특성 치를 softness, elasticity, volume, stickiness 값으로 변화하기 위해 fuzzy logic을 사용하였다. 또한 Fuzzy logic의 결과인 Softness, Elasticity, Volume, Stickiness 값으로 피혁의 고급감을 예측하기 위한 신경망 모델(Neural network)을 구성하였다. 즉, 자동차 표피재 중 피혁의 4가지 물리량으로 인간의 감성인 표피재의 고급감을 예측하여 고감성 자동차 시트 표피재의 개발을 위한 예측 모델의 가능성을 평가하였다.