Shigekazu Ishihara

An analysis of Kansei structure on shoes using self-organizing neural networks

Kansei engineering is a technology for translating human feelings into product design. Several multivariate analyses are used for analyzing human feelings and building rules. Although these methods are reliable, they require large computing resources. It is difficult for general users to deal with many variables because of small personal computers, and the need for the user to be an expert on statistics. This paper presents an automatic semantic structure analyzer and Kansei expert systems builder using self-organizing neural networks, ART1.5-SSS and PCAnet. ART1.5-SSS is our modified version of ART1.5, a variant of the Adaptive Resonance Theory neural network. It is used as a stable non-hierarchical classifier and a feature extractor, in a small sample size condition. PCAnet performs principal component analysis based on generalized Hebbian algorithm by Sanger (1989). These networks enable quick and automatic rule building in Kansei engineering expert systems. AKSYONN4 system is the automatic builder for Kansei engineering expert systems because it uses self-organizing neural networks. The system enables ‘real-world’ applications of Kansei engineering in product development. Relevance to industry An automatic analysis of human feelings on products and automatic building of Kansei engineering expert systems can increase the prospects of applying Kansei engineering to acceptable product design. Neural networks-based analysis and automatic expert system building enable the on-site analyzing.

Averageness or symmetry: Which is more important for facial attractiveness?

Effects of averageness and symmetry on the judgment of facial attractiveness were investigated using a generalized Procrustes method and multiple regression analyses. Participants (n=114) rated attractiveness of 96 photographs of faces with neutral expressions. Through a generalized Procrustes method, the faces and their mirror-reversed versions were represented as points on a hyperplane. Both averageness and symmetry of each individual were defined as distances on the plane. A multiple regression analysis was performed to examine the effect of symmetry and averageness for each gender. For male faces, both symmetry and averageness affected attractiveness ratings positively , and there was no difference between the effects of averageness and symmetry. On the other hand, for female faces only averageness affected attractiveness, whereas symmetry did not. However, these effects were not large.

Effect of averageness and sexual dimorphism on the judgment of facial attractiveness

Effect of sexual dimorphism and averageness on the judgment of facial attractiveness was investigated. Participants (n=114) rated attractiveness of 96 facial photographs with neutral expressions. Principal component analyses were conducted on 80 facial feature points standardized via the generalized Procrustes method. Local regression analysis was used to obtain the distribution of attractiveness evaluations for the first two principal components. The distribution of facial attractiveness of each sex was approximately line-symmetrical, and each axis of the symmetry passed through average male and female faces. These results suggest that sexual dimorphism and averageness independently influence facial attractiveness.

AFFECTIVE MEANING: THE KANSEI ENGINEERING APPROACH

Publisher Summary In the beginning of the 1970s, the concept of Kansei Engineering was introduced in Japan. Kansei Engineering can be defined as a product development methodology that translates customers’ and users’ feelings, impressions, and emotions into concrete design parameters. This chapter provides a background to Kansei Engineering and examples of how it may be used. Some of the application areas that are covered are quality feeling, driving feeling of vehicles, and the subjective impression of comfort and safety. In Japanese, Kansei is the concept of sensing a situation or an artifact and building an individual emotional response. The term Kansei itself is a multifaceted expression that does not have a complete equivalent in the English language. There are many different approaches to translating the word Kansei. In the context of product development, the Kansei can be referred to as the impression somebody gets from a certain artifact, environment, or situation using all her or his senses of vision, hearing, feeling, smell, and taste, as well as her or his cognition. Kansei Engineering studies, in most cases, are performed with quantitative data and statistical tools. The basis of the method is the identification of the relationship between the affective impression of the users and the product design parameters. There is no problem in using qualitative data instead of quantitative data within the framework of Kansei Engineering. The use of Rough Set Analysis is a tool supporting such a study. The use of qualitative data enables a deeper understanding of complex relationships that form the basis of the reactions of the humans. The qualitative methods and the quantitative methods should be seen primarily as complements to one another. Many authors point to the advantages of combining a qualitative and a quantitative approach. In that way, better understanding of complex phenomena can be obtained.

Age-related decline in color perception and difficulties with daily activities–measurement, questionnaire, optical and computer-graphics simulation studies

Abstract In aging societies, the age-related decline in visual ability is a particularly important problem. To identify problems in daily living caused by this decline in visual ability, we simulated vision in the elderly using yellowed lenses. A questionnaire study was then conducted to investigate the population and age group that has visual deficits about issues identified in the optical study. Subjective responses related to yellowing in vision became prominent in people over 75 years old. A color judgment experiment was carried out using subjects aged 80 or older. Confusing color combinations are; yellow/white, blue/green, dark blue/black and purple/dark red. Based on this color confusion data, we used computer graphics to simulate vision in the elderly. Simulated views of public signs are shown. Relevance to industry This study shows what colors tend to be confused by the elderly and provides essential data for developing products for older adults. Color combinations on interfaces such as switches, indicators and displays have to be considered carefully. Optical and computer-graphics simulations of the yellowed vision of the elderly based on color tests are powerful tools for improvement through experience.

Affective design of waiting areas in primary healthcare

Purpose – This paper seeks to deal with affective design of waiting areas (servicescapes) and has twofold aims. The first, is to explore affective values for waiting areas. The second, is to identify interactions between physical design attributes and affective values.Design/methodology/approach – This study included a free association method for data collection, applying Kansei engineering methodology to extract design solutions relating to specific feelings. The study was undertaken at six primary health centres in Ostergotland County, Sweden. In total, 88 participants (60 patients and 28 staff) were interviewed.Findings – The selected waiting areas show significant differences for their perceived affective qualities. The most desired feeling for creating affective values is found to be “calm”. The core design attributes contributing to this feeling are privacy, colours, child play-areas and green plants. Good design of lighting, seating arrangements and a low sound level are also important design attributes to give a more complete design solution.Research limitations/implications – The study provides useful insights for understanding affective needs in servicescapes, and it provides design suggestions. The results have not been analysed separately for gender or different age groups.Practical implications – The paper proposes a framework model to be applied when dealing with affective values in servicescapes.Originality/value – This paper makes an original contribution to understand affective values towards the physical environment in servicescape design. It offers a methodology to study complex environments with many alternative design solutions using limited resources. Moreover, this study uses a combination of a free association method and Rough Sets theory in affective design.

arboART: ART based hierarchical clustering and its application to questionnaire data analysis

A hierarchical clustering mechanism is designed to analyze multidimensional data and feature selection based on ART-type neural networks. Prototype of clusters obtained from an ARTs top-down vectors are sent to another ART. Several ART networks that have different similarity criteria are used for cluster combination. This scheme of hierarchical clustering (arboART) enables to make a tree structure graph of classification result of samples, and find features of each cluster. arboART is utilized to automatic rule generation of Kansei engineering expert systems. Analyzing result on color evaluation experiment by arboART and comparison with conventional multivariate analysis are shown.

Multiple mechanisms in the perception of face gender: Effect of sex-irrelevant features.

Effects of sex-relevant and sex-irrelevant facial features on the evaluation of facial gender were investigated. Participants rated masculinity of 48 male facial photographs and femininity of 48 female facial photographs. Eighty feature points were measured on each of the facial photographs. Using a generalized Procrustes analysis, facial shapes were converted into multidimensional vectors, with the average face as a starting point. Each vector was decomposed into a sex-relevant subvector and a sex-irrelevant subvector which were, respectively, parallel and orthogonal to the main male-female axis. Principal components analysis (PCA) was performed on the sex-irrelevant subvectors. One principal component was negatively correlated with both perceived masculinity and femininity, and another was correlated only with femininity, though both components were orthogonal to the male-female dimension (and thus by definition sex-irrelevant). These results indicate that evaluation of facial gender depends on sex-irrelevant as well as sex-relevant facial features.

Independence of older adults in performing instrumental activities of daily living (IADLs) and the relation of this performance to visual abilities

A questionnaire study was undertaken of more than 2800 elderly people aged 60 years and over and living at home, to investigate the relationship between their performance of some instrumental activities of daily living (IADLs) and their visual abilities. The IADL measured the ability of elderly participants to pick up coins, manage monthly financial matters, use the telephone and take medication as recommended. Visual abilities were assessed by means of each subjects answers to questions relating to resolution, focus, adaptation to bright or to dim lighting, dynamic acuity, distance perception and colour vision. The types of visual functions that, together with age and gender, contribute to determining the level of independence in the performance of IADL activities were identified using logistic regression analysis. The results indicated that elderly participants who had problems with either distance perception or yellowish vision also tended to have difficulties in picking up coins, using the telephone and taking medication as recommended. In addition, problems with adaptation and dynamic acuity were associated with difficulty in managing monthly financial matters. From an analysis of all subjects, distance perception was the significant factor that determined whether an elderly subject could pick up coins or use a telephone unaided. Yellowish vision was also significantly associated with a need for assistance or with an inability to manage monthly financial matters, use the telephone or take medication as recommended.

Incorporating Markov chain modelling and QFD into Kansei engineering applied to services

Instead of usability, customers today concern themselves more on satisfying their emotions/Kansei. This paper discusses an integrative framework that incorporates the Kano model, Markov chain, and quality function deployment (QFD) into Kansei engineering (KE). Its purposes are: 1 to exhibit the relationship between service performance and Kansei 2 to enable service designers to establish the extent to which they prioritise their improvement programmes in dealing with current and future preferences. A comprehensive case study involving Indonesian, Japanese, and Singaporean tourists, was carried out. Understanding the cultural differences with respect to Kansei evaluation will yield valuable insights for international marketing strategies.