How to identify market need and how to involve it into product design are permanent issues for enterprises. Recently, market need vary, and it is necessary to respect need evaluated by human image or feeling. In an investigation of identifying need that is expressed by human image or feeling, questionnaire by means of SD(Semantic Differential)method is often used. SD method sets pairs of adjectives as evaluation words and it measures semantic of objects. However, as it is not clear which type of information should be clarified, a guideline for selection of evaluation words is not established. In this paper, information to be obtained in the investigation of such need is shown and a guideline for selection of evaluation words used in SD method is proposed. The proposed guideline makes it possible to select evaluation words systematically. Also, by clarifying the process that evaluates Kansei quality under recognition-perception model, effective information on product design in consideration of Kansei quality can be obtained.

View full abstract

To mine data set for an optimal model taking into account both linear and non-linear parts of variation of response variable, a strategy of hybrid modeling for combining CART with linear regression analysis is proposed after the features are extracted from a POS data set. To valid the strategy, the POS data set is applied, and useful results are obtained as follows.
　(1)Hybrid modeling can improve accuracy of the sole modeling of CART and/or regression model.
　(2)It can handle any case with surrogate variable instead of any predictor, which has a missing value.
　(3)Autocorrelation of residual time series and its residual mean squared error after hybrid can be improved by application of autoregressive model.

View full abstract

[in Japanese]

View full abstract