Title | ||
---|---|---|
Eliciting design knowledge from affective responses using rough sets and Kansei engineering system. |
Abstract | ||
---|---|---|
In the last 20 years, the Kansei engineering system (KES) has employed a variety of mathematical models to overcome design problems in consumer products. However, the increasing globalization of consumer markets has made the acquisition of market knowledge more competitive than ever; therefore, a strong focus has recently been placed on developing the means to capture consumer affective responses and obtain comprehensive data related to preferences in product exterior features. Rough set theory (RST) is a rule-based knowledge acquisition method capable of targeting imprecise, non-linear human perceptions. Surprisingly, little research has been conducted into the development of KES combined with RST. Therefore, this study used a systemic approach to perform a visual design of a toothbrush by combining the Kansei engineering and RST for exploring the relationship between form and color during a product evaluation. We also provide a point-by-point comparison of KES with RST to provide a reference for the merging of these two techniques. These findings will be of considerable interest to marketing researchers, artists, product designers, and color scientists as well as manufacturers and research centers. |
Year | DOI | Venue |
---|---|---|
2016 | 10.1007/s12652-015-0307-6 | Journal of Ambient Intelligence and Humanized Computing |
Keywords | Field | DocType |
Kansei engineering system, Rough sets, Affective responses, Knowledge acquisition, Decision rules | Decision rule,Data mining,Communication design,Design knowledge,Computer science,Kansei engineering,Rough set,Affect (psychology),Perception,Knowledge acquisition | Journal |
Volume | Issue | ISSN |
7 | 1 | 1868-5145 |
Citations | PageRank | References |
4 | 0.40 | 9 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Meng-Dar Shieh | 1 | 107 | 9.82 |
Yu-En Yeh | 2 | 10 | 0.95 |
Chih-Lung Huang | 3 | 4 | 0.40 |