Discovery of automotive design paradigm using relevance feedback

• Published in: Personal and ubiquitous computing Vol. 18; no. 6; pp. 1363 - 1372
• Main Authors: Jung, Hoill, Chung, Kyung-Yong
• Format: Journal Article
• Language: English
• Published: London Springer London 01-08-2014; Springer Nature B.V
• Subjects: Automobiles; Automotive components; Automotive engineering; Automotive industry; Computer Science; Customer feedback; Design engineering; Feedback; Filtering; Filtration; Mobile Computing; Original Article; Personal Computing; Sensitivity; User Interfaces and Human Computer Interaction; Relevance feedback; Sensibility analysis; Ergonomics; Recommendation; Automotive design
• ISSN: 1617-4909; 1617-4917
• DOI: 10.1007/s00779-013-0738-z

According to the development of convergence technology and diversification of lifestyle, the importance of automotive design about sensibility products is rapidly increasing. According to the technical development, product performance and reliability of more than certain standards are recognized as basal conditions of market entry. And design and usability of products and subjective satisfaction are being magnified as the success factors of products. As functional performance including maximum speed, horsepower, and mileage reaches the satisfactory level in the automobile industry, consumers think the emotional aspects of the exterior and interior decor of automobiles as important. An analysis of customers’ sensibility and preferences is an important business strategy in the automobile industry that is increasingly becoming more customer oriented. In this paper, we proposed the discovery of automotive design paradigm using the relevance feedback. The proposed method applies a method that supports automotive design using the image-based collaborative filtering utilizing sensibility as a starting point in the development process. Although a collaborative filtering process can well predict the users’ interests and preferences, it cannot efficiently analyze design information while considering the contents of specific contents. The process extracts features from the image data that the users are interested to mitigate a problem, which is regarded as an undulated analysis, and then recommends an automotive design by combining the image filtering and collaborative filtering that use the static relationship between the users’ preference and the image color information. The proposed automotive design paradigm prediction system provides a recommendation by the image-based collaborative filtering. Paradigm recommendation according to sensibility and tendency is possible by applying the relevance feedback to react the paradigm which changes according to various lifestyles. Ultimately, this paper suggests empirical applications to verify the adequacy and validity of this system.