An application of fuzzy linguistic summarization and fuzzy association rule mining to Kansei Engineering: a case study on cradle design

Fierce competition in the global market forces companies to satisfy all aspects of customers' needs during the product design stage. Among the customers' needs, affective needs are difficult to satisfy since understanding the affective needs of customers is a challenging task. Therefore, Kansei Engineering (KE), which is capable of transforming the affective needs of customers into product design form elements, has been widely used in literature. In KE, there are two types of systems: Forward KE and Backward KE. In the forward KE, Kansei words are inputs of the system and product design form elements are outputs of the system, while the product design form elements are inputs and Kansei words are outputs of the system in the backward KE. In this study, fuzzy linguistic summarization is proposed to extract fuzzy rules in the form of "if-then" rules that associate customers' affective needs into product design form elements for both backward and forward KE. The brute force approach and genetic algorithm (GA) are used to obtain the most useful linguistic summaries supported by enough data, efficiently. Furthermore, fuzzy association rule mining using the Apriori algorithm is employed to compare the obtained results of fuzzy linguistic summarization. A case study is conducted on cradle design to illustrate the applicability of the proposed fuzzy linguistic summarization and the fuzzy association rule mining. Even though the brute force approach is the best option to generate linguistic summaries, it could not be efficiently used in the design of complex products since its time complexity is exponential; and therefore, GA could be used to generate linguistic summaries in an efficient way when time complexity of the approaches is compared. The results show that fuzzy linguistic summarization is an effective and powerful tool to capture the affective needs of customers.