Time identification of design knowledge push based on cognitive load measurement. (October 2022)

• Record Type: Journal Article
• Authors: Nie, Yafei; Tong, Shurong; Li, Jing; Zhang, Yicha; Zheng, Chen; Fan, Bin
• Is Part Of: Advanced engineering informatics. Volume 54(2022)
• Publication Date: 2022-10
• Subjects: Product design -- Knowledge push -- Cognitive load measurement -- Designer's behaviors -- Behavioral measurement; Computer-aided engineering -- Periodicals; Engineering -- Data processing -- Periodicals; 620.00285
• DOI: 10.1016/j.aei.2022.101783
• Languages: English
• ISSNs: 1474-0346

Abstract

Highlights: Current knowledge acquisition approaches for product design have been reviewed. Behavioral indicators related to changes in cognitive load are identified. The efficacy of inferring the cognitive load based on behavioral indicators are validated through behavioral observations. A method based on cognitive load measurement to identify the suitable time for the design knowledge push is proposed. Abstract: The reuse of multidisciplinary design knowledge is pivotal in product development because of the increasingly fierce market competition. It can assist designers, particularly those who lack sufficient experience, in making correct decisions and achieving rapid design. Traditionally, designers primarily acquire design knowledge through information retrieval, which is typically time-consuming and inefficient. A solution that is widely considered to overcome the deficiencies of traditional knowledge retrieval approaches and actively provide designers with necessary knowledge is knowledge push. However, achieving the timely push of required knowledge to designers during the design process remains a challenging task. Accordingly, this paper presents a time identification method based on cognitive load measurement to identify the suitable time for design knowledge push. First, behavioral indicators related to the changes in cognitive load are identified by investigating the influence of the load on three types of behaviors: mouse dynamics, keystroke dynamics, and emotional states. Second, the possibility and efficacy of inferring the cognitive load by simultaneously and unobtrusively tracking the three aforementioned behaviors are considered through behavioral observations. Finally, predicting the knowledge push time based on the cognitive load using classification algorithms is investigated. The experimental results indicate that the accuracy of the proposed method in inferring the cognitive load is 55%, and that of push time is 83%.