Bibliographic Details
| Title: |
Behavior-Based Design Fixation Automated Detection for Novice Designers to Facilitate Creative Design Processes. |
| Authors: |
Jia, Miao1 jiamiao@sjtu.edu.cn, Zhao, Qianyou1 1025034345@sjtu.edu.cn, Jia, Qinghan2 213203176@seu.edu.cn, Chen, Bin1 cb5183298@sjtu.edu.cn, Hu, Jie3 hujie@sjtu.edu.cn, Qi, Jin1 jinhuaqj@sjtu.edu.cn |
| Source: |
Journal of Mechanical Design. Mar2026, Vol. 148 Issue 3, p1-12. 12p. |
| Subjects: |
Behavioral assessment, Design students, Cognitive bias, Novelty (Perception), Detection algorithms, Conceptual design, Engineering design |
| Abstract: |
Design fixation usually leads designers to unconsciously copy features of previous solutions directly into later solutions. This limits the innovation of the solution and leads to low-quality design results. Currently, fixation evaluation methods mainly rely on manual evaluation, which is unable to remind designers of fixation occurrences in a timely manner during the design process. To address the aforementioned issues, this study proposes a framework for a behavioral fixation automatic identification system (BF-AIS). This system consists of two modules: fixation identification and fixation judgment. Additionally, we established mathematical models to calculate the behavior-fixation mapping relationship for the first time. Finally, an experimental evaluation involving 30 industrial design students was conducted. The results showed that the whole level of novice designers' fixation reduced by 54.4% and the quality of the solutions increased by 39.9% after using the system. After the fixation reminder was issued, the probability of the next solution continuing to solve the fixation was reduced by 93%. The design fixation computational framework proposed in this study achieves the transformation of design fixation judgment from traditional manual evaluation to automatic identification, which helps novice designers generate creative design results. [ABSTRACT FROM AUTHOR] |
|
Copyright of Journal of Mechanical Design is the property of American Society of Mechanical Engineers and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) |
| Database: |
Engineering Source |