Search

There is limited information about the design process and outcomes of novice industrial designers when working with different levels of problem abstraction. In this paper, we propose a new way of describing the cognitive processes of problem solving based on problem decomposition strategy studies and network-based cognitive maps. An empirical study was conducted to examine the impact of problem abstraction on novice designers, and their reasoning mode was quantitatively explored. Thirty-three novice designers majoring in industrial design participated in a 40-min design exercise and verbalized their cognitive process while they were solving a given design problem. The verbal protocols from the experiment were first segmented, then encoded based on cognitive maps. By analyzing the problem-solving process using this new method, we found that designers use different reasoning modes for different levels of problem abstraction. Abstract problems helped designers to break design fixation and promote the divergence of ideas. Ideas also improved in fluency, originality and novelty so that the abstract group generated better solutions. The study contributes to an enhanced understanding of design activity.

Recent advances in Artificial Intelligence raise interest in its participation in design activity, which is commonly considered to be complex and human-dominated. In this work, we aim to examine AI...

Design is an iterative process that aims at problem-solving. While the importance of mental iteration has been identified, there are little research on how to improve mental iteration in design process. In this paper, we propose a method to augment design by AI. An experiment was conducted to study the effect of AI augment on design iteration. The results indicate AI augment could improve the designers’ performance in fluency and stylization.

Image-to-Image translation was proposed as a general form of many image learning problems. While generative adversarial networks were successfully applied on many image-to-image translations, many models were limited to specific translation tasks and were difficult to satisfy practical needs. In this work, we introduce a One-to-Many conditional generative adversarial network, which could learn from heterogeneous sources of images. This is achieved by training multiple generators against a discriminator in synthesized learning way. This framework supports generative models to generate images in each source, so output images follow corresponding target patterns. Two implementations, hybrid fake and cascading learning, of the synthesized adversarial training scheme are also proposed, and experimented on two benchmark datasets, UTZap50K and MVOD5K, as well as a new high-quality dataset BehTex7K. We consider five challenging image-to-image translation tasks: edges-to-photo, edges-to-similar-photo translation on UTZap50K, cross-view translation on MVOD5K, and grey-to-color, grey-to-Oil-Paint on BehTex7K. We show that both implementations are able to faithfully translate from an image to another image in edges-to-photo, edges-to-similar-photo, grey-to-color, and grey-to-Oil-Paint translation tasks. The quality of output images in cross-view translation need to be further boosted.

Cultural products that adhere to the Doctrine of the Mean in Confucian philosophy have high commercial and cultural value. However, they are challenging to design and are seldom studied owing to th...

This study focuses on gender differences in the influence of online communication on e-commerce purchase decision strategies. From the literature, we deduce a new theoretical model based on three foundational theories and design a 2 2 mixed factorial experiment to test the influence of online communication in cases with and without online communication. This involves analyzing screen-recording data to check the effect of shopping behavior initiation, and using questionnaire research to test differences in the user experience before and after such communication. Finally, we concluded that the influence of online communication differs between men and women, and the influence is largely positive to both males and females. We build a research model to examine the moderating effect of online communication affects and associated gender differences.We argue for the positive moderating effect of online communication on consumers' e-commerce purchase behavior.Online communication process affected the shopping experience on gender lines, and shopping initiation had a positive effect for both men and women.So in subsequent practical application, we communicate by offering more online, including a means for users to guide and stimulate consumption.

Products with gender inclination are generally attractive to specific consumers. This paper explored influence of product elements on gender inclination by using watches as a case study. We adopt morphological analysis to divide the appearance of a watch into five elements with several types, and then obtained element-wise gender inclination through a questionnaire survey. Next, we adopted fuzzy analytic hierarchy process (FAHP) to quantify the relative importance of the five elements as well as their types on gender inclinations. To verify the quantitive results of FAHP, we selected several types with obvious gender inclinations to construct five virtual watches, and performed a validation questionnaire based on the virtual watches. It was found that the validation results were consistent with those of FAHP, meaning that FAHP can provide a relatively more quantitive reference for designers and manufactures to examine the gender inclination of products.