AHFE Open AccessKansei Engineering
Editors: Mitsuo Nagamachi, Shigekazu Ishihara
Topics: Kansei Engineering
Publication Date: 2024
ISBN: 978-1-964867-21-2
DOI: 10.54941/ahfe1005134
Articles
Facilitation of Kansei engineering design process with LLM multi-agent discussion
Recent advances in Large Language Models and Generative AI continue to have a positive impact on the design process and Kansei engineering.At AHFE 2023, we presented the trials of product design using Generative AI based on Kansei engineering (Ishihara, Kuo & Ishihara, AI image generation boosts Kansei engineering design process, 2023).In this study, we explored the possibilities of multi-agent discussion in the design process and Kansei engineering. GPT-4 (OpenAI) was asked to create experts and discuss the given topic from each expert's point of view. In the example below, the topic was given as "We would like to discuss the design of an innovative chair made with a 3D printer. We would like to hear opinions from as many different perspectives as possible.GPT-4 automatically creates 3 virtual experts as: a designer, an engineer, and an environmental specialist. These different experts were created without any specific direction.The following lines are the roles of the experts set up in GPT-4: Designer - Focuses the discussion from an aesthetic point of view. Emphasizes innovation and aesthetics in design. Passionate in tone and fond of creative ideas.Engineer - Focuses on practicality and technical feasibility. Discusses cost and material efficiency in detail. Analytical in tone and logical in approach.Environmentalist - Focuses on sustainability and environmental impact. Discusses the use of recyclable materials and reducing environmental impact. They are soft-spoken and have deep insight into environmental issues.Intermediate discussions are in the following lines;---Persona 1: DesignerInspired by the engineer's opinion, I'd like to think a little more about the balance between durability and design. Durability is very important because chairs are used on a daily basis, and the key to manufacturing with a 3D printer is ensuring structural strength while still maintaining an aesthetically pleasing design. This can be seen as a design challenge.Persona 3: Environmental SpecialistI agree with the designer's suggestion, but materials should be carefully chosen to minimize environmental impact. Environmentally friendly materials, such as bioplastics, can provide greater design freedom while ensuring sustainability. The energy efficiency of the 3D printer is also important.Persona 2: EngineerI agree with the points made by the environmental experts. However, when using environmentally friendly materials, one must also pay attention to the physical properties of these materials. It is important to choose materials that are sustainable while still meeting the basic performance requirements of the chair, such as strength and heat resistance.Persona 1: DesignerThe engineer's technical perspective is very important. As a designer, the challenge is how to turn these technical limitations into art. For example, if there is a limit to the strength of a material, we can incorporate that as part of the design. I think balancing the flexibility of the design with the technical requirements will be key to the success of this project.The final agenda is as follows;---Designer's PerspectiveDesign Innovation: 3D printing allows for unique shapes and patterns that were previously impossible.Aesthetics and Individuality: Aesthetically pleasing designs that match consumer tastes and contemporary interior trends are important.Appealing to consumer sensibilities: Unique and beautiful designs can serve as status symbols, making them feel worth the high price tag.Engineer's PerspectivePracticality and technical feasibility: Consider the balance between manufacturing efficiency and cost while maintaining durability and safety.Customization and Quality: Ensure long-term cost-effectiveness and satisfaction by allowing adjustments to accommodate each individual's body shape and preferences.Overcoming technical limitations: Consider the physical limitations of 3D printing technology as part of the design.Environmental ExpertiseSustainability: Consider the use of recyclable materials and the recyclability of the product.Environmental impact: Energy consumption and material choices during the manufacturing process are important.Appealing to eco-conscious consumers: Green products add value and justify a price premium.---This is a summary of the discussion on the design of 3D-printed chairs from each expert's perspective. A balance between design innovation, technical feasibility, and sustainability is important, and a product based on these factors will influence consumer purchase incentives and can be successful in the marketplace, even at a high price point.We are now trying to combine this with Generative Graphics AI to visualize ideas based on this discussion among virtual experts.
Shigekazu Ishihara, Taku Ishihara, Keiko Ishihara
Open Access
Article
Conference Proceedings
Sentiment Analysis of Self-Driving Cars Using Text Mining
This study aims to predict future changes brought about by self-driving cars and find ways to respond to user experience (UX) through sentimental analysis of consumers' perceptions of self-driving cars. In particular, this study conducted sentiment analysis through monitoring and analysis of text information using user-generated content (UGC). Through this, the plan is to identify customer needs (Voice of Customers) and use it as a basis for future autonomous vehicle interior development.
Donghwan Kim
Open Access
Article
Conference Proceedings
What Are Your Impressions? Proposal for Emotional Assessment Platform
Compelling visuals, spanning photographs, drawings, paintings, and illustrations, significantly enhance our daily encounters, conveying a wealth of information and eliciting emotions. Recognizing the impact of specific images and distinguishing them from less impactful ones proves valuable for various applications, including marketing and academic evaluations. However, evaluating these creative expressions presents inherent challenges. In our pursuit of understanding emotional responses to movie posters, we employed Russell's valence-arousal emotion model, incorporating measures of arousal and valence. Our investigation revealed that distinctive movie posters often received assessments marked by low arousal and positive valence. Expanding on these findings, we have enhanced the system to accommodate any image, incorporating administrative features tailored for experimental projects. This paper provides a concise overview of the system, emphasizing its capabilities, and explores a planned experiment use case.An overview of the system: Upon the successful login of a registered user into the system, the portal page is displayed, allowing the user to create a project. A project includes a title, description, and two measure titles, such as arousal and valence. Additionally, the project encompasses a collection of URLs corresponding to the images that need to be evaluated.Access to the evaluation pages is open to the public; therefore, there is no need to register an account to access them. The evaluation process consists of three steps: 1. Introduction, 2. Evaluation, and 3. Displaying the Evaluation Result. The introduction screen provides the project title and description to elucidate the purpose of image evaluation, accompanied by a 'Start Evaluation' button. Clicking this button directs users to the next page for the actual evaluation. On this page, six images, randomly selected from the database, are presented along with two evaluation scales ranging from -1.0 (negative value) to 1.0 (positive value). Users can assess their impressions of each image using two slider interfaces. Upon submitting the evaluation, the result page is generated, featuring a scatter plot graph that illustrates the user's decisions alongside the average scores calculated from other users for each image.Planned experiences: Conducting sensitivity evaluations for paintings involves examining people's ability to distinguish between human-created and AI-generated artworks, along with determining their preferences. The experiment utilized a set of images, comprising half human-drawn and half AI-generated, prompting participants to evaluate them based on two criteria: humanness and preference. The evaluators were unaware of the image authors. By plotting the results on two axes, we can analyze the preferred images by humans and AI and explore the discernibility of AI-created art.Similarly, a sensitivity evaluation for fashion is underway, utilizing two indices: fashionability and likability. Participants are asked to rate fashion items based on these criteria, shedding light on the styles deemed fashionable and preferred by individuals and providing insights into the variations in personal sensibilities. Additionally, collecting data on participants' age groups allows for an analysis of preferences across generations, thereby broadening the scope of the research.
Jun Iio
Open Access
Article
Conference Proceedings
Tactile Estimation of Surface Texture Based on Heightmap Image Features and Customer Attribute Information
In this study, we investigated whether the accuracy of tactile estimation of surface textures can be improved by considering the customer's attribute information. We transformed the texture into a heightmap image and used the image features as input for tactile estimation by machine learning. The results show that the accuracy of tactile estimation is statistically improved by taking into account the gender, risk preference, and personality of the subjects. This method is expected to be useful for designers to adjust products according to the customer and to improve product quality based on tactile sensation.
Hiroki Nakanishi, Yuichi Kurita
Open Access
Article
Conference Proceedings
Mechanism of Multidimensional Subjective Perception of Automotive Interior Fabric Materials
With the rise of new energy vehicles and increased consumer demand for personalization, understanding consumer behavior and emotional experience has become critical. This study analyzes the perceptual dimensions and influencing factors of automotive interior materials that affect consumers' car purchase decisions. The study analyzes consumers' preference for interior materials of new energy vehicles by examining the subjective perception differences between visual and visual-tactile dimensions. The study adopts the "material perception" theory to investigate people's perceptual evaluation of automotive interior fabric materials. Through perception experiments and multidimensional scaling analysis, we establish a space of perception dimensions and a structural model of material perception factors affecting car purchasing decisions. Regarding material roughness, there were significant differences across conditions, with visuotactile sensation rougher than visual sensation, and the interaction of material properties and sensory conditions had a substantial effect on emotionally assessed words. The study's results reveal the critical factors in consumers' car-buying choices and the advantages of automotive interior materials in the emotional perception dimension.
Siqi Yu, Guo Yongyan
Open Access
Article
Conference Proceedings
Exploring the Relationship between Form Features and Price Perception
Price is undeniably a critical factor that shapes consumers' decisions when navigating the intricate landscape of purchasing. Within the realm of consumer behavior, studies have shed light on a fascinating phenomenon: consumers tend to assess the internal cues of a product, particularly its form, when gauging product quality during the purchasing process. Only when form falls short as a judgment criterion do they turn to external cues, such as price. This leads to an intriguing inference — the form of a product significantly influences its perceived price. In light of this, our study is committed to delving deeply into the complex interplay between form features and the perception of price, with the aim of pinpointing specific design elements that enhance consumer perceived price. To focus on the interaction between form features and the perception of price, we eliminate the potential impact of color and material. Thus, this study selects glass perfume bottles with relatively simple colors and materials as the research objects. The study adopts a two-stage experimental approach conducted in the form of focus groups. In the first stage, five high-involvement consumers with over 25 perfume purchasing experiences discussed together to choose seven bottles that are unanimously considered high-priced perfume bottle samples. In the second stage, five expert designers with over 15 years of design experience are invited to extract the design features from the samples selected in the previous stage. The results of this study indicate that specific design features contribute to people's perception of higher prices. Examples of such features include the simulated diamond surface cut, an overall aspect ratio close to 16:9, small and delicate decorations, and clearly demarcated lines between the cap and body. The findings thereby provide valuable insights for designers and strategic recommendations for businesses in terms of pricing strategies.
Feichen Wu, Hanbing Li, Chunheng Ho
Open Access
Article
Conference Proceedings
Study on the shape design of off-road vehicle combined with double diamond model
In order to improve the design quality of car form and guide the designers to grasp the direction of car form design more accurately, this paper researches the process of car form design. Taking the double diamond model design process as the research carrier, firstly, the user's perceptual imagination is studied, and the correlation matrix between the user's perceptual imagination and the product form characteristics is established by combining the evaluation construction theory. Secondly, the correlation matrix was integrated into the double diamond model design process, forming an effective combination of user perceptual needs and the designer's design process. In order to prove the effectiveness of the method, it was implemented in the Sport Utility Vehicle form design project led by the author. We find that the method can effectively combine the user's perceptual needs with the designer's creative process and the evaluation process of the program, providing more scientific guidance for the creativity and evaluation of Sport Utility Vehicle, which is of great significance for improving the quality of vehicle form design. In addition, the Sport Utility Vehicle designed under the guidance of the optimized design process, as the main models of the enterprise, have gained high evaluation from users and also brought the enterprise rich profit returns.
Huajie Wang, Zhang Jin, Xikai Tan
Open Access
Article
Conference Proceedings
A Front Face Design of New Energy Vehicles Based on Rough Set Theory and Backpropagation Neural Network
With the increasing awareness of environmental protection and prominent problem of traditional energy, new energy vehicles are an important choice to replace traditional oil-fueled vehicles. As an important part of new energy vehicles, the design of front face has an important impact on vehicles’ image, sales, and brand awareness. A front face’s modeling design process of new energy vehicles is proposed in this paper based on Kansei Engineering (KE)/ Rough Set Theory (RST)/ Backpropagation Neural Network (BPNN). Firstly, Kansei semantic analysis is carried out on the front face’s modeling of new energy vehicles, including collecting the front face samples of new energy vehicles and Kansei semantic words, the collected Kansei semantic words are reduced dimensional and clustered by using Factor Analysis (FA). Secondly, the morphological analysis method is used to decompose the front face samples of new energy vehicles into different design features, the attribute reduction algorithm in RST is used to identify the key design features of new energy vehicles that have an important impact on users’ satisfaction. Finally, BPNN is used to establish the mapping model between the users’ Kansei image and the key design features of new energy vehicles’ front face, thus obtaining the optimal design combination of new energy vehicles’ front face with the highest Kansei value. The results enable designers to grasp users’ sentimental cognition of new energy vehicles’ front face modeling effectively and accurately so as to improve users’ purchase desire. This method can provide references for the modeling design of related products.
Chen Zimo, Feng Hailong, Li Yajun
Open Access
Article
Conference Proceedings
Assessing Self-disclosure Willingness in Metaverse-Based Structured Group Encounter
Avatar-based communication in the metaverse offers a more extensive range of non-verbal information compared to traditional web-conferencing platforms. This study introduced a metaverse-based structured group encounter (M-SGE) and examined its effects on state anxiety, mood, and self-disclosure. The results indicated a significant reduction in state anxiety among participants following their involvement in M-SGE (p = .01, d = .90). Additionally, there was a marked increase in the participants’ willingness to self-disclose (p = .019, d = -.79). However, no significant differences in mood were observed before and after the M-SGE. The M-SGE offers the advantage of enabling communication through avatars for individuals perceiving face-to-face conversations as a challenge, regardless of time and place constraints. During the experiment, there were occasional instances of voice feedback and audio difficulties among participants, indicating the need for an improved communication environment.
Teru Kawakita, Hideaki Kanai
Open Access
Article
Conference Proceedings