Search

This study explores the application of image generative AI to support design process by creating inspiration boards. Through an evaluative study, we compare the diversity, quantity, fidelity, and ambiguity of boards generated by image generative AI and traditional methods. The results highlight how generative AI produces a quantity of images, it exhibits limited diversity compared to traditional methods. This suggests a tendency for supporting interpolation rather than extrapolation of ideas, in turn providing insights on best practice and into the optimal stage for its application. [ABSTRACT FROM AUTHOR]

This article presents an fNIRS experiment investigating cognitive differences between physical and digital prototyping methods in designers (N=25) engaged in open and constrained design tasks. Initial results suggest that physical prototyping yields increased hemodynamic response (i.e., brain activity) compared to digital design, and that constrained design yields increased hemodynamic response compared to open design, in the prefrontal cortex. Further work will seek to triangulate results by investigating potential correlations to design processes and design outputs. [ABSTRACT FROM AUTHOR]

Generative design is now a core capability of today's CAD systems enabling broader exploration of the design space. This paper presents a desktop review of 15 tools with the aim of characterising where the tools are used in the design process and to what extent they can be considered creative.The results showed that, despite their increasing capabilities, GD tools are unable to exhibit all phases of creativity and cannot be applied in all stages of the design process. This highlights the criticality of the human in design providing opportunities for GD to augment designer creativity. [ABSTRACT FROM AUTHOR]

This study investigates the relationship between the number and type of prototypes developed in rapid prototyping contexts, a team's performance self-estimations, and final actual performance. Findings suggest a strong correlation between each of these elements, with the converse also found to be true, motivating the introduction of the concept of Design Delusion - a type of cognitive dissonance due to differences between perceived and actual states. The paper suggests that early prototyping helps identify and mitigate design delusion, improving design decisions and preventing technical debt. [ABSTRACT FROM AUTHOR]

Design hackathons offer a unique research opportunity to study time-pressured collaborative design. At the same time, research on design hackathons faces unique methodological challenges, prompting the exploration of new research approaches. This paper proposes a new data-collection framework that leverages a virtual format of hackathon events and enables a deeper insight into hackathon dynamics. The framework applicability is presented through a case study of the IDEA challenge hackathon, in which different intrusive and non-intrusive data collection approaches were used. [ABSTRACT FROM AUTHOR]

Design neurocognition is an emerging research area that can provide insights into the black box of designers' cognitive processes. However, work to date has focused on neurocognition on its own, without integrating this with other design measures. This paper presents the results of a pilot study which brings together designer neurocognition with design output and assessment of the design process followed in a constrained prototyping activity comparing use of physical and digital Lego. This was achieved via EEG data capture, a TLX survey and measures of design output variance. Differences between physical and digital prototyping methods were found with respect to Task Related Powers of EEG signals and the design process followed with digital prototyping methods found to take longer, require more effort and cause more frustration. No differences were found with regard to design output. Whilst the sample size used (n=12) was small, future studies will use large sample sizes to increase their statistical power and will consider alternative EEG or fNIRS to capture brain activity due to challenges with the headset used in this study. [ABSTRACT FROM AUTHOR]

Prototyping strategies and technology often focus on reducing the fabrication time and cost between design iterations, however, there is limited knowledge about the specific characteristics of change that prototyping strategies aim to impact. To investigate, and better understand these characteristics, this study curates and systematically analyses a representative dataset of 50 'real-world' prototype samples. The study aims to explore the various elements that constitute a design change and to determine their impact on the scale of volumetric change detected. The results highlight emergent patterns and correlations between study metrics to better understand the reasons for design change and the frequency and scale of changes detected in the sample dataset. Findings reveal that the purpose of a design change is, in certain cases, highly correlated to the scale of change affected, and that some changes are more prevalent in the dataset than others, with an average volumetric difference of 4.2% between sample versions detected. The study provides an initial characterisation of prototype change to guide iterative prototyping processes and improve the efficiency and effectiveness of design iterations. [ABSTRACT FROM AUTHOR]

The breadth of media and approaches used when prototyping are vast, with each holding inherent properties that vary their suitability for a given prototyping activity. While several have established classifications of types and purposes of prototypes, there is little by way of guidance for designers on how select and strategise prototyping given their activity needs, or how the prototype chosen may influence their process, success or efficiency. This paper presents nine affordances of prototypes derived from literature, together characterising the properties of prototyping media or approaches that affect their suitability across prototyping activities. The affordances are illustrated through application to physical and digital classes of prototypes and four real prototype cases, showing descriptive capability, inherent differences between the media, and enabling direct and consistent comparison. By mapping affordances across many media and approaches, this work enables better method selection to align with activity needs, better description and comparison of media and approaches, and the ability the broadly interrogate and direct future development of prototyping technologies. [ABSTRACT FROM AUTHOR]

Machine Learning (ML) techniques are showing increasing use and value in the engineering sector. Object Detection methods, by which an ML system identifies objects from an image presented to it, have demonstrated promise for search and retrieval and synchronised physical/digital version control, amongst many applications. However, accuracy of detection often decreases as the number of objects considered by the system increases which, combined with very high training times and computational overhead, makes widespread use infeasible. This work presents a hierarchical ML workflow that leverages the pre-existing taxonometric structures of engineering components and abundant digital models (CAD) to streamline training and increase accuracy. With a two-layer structure, the approach demonstrates potential to increase accuracy to >90%, with potential time savings of 75% and greatly increased flexibility and expandability. While further refinement is required to increase robustness of detection and investigate scalability, the approach shows significant promise to increase feasibility of Object Detection techniques in engineering. [ABSTRACT FROM AUTHOR]