An official website of the United States government
A practical and well-studied method for computing the novelty of a design is to construct an ordinal embedding via a collection of pairwise comparisons between items (called triplets), and use distances within that embedding to compute which designs are farthest from the center. Unfortunately, ordinal embedding methods can require a large number of triplets before their primary error measure — the triplet violation error — converges. But if our goal is accurate novelty estimation, is it really necessary to fully minimize all triplet violations? Can we extract useful information regarding the novelty of all or some items using fewer triplets than classical convergence rates might imply? This paper addresses this question by studying the relationship between triplet violation error and novelty score error when using ordinal embeddings. Specifically, we compare how errors in embeddings produced by Generalized Non-Metric Dimensional Scaling (GNMDS) converge under different sampling methods, for different numbers of embedded items, sizes of latent spaces, and for the top K most novel designs. We find that estimating the novelty of a set of items via ordinal embedding can require significantly fewer human-provided triplets than is needed to converge the triplet error, and that this effect is modulated by the type of triplet sampling method (random versus uncertainty sampling). We also find that uncertainty sampling causes unique converge behavior in estimating most novel items compared to non-novel items. Our results imply that in certain situations one can use ordinal embedding techniques to estimate novelty error in fewer samples than is typically expected. Moreover, the convergence behavior of top K novel items motivates new potential triplet sampling methods that go beyond typical triplet reduction measures.
more »
« less
Novelty and the Structure of Design Landscapes: A Relational View of Online Innovation Communities
Design artifacts in online innovation communities are increasingly becoming a primary source of innovation for organizations. A distinguishing feature of such communities is that they are organized around design artifacts, not around people. The search for novel innovations thus equates to a search for novel designs. This is not a trivial problem since the novelty of a design is a function of its relationship to other designs, and this relationship changes as each design is added. These relations between artifacts affect both consumption and production. Moreover, these relations form a landscape whose structure affects the emergence of novelty. We find evidence for our theorizing using an analysis of over 35,000 Thingiverse design artifacts. This work identifies the differential effects of different forms of novelty, visual and verbal, on subsequent innovation, and identifies the differential effects of different degrees of structure in the landscape on novelty.
more »
« less
- PAR ID:
- 10302566
- Date Published:
- Journal Name:
- MIS quarterly
- Volume:
- 46
- Issue:
- 3
- ISSN:
- 0276-7783
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Text-to-image generative models have increasingly been used to assist designers during concept generation in various creative domains, such as graphic design, user interface design, and fashion design. However, their applications in engineering design remain limited due to the models’ challenges in generating images of feasible designs concepts. To address this issue, this paper introduces a method that improves the design feasibility by prompting the generation with feasible CAD images. In this work, the usefulness of this method is investigated through a case study with a bike design task using an off-the-shelf text-to-image model, Stable Diffusion 2.1. A diverse set of bike designs are produced in seven different generation settings with varying CAD image prompting weights, and these designs are evaluated on their perceived feasibility and novelty. Results demonstrate that the CAD image prompting successfully helps text-to-image models like Stable Diffusion 2.1 create visibly more feasible design images. While a general tradeoff is observed between feasibility and novelty, when the prompting weight is kept low around 0.35, the design feasibility is significantly improved while its novelty remains on par with those generated by text prompts alone. The insights from this case study offer some guidelines for selecting the appropriate CAD image prompting weight for different stages of the engineering design process. When utilized effectively, our CAD image prompting method opens doors to a wider range of applications of text-to-image models in engineering design.more » « less
-
null (Ed.)With increasing challenges to health care in the foreseeable future, novel technology solutions are increasingly needed. Meanwhile, biomedical engineers are increasingly asked to develop user-centered solutions (i.e., desired by the end users). Nevertheless, the importance of user-centeredness is often neglected in the innovation process. It remains unclear about the interplay between thinking of solution novelty and desirability in addition to feasibility, and thus it is challenging for biomedical engineering educators to balance the teaching of the above two aspects in a BME design curriculum. This study aims to develop a preliminary version of a user-centered innovation potential assessment instrument applicable to diverse biomedical engineering design projects. The assessment instrument was adapted from File and Purzer (2014)’s definition of innovation potential (1) feasibility (2) viability (3) desirability and (4) novelty. Among these aspects, we focused on assessing feasibility, desirability and novelty, which can be quantified and assigned to each design idea proposed by the students. As the first attempt, we targeted students’ innovation potential in the design prototyping phase. To validate our preliminary development, we gave an in-class design task for smart pill dispenser to 30+ pairs of senior students enrolled in the BME capstone design course. To assess the design ideas, the instructor and his teaching assistant (two of the authors on the paper) applied a thematic analysis. We first identified patterns from the submitted design ideas by extracting key attributes including dispenser’s portability, tracking/reminding capability, safety, and easy to use. We then estimated the frequency and novelty of these key attributes appearing in each design idea and converted each of them to a 5-point scale. Finally, we calculated a composite score for user-centered innovation potential by multiplying the scales on feasibility, desirability and novelty. We believe this study has added value to improving our understanding of user-centered innovation potential in an undergraduate biomedical engineering curriculum. With further development and scaled-up validation, we may be able to use the instrument to provide insights into developing teaching interventions for stimulating user-centered innovative potentials among biomedical engineers.more » « less
-
This study explores the integration of text-to-image generative AI, particularly Stable Diffusion, in conjunction with ControlNet and LoRA models in conceptual landscape design. Traditional methods in landscape design are often time-consuming and limited by the designer’s individual creativity, also often lacking efficiency in the exploration of diverse design solutions. By leveraging AI tools, we demonstrate a workflow that efficiently generates detailed and visually coherent landscape designs, including natural parks, city plazas, and courtyard gardens. Through both qualitative and quantitative evaluations, our results indicate that fine-tuned models produce superior designs compared to non-fine-tuned models, maintaining spatial consistency, control over scale, and relevant landscape elements. This research advances the efficiency of conceptual design processes and underscores the potential of AI in enhancing creativity and innovation in landscape architecture.more » « less
-
Recent breakthroughs in deep-learning (DL) approaches have resulted in the dynamic generation of trace links that are far more accurate than was previously possible. However, DL-generated links lack clear explanations, and therefore non-experts in the domain can find it difficult to understand the underlying semantics of the link, making it hard for them to evaluate the link's correctness or suitability for a specific software engineering task. In this paper we present a novel NLP pipeline for generating and visualizing trace link explanations. Our approach identifies domain-specific concepts, retrieves a corpus of concept-related sentences, mines concept definitions and usage examples, and identifies relations between cross-artifact concepts in order to explain the links. It applies a post-processing step to prioritize the most likely acronyms and definitions and to eliminate non-relevant ones. We evaluate our approach using project artifacts from three different domains of interstellar telescopes, positive train control, and electronic healthcare systems, and then report coverage, correctness, and potential utility of the generated definitions. We design and utilize an explanation interface which leverages concept definitions and relations to visualize and explain trace link rationales, and we report results from a user study that was conducted to evaluate the effectiveness of the explanation interface. Results show that the explanations presented in the interface helped non-experts to understand the underlying semantics of a trace link and improved their ability to vet the correctness of the link.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.25300/MISQ/2022/15059
