Search

Virtual Reality (VR) has been a beneficial training tool in fields such as advanced manufacturing. However, users may experience a high cognitive load due to various factors, such as the use of VR hardware or tasks within the VR environment. Studies have shown that eye-tracking has the potential to detect cognitive load, but in the context of VR and complex spatiotemporal tasks (e.g., assembly and disassembly), it remains relatively unexplored. Here, we present an ongoing study to detect users' cognitive load using an eye-tracking-based machine learning approach. We developed a VR training system for cold spray and tested it with 22 participants, obtaining 19 valid eye-tracking datasets and NASA-TLX scores. We applied Multi-Layer Perceptron (MLP) and Random Forest (RF) models to compare the accuracy of predicting cognitive load (i.e., NASA-TLX) using pupil dilation and fixation duration. Our preliminary analysis demonstrates the feasibility of using eye tracking to detect cognitive load in complex spatiotemporal VR experiences and motivates further exploration.

This study investigates methods for controlling the physical properties of the intrinsic magnetic topological insulator MnBi$_2$Te$_4$ (MBT) by substituting Mn with Pb in Mn$_{1-x}$Pb$_x$Bi$_2$Te$_4$ (MPBT) solid solutions. This substitution enables tunable magnetic and electronic properties. Using various angle-resolved photoemission spectroscopy (ARPES) techniques, including spin-resolved and circular dichroism (CD) measurements, we analyzed the evolution of the electronic structure across different Pb concentrations, with a focus on topological phase transitions (TPT) near x = 50 %. Key indicators of TPT include the presence or absence of topological surface states (TSS) and bulk band gap closure. The results show a gradual decrease of the bulk band gap in the electronic structure of MPBT up to x = 40 %, where it nearly vanishes, followed by a constant gap value between 40 - 60 %, and its reopening above 80 %, which is accompanied by a transition of the electronic structure of MPBT to a PbBi$_2$Te$_4$-like electronic structure. TSS were observed at x less than 30 % and greater than 80 %, as confirmed by CD and spin-resolved ARPES data, but were absent near x = 55 %, suggesting a distinct topological phase - possibly semi-metallic or a trivial insulator with a narrow gap phase. These findings demonstrate the tunability of the electronic structure of MPBT, making it a promising candidate for topological and spintronic applications.

Apprenticeship and training programs in advanced manufacturing frequently encounter safety and accessibility concerns due to using heavy machinery. Virtual Reality (VR) training addresses such constraints while maintaining the spatial and procedural learning requirements of such training. However, designing effective VR training is challenging because advanced manufacturing processes are complex and require experts to train novices for a long time. This paper presents a VR Training Apprenticeship (VRTA) tailored for cold spray, which we carefully designed to teach novices step-by-step this particular advanced manufacturing process. To assess its effectiveness, we conducted an exploratory study ($n = 22$). We evaluated user experience (UX) measures in the form of quantitative scales, users' qualitative insights, and task performance with real-world machinery after the VR training. We discuss how the VRTA design contributed to the effectiveness and the challenges of considering VR training for advanced manufacturing.

Storyboarding is an established method for designing user experiences. Generative AI can support this process by helping designers quickly create visual narratives. However, existing tools only focus on accurate text-to-image generation. Currently, it is not clear how to effectively support the entire creative process of storyboarding and how to develop AI-powered tools to support designers' individual workflows. In this work, we iteratively developed and implemented StoryDiffusion, a system that integrates text-to-text and text-to-image models, to support the generation of narratives and images in a single pipeline. With a user study, we observed 12 UX designers using the system for both concept ideation and illustration tasks. Our findings identified AI-directed vs. user-directed creative strategies in both tasks and revealed the importance of supporting the interchange between narrative iteration and image generation. We also found effects of the design tasks on their strategies and preferences, providing insights for future development.

Using angle-resolved photoemission spectroscopy (ARPES) and density functional theory (DFT), an experimental and theoretical study of changes in the electronic structure (dispersion dependencies) and corresponding modification of the energy band gap at the Dirac point (DP) for topological insulator (TI) $\mathrm{Mn}_{1-x} \mathrm{Ge}_x \mathrm{Bi}_2 \mathrm{Te}_4$ have been carried out with gradual replacement of magnetic Mn atoms by non-magnetic Ge atoms when concentration of the latter was varied from 10$\%$ to 75$\%$. It was shown that when Ge concentration increases then the bulk band gap decreases and reaches zero plateau in the concentration range of 45$\%$-60$\%$ while non-topological surface states (TSS) are present and exhibit an energy splitting of 100 and 70 meV in different types of measurements. It was also shown that TSS disappear from the measured band dispersions at a Ge concentration of about 40$\%$. DFT calculations of $\mathrm{Mn}_{1-x} \mathrm{Ge}_x \mathrm{Bi}_2 \mathrm{Te}_4$ band structure were carried out to identify the nature of observed band dispersion features and to analyze a possibility of magnetic Weyl semimetal state formation in this system. These calculations were performed for both antiferromagnetic (AFM) and ferromagnetic (FM) ordering types while the spin-orbit coupling (SOC) strength was varied or a strain (compression or tension) along the $c$-axis was applied. Calculations show that two different series of topological phase transitions (TPTs) may be implemented in this system depending on the magnetic ordering. At AFM ordering transition between TI and trivial insulator phase goes through the Dirac semimetal state, whereas for FM phase such route admits three intermediate states instead of one (TI - Dirac semimetal - Weyl semimetal - Dirac semimetal - trivial insulator).

Access to large amounts of diverse design solutions can support designers during the early stage of the design process. In this paper, we explore the efficacy of large language models (LLM) in producing diverse design solutions, investigating the level of impact that parameter tuning and various prompt engineering techniques can have on the diversity of LLM-generated design solutions. Specifically, LLMs are used to generate a total of 4,000 design solutions across five distinct design topics, eight combinations of parameters, and eight different types of prompt engineering techniques, comparing each combination of parameter and prompt engineering method across four different diversity metrics. LLM-generated solutions are compared against 100 human-crowdsourced solutions in each design topic using the same set of diversity metrics. Results indicate that human-generated solutions consistently have greater diversity scores across all design topics. Using a post hoc logistic regression analysis we investigate whether these differences primarily exist at the semantic level. Results show that there is a divide in some design topics between humans and LLM-generated solutions, while others have no clear divide. Taken together, these results contribute to the understanding of LLMs' capabilities in generating a large volume of diverse design solutions and offer insights for future research that leverages LLMs to generate diverse design solutions for a broad range of design tasks (e.g., inspirational stimuli)., Comment: preprint of journal paper

As Generative AI rises in adoption, its use has expanded to include domains such as hiring and recruiting. However, without examining the potential of bias, this may negatively impact marginalized populations, including people with disabilities. To address this important concern, we present a resume audit study, in which we ask ChatGPT (specifically, GPT-4) to rank a resume against the same resume enhanced with an additional leadership award, scholarship, panel presentation, and membership that are disability related. We find that GPT-4 exhibits prejudice towards these enhanced CVs. Further, we show that this prejudice can be quantifiably reduced by training a custom GPTs on principles of DEI and disability justice. Our study also includes a unique qualitative analysis of the types of direct and indirect ableism GPT-4 uses to justify its biased decisions and suggest directions for additional bias mitigation work. Additionally, since these justifications are presumably drawn from training data containing real-world biased statements made by humans, our analysis suggests additional avenues for understanding and addressing human bias.

Concept generation is a creative step in the conceptual design phase, where designers often turn to brainstorming, mindmapping, or crowdsourcing design ideas to complement their own knowledge of the domain. Recent advances in natural language processing (NLP) and machine learning (ML) have led to the rise of Large Language Models (LLMs) capable of generating seemingly creative outputs from textual prompts. The success of these models has led to their integration and application across a variety of domains, including art, entertainment, and other creative work. In this paper, we leverage LLMs to generate solutions for a set of 12 design problems and compare them to a baseline of crowdsourced solutions. We evaluate the differences between generated and crowdsourced design solutions through multiple perspectives, including human expert evaluations and computational metrics. Expert evaluations indicate that the LLM-generated solutions have higher average feasibility and usefulness while the crowdsourced solutions have more novelty. We experiment with prompt engineering and find that leveraging few-shot learning can lead to the generation of solutions that are more similar to the crowdsourced solutions. These findings provide insight into the quality of design solutions generated with LLMs and begins to evaluate prompt engineering techniques that could be leveraged by practitioners to generate higher-quality design solutions synergistically with LLMs., Comment: Proceedings of the ASME 2023 International Design Engineering Technical Conferences and Computers and Information in Engineering Conferences

Typical parametric approaches restrict the exploration of diverse designs by generating variations based on a baseline design. In contrast, generative models provide a solution by leveraging existing designs to create compact yet diverse generative design spaces (GDSs). However, the effectiveness of current exploration methods in complex GDSs, especially in ship hull design, remains unclear. To that end, we first construct a GDS using a generative adversarial network, trained on 52,591 designs of various ship types. Next, we constructed three modes of exploration, random (REM), semi-automated (SAEM) and automated (AEM), with varying levels of user involvement to explore GDS for novel and optimised designs. In REM, users manually explore the GDS based on intuition. In SAEM, both the users and optimiser drive the exploration. The optimiser focuses on exploring a diverse set of optimised designs, while the user directs the exploration towards their design preference. AEM uses an optimiser to search for the global optimum based on design performance. Our results revealed that REM generates the most diverse designs, followed by SAEM and AEM. However, the SAEM and AEM produce better-performing designs. Specifically, SAEM is the most effective in exploring designs with a high trade-off between novelty and performance. In conclusion, our study highlights the need for innovative exploration approaches to fully harness the potential of GDS in design optimisation.

In this work, we introduce ShipHullGAN, a generic parametric modeller built using deep convolutional generative adversarial networks (GANs) for the versatile representation and generation of ship hulls. At a high level, the new model intends to address the current conservatism in the parametric ship design paradigm, where parametric modellers can only handle a particular ship type. We trained ShipHullGAN on a large dataset of 52,591 \textit{physically validated} designs from a wide range of existing ship types, including container ships, tankers, bulk carriers, tugboats, and crew supply vessels. We developed a new shape extraction and representation strategy to convert all training designs into a common geometric representation of the same resolution, as typically GANs can only accept vectors of fixed dimension as input. A space-filling layer is placed right after the generator component to ensure that the trained generator can cover all design classes. During training, designs are provided in the form of a shape-signature tensor (SST) which harnesses the compact geometric representation using geometric moments that further enable the inexpensive incorporation of physics-informed elements in ship design. We have shown through extensive comparative studies and optimisation cases that ShipHullGAN can generate designs with augmented features resulting in versatile design spaces that produce traditional and novel designs with geometrically valid and practically feasible shapes.

In this paper, we introduce novel methods for computing middle surfaces between various 3D data sets such as point clouds and/or discrete surfaces. Traditionally the middle surface is obtained by detecting singularities in computed distance function such as ridges, triple junctions, etc. It requires to compute second order differential characteristics and also some kinds of heuristics must be applied. Opposite to that, we determine the middle surface just from computing the distance function itself which is a fast and simple approach. We present and compare the results of the fast sweeping method, the vector distance transform algorithm, the fast marching method, and the Dijkstra-Pythagoras method in finding the middle surface between 3D data sets.