Biomedical data harmonization is essential for enabling exploratory analyses and meta-studies, but the process of schema matching-identifying semantic correspondences between elements of disparate datasets (schemas)-remains a labor-intensive and error-prone task. Even state-of-the-art automated methods often yield low accuracy when applied to biomedical schemas due to the large number of attributes and nuanced semantic differences between them. We present BDIViz, a novel visual analytics system designed to streamline the schema matching process for biomedical data. Through formative studies with domain experts, we identified key requirements for an effective solution and developed interactive visualization techniques that address both scalability challenges and semantic ambiguity. BDIViz employs an ensemble approach that combines multiple matching methods with LLM-based validation, summarizes matches through interactive heatmaps, and provides coordinated views that enable users to quickly compare attributes and their values. Our method-agnostic design allows the system to integrate various schema matching algorithms and adapt to application-specific needs. Through two biomedical case studies and a within-subject user study with domain experts, we demonstrate that BDIViz significantly improves matching accuracy while reducing cognitive load and curation time compared to baseline approaches.

Adaptive training of motor-skills, where the difficulty level of the training task is adapted optimally based on the learner’s skill levels, has been shown to enable higher learning gains compared to non-adaptive training. However, prior approaches rely on adapting physical tools that are tedious to design and build. This work investigates using augmented reality (AR) to achieve a similar objective of maintaining functional task difficulty – the difficulty experienced by the learner – at an optimal challenge point during adaptive training. A study prototype of an AR adaptive basketball training system was developed, wherein the learners train to throw a physical ball into a virtual AR hoop seen through a head-mounted device. Results from the study (N=16) aimed to measure the learning gains showed higher learning gains after adaptive AR training compared to non-adaptive AR training. An analysis of participant feedback, however, highlighted challenges with AR-based adaptive training, pointing to the need for a different design approach compared to the physical adaptive tools. Collectively, this exploratory study investigates the use of AR for adaptive motor-skill learning and lays the foundation for future research directions for the AR-tool design.

Virtual Reality (VR) can support effective and scalable training of psychomotor skills in manufacturing. However, many industry training modules offer experiences that are close-ended and do not allow for human error. We aim to address this gap in VR training tools for psychomotor skills training by exploring an open-ended approach to the system design. We designed a VR training simulation prototype to perform open-ended practice of drilling using a 3-axis milling machine. The simulation employs near “endto-end” instruction through a safety module, a setup and drilling tutorial, open-ended practice complete with warnings of mistakes and failures, and a function to assess the geometries and locations of drilled holes against an engineering drawing. We developed and conducted a user study within an undergraduate-level introductory fabrication course to investigate the impact of open-ended VR practice on learning outcomes. Study results reveal positive trends, with the VR group successfully completing the machining task of drilling at a higher rate (75% vs 64%), with fewer mistakes (1.75 vs 2.14 score), and in less time (17.67 mins vs 21.57 mins) compared to the control group. We discuss our findings and limitations and implications for the design of open-ended VR training systems for learning psychomotor skills.

In this paper, we propose SensorViz, a visualization tool that supports novice makers during different stages of prototyping with sensors. SensorViz provides three modes of visualization: (1) visualizing datasheet specifications before buying sensors, (2) visualizing sensor interaction with the environment via AR before building the physical prototype, and (3) visualizing live/recorded sensor data to test the assembled prototype. SensorViz includes a library of visualization primitives for different types of sensor data and a sensor database builder, which once a new sensor is added automatically creates a matching visualization by composing visualization primitives. Our user study with 12 makers shows that users are more effective in selecting sensors and configuring sensor layouts using SensorViz compared to traditional prototyping utilizing datasheets and manual testing on the prototype. Our post hoc interviews indicate that SensorViz reduces trial and error by allowing makers to explore sensor positions on the prototype early in the design process.

Integrating fabrication activities into existing video games provides opportunities for players to construct objects from their gameplay and bring the digital content into the physical world. In our prior work, we outlined a framework and developed a toolkit for integrating fabrication activities within existing digital games. Insights from our prior study highlighted the challenge of aligning fabrication mechanics with the existing game mechanics in order to strengthen the player aesthetics.

A recent study on motor-skill training showed that adaptive training tools that use shape-change to adapt the training difficulty based on learners’ performance can lead to higher learning gains. However, to date, no support tools exist to help designers create adaptive learning tools. Our formative study shows that developing the adaptive learning algorithm poses a particular challenge. To address this, we built Adapt2Learn, a toolkit that auto-generates the learning algorithm for adaptive tools. Designers choose their tool’s sensors and actuators, Adapt2Learn then configures the learning algorithm and generates a microcontroller script that designers can deploy on the tool. Once uploaded, the script assesses the learner’s performance via the sensors, computes the training difficulty, and actuates the tool to adapt the difficulty. Adapt2Learn’s visualization tool then lets designers visualize their tool’s adaptation and evaluate the learning algorithm. To validate that Adapt2Learn can generate adaptation algorithms for different tools, we built several application examples that demonstrate successful deployment.

Fabricating objects from a player’s gameplay, for example, collectibles of valuable game items, or custom game controllers shaped from game objects, expands ways to engage with digital games. Researchers currently create such integrated fabrication games from scratch, which is time-consuming and misses the potential of integrating fabrication with the myriad existing games. Integrating fabrication with the real-time gameplay of existing games, however, is challenging without access to the source files.

Adaptive tools that can change their shape to support users with motor tasks have been used in a variety of applications, such as to improve ergonomics and support muscle memory. In this paper, we investigate whether shape-adapting tools can also help in motor skill training. In contrast to static training tools that maintain task difficulty at a fixed level during training, shape-adapting tools can vary task difficulty and thus keep learners’ training at the optimal challenge point, where the task is neither too easy, nor too difficult.