An official website of the United States government
This NSF-funded study aims to develop and evaluate a novel debriefing system that aims to capture and visualize multimodal data streams from multi-user VR environment that evaluate learners’ cognitive (clinical decision-making) and behavioral (situational awareness, communication) processes to provide data-informed feedback focused on improving team-based care of patients who suffer sudden medical emergencies. Through this new multimodal debriefing system, instructors will be able to provide personalized feedback to clinicians during post-simulation debriefing sessions.
more »
« less
Toward Wearable Devices for Multiteam Systems Learning
This chapter provides an overview of an exploratory case study involving a multiteam system in the fire and rescue emergency context incorporating human sensor analytics (e.g., proximity sensors) and other data sources to reveal important insights on within- and between-team learning and training. Incorporating a design research approach, the case study consisting of two live simulation scenarios that informed the design and development of a wearable technology-based system targeted to capture team-based behavior in the live simulation and visualize it during the debriefing session immediately following to potentially inform within- and cross-team behavior from a multiteam systems perspective informed by theory and practice.
more »
« less
- Award ID(s):
- 1637263
- PAR ID:
- 10113357
- Date Published:
- Journal Name:
- Lecture notes in computer science
- ISSN:
- 1611-3349
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Abstract Adhesive bonding of composite materials has become increasingly crucial for advanced engineering applications, offering unique advantages for lightweight and high-performance designs. This study presents a novel framework, physics-informed failure mode proportion prediction (PIFMP) model, for predicting failure mode proportions in composite adhesive joints, addressing critical gaps in understanding mixed-mode failure behaviors. In contrast to conventional approaches that focus solely on force or stress prediction, this research integrates important parameters from multistage manufacturing processes (MMPs) and simulation data into a physics-informed machine learning (PIML) framework, enabling proactive failure prediction and design optimization. The proposed framework unifies data-driven machine learning models with features derived from finite element analysis (FEA), incorporating cohesive zone modeling (CZM) to capture the physical dynamics of adhesive behavior under lap shearing. By embedding FEA-based physics features into the machine learning process and leveraging a time-series transformer model to analyze the temporal progression of interfacial damage and separation, the framework ensures predictive accuracy and physics-informed consistency, enabling precise analysis of failure mechanisms. The empirical study validates the effectiveness and the reliability of the framework, demonstrating enhanced predictive performance through cross-validation. The work establishes a foundational approach for failure analysis and provides a robust basis for future advancements.more » « less
-
Household air pollution is a pervasive environmental health problem wherever access to cleaner fuels is poor. Despite numerous attempts to transition households away from polluting fuels, interventions are rarely sustainable. This intractability indicates that structural (i.e., systemic) dynamics act to maintain the status quo. In this case study of Ghana's Rural Liquefied Petroleum Gas (LPG) Promotion Program, our objectives were to 1) identify system structures affecting sustained fuel use, and 2) test strategies for improving intervention outcomes. To address these objectives, we applied a system dynamics approach, informed by a systematic literature review. A virtual simulation model was constructed to represent the implementation of the Rural LPG Program and its outcomes. By analyzing the model's structure and behavior, we proposed strategies that would improve the intervention's outcomes and tested the effectiveness of the strategies within the simulation model. Our results show that distributing two LPG cylinders to households (instead of one) contributed toward primary use of the fuel, whereas free weekly delivery of LPG (for up to four years) had limited long-term benefits and diminishing returns. Furthermore, reducing the time for users to perceive the benefits of cleaner fuels enhanced willingness-to-pay, and thereby helped to sustain higher rates of LPG use. This suggests that intervention planners should identify new users' expectations of benefits and proactively design ways to realize those benefits quickly (in a few weeks or less), while policy makers should support this as a design requirement in approval processes.more » « less
-
Wearable computers are poised to impact disaster response, so there is a need to determine the best interfaces to support situation awareness, decision support, and communication. We present a disaster response wearable design created for a mixed reality live-action role playing design competition, the Icehouse Challenge. The challenge, an independent event in which the authors were competitors, offers a simulation game environment in which teams compete to test wearable designs. In this game, players move through a simulated disaster space that requires team coordination and physical exertion to mitigate virtual hazards and stabilize virtual victims. Our design was grounded in disaster response and team coordination practice. We present our design process to develop wearable computer interfaces that integrate physiological and virtual environmental sensor data and display actionable information through a head-mounted display. We reflect on our observations from the live game, discuss challenges, opportunities, and design implications for future disaster response wearables to support collaboration.more » « less
-
Leung, Carson (Ed.)Examining the effectiveness of machine learning techniques in analyzing engineering students’ decision-making processes through topic modeling during simulation-based design tasks is crucial for advancing educational methods and tools. Thus, this study presents a comparative analysis of different supervised and unsupervised machine learning techniques for topic modeling, along with human validation. Hence, this manuscript contributes by evaluating the effectiveness of these techniques in identifying nuanced topics within the argumentation framework and improving computational methods for assessing students’ abilities and performance levels based on their informed decisions. This study examined the decision-making processes of engineering students as they participated in a simulation-based design challenge. During this task, students were prompted to use an argumentation framework to articulate their claims, evidence, and reasoning, by recording their informed design decisions in a design journal. This study combined qualitative and computational methods to analyze the students’ design journals and ensured the accuracy of the findings through the researchers’ review and interpretations of the results. Different machine learning models, including random forest, SVM, and K-nearest neighbors (KNNs), were tested for multilabel regression, using preprocessing techniques such as TF-IDF, GloVe, and BERT embeddings. Additionally, hyperparameter optimization and model interpretability were explored, along with models like RNNs with LSTM, XGBoost, and LightGBM. The results demonstrate that both supervised and unsupervised machine learning models effectively identified nuanced topics within the argumentation framework used during the design challenge of designing a zero-energy home for a Midwestern city using a CAD/CAE simulation platform. Notably, XGBoost exhibited superior predictive accuracy in estimating topic proportions, highlighting its potential for broader application in engineering education.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- The DOI is not currently available.
