Test Scenarios Research Articles

MaP-SGAN: Multi-anchor point siamese GAN for Wi-Fi CSI-based cross-domain gait recognition

With the pervasive growth of IoT, Wi-Fi CSI-based human gait recognition faces the challenge of maintaining model robustness in new environments. Current cross-domain methods often rely on symmetric data, restricting their practical utility. To overcome this limitation, we propose MaP-SGAN, an innovative model specifically designed to enhance gait recognition’s robustness in cross-domain scenarios. MaP-SGAN integrates three crucial components: (1) the Consistency Maintenance Module, utilizing a Siamese network to ensure latent vector consistency within the asymmetric data domain; (2) the Diversity Enhancement Module, incorporating static environmental information to diversify the generator and improve the alignment of generated samples with the target domain’s characteristics; (3) the Multi-anchor Point Metrics in the discriminator, employing multi-anchor point metrics to constrain the similarity between generated data and target domain features. This metric approach comprehensively addresses the distributional differences between the source and target domains, thereby enhancing the model’s discriminative capability and generalization performance. Through extensive testing in diverse scenarios involving different clothing and environments, our proposed MaP-SGAN model achieves an average accuracy of 87.58% in cross-clothing recognition, which is an improvement of 4.03% compared to existing state-of-the-art models. The average accuracy in cross-environment recognition is 53.8%, which is an improvement of about 6.34% compared to existing state-of-the-art models.

A test rig for the validation of CFD simulations of a passenger vehicle under hood environment

As part of global efforts to reduce greenhouse gas emissions, the automotive industry is moving towards the electrification of its fleet – including full electric and hybrid vehicles. Considering hybrid vehicles, the energy efficiency and thermal management of powertrains including IC engines remains an important contribution. In this regard, engineers need accurate tools to understand heat-transfer in engine bays. This work presents a flexible test rig design to be used for the validation of CFD simulations of an underhood environment. The test rig and measurement equipment are introduced in detail with experimental data (and CAD) being available.A possible test scenario presented in this research is when an engine is subjected to heavy loads (i.e., constant uphill driving) and the vehicle is subsequently stopped. The experimental results are analysed and, furthermore, the data in terms of flow and temperature fields is compared against the results of the numerical simulations. This sort of comparison is the main usage scenario for the constructed rig, and it demonstrates the value of this facility for research. The rig's geometry and the experimental data being available can additionally be used to facilitate development and validation of various CAE methodology as well as simulation techniques.

Evaluation method with digital expert on the criticality of car-following scenarios for autonomous vehicles testing

Evaluation of autonomous vehicles is one of the major challenges before they can be released. Due to the advantages in efficiency, cost, and safety, scenario-based simulation methods have recently received great attention. Even so, as the complexity and uncertainty exist in the real driving environment, the scenarios that autonomous vehicles may encounter are infinite. Therefore, it is necessary to classify simulation scenarios according to their criticality. It contributes to accelerating the evaluation processes. This paper presents a novel criticality evaluation method, based on a proposed Digital Expert, for car-following autonomous driving. The Digital Expert acts as the evaluator to evaluate the criticality of scenarios depending on their driving performance. Driving performance refers to the achieved degree of driving intentions. Firstly, a Digital Expert is established as the evaluator for the criticality of the scenario using the inverse reinforcement learning method. Then, based on the fact that the intention of Digital Expert is to maximize its internal reward function, the reward function is used to evaluate driving performance. Finally, calculating the criticality of the car-following scenario according to the mapping relationship between driving performance and criticality. Using the driving data in the NGSIM data set, this paper generates two groups of simulated car-following scenarios and evaluates the criticalities of the two scenarios. The experimental results show that the proposed criticality evaluation method can reasonably evaluate the criticality of car-following scenarios.

Utility of microbial cell free DNA next-generation sequencing for diagnosis and management of infectious diseases

Microbial cell-free DNA (mcfDNA) sequencing is a promising tool to identify infectious pathogens when traditional methods fail to identify the causative agent. We performed a retrospective observational cohort study to evaluate clinical outcomes among pediatric and adult patients who underwent mcfDNA testing. 127 mcfDNA tests were reviewed from 112 patients. Baseline characteristics included 61 (54.5 %) adults, 52 (40.9 %) tests were from female patients, and 67 (52.8 %) tests were obtained from patients designated as immunocompromised. Of all tests obtained, 59 (46.4 %) were deemed clinically relevant. 41 (32.3 %) of tests also led to a change in antimicrobial management for the corresponding patient. No statistically significant association was ascertained between patient-specific factors and clinically relevant test results. Testing in certain clinical scenarios or high-risk settings may be useful, however further studies are needed to assess the cost-benefit of this approach.

Database of in-plume emission factors from open demilitarization of military ordnance

ABSTRACT A searchable database of emission factors from open burning, open detonation, and static firing of military ordnance and rocket motors has been developed and made available. Sampling and analytical results since 2010 have been compiled from seven campaigns in the USA and Canada at four different sites. Various ordnance types were used for multiple test scenarios varying location, soil covered/uncovered, metal-cased and uncased, and net explosive weight. Target compounds include, variously, particulate matter, metals, energetics, volatile organic compounds, and others. Data were primarily derived from unmanned aerial sampling methods using ordnance charge sizes and procedures representative of operational demilitarization operations. The database includes 1,212 emission factors for 39 different types of munitions and an array of pollutants where open burns accounted for 514 scenarios, static firing for 83, and open detonation for 614. The database will be of use for risk evaluations, environmental reporting requirements, and demilitarization operations.

Bi-level path tracking control of tractor semi-trailers by coordinated active front steering and differential braking

In recent years, autonomous tractor semi-trailers have been considered a promising solution for transportation on highways, ports, and large logistics centers to improve safety and efficiency. However, due to the complicated dynamics introduced by articulation structure, there are still challenges in achieving high-precision path tracking and stability control for tractor semi-trailers, especially in critical scenarios. In this work, a bi-level path tracking control scheme for the autonomous tractor semi-trailer is proposed. At the higher level, a robust model predictive controller coordinating active front steering and differential braking is devised for addressing path tracking, stability control and robustness for an autonomous tractor semi-trailer. At the lower level, incorporating a logic switching mechanism, the designed optimal braking torque distribution module and the PID-based longitudinal control module prioritize the implementation of differential braking and target speed tracking. Simulation results demonstrate that the proposed control strategy offers remarkable path tracking performance in three designed testing scenarios.

The Influence of Solar Irradiance and Temperature on The Pll-Synchronized Inverter Within Grid-Connected PV Systems

This study assesses the influence of solar irradiance and temperature on αβPLL synchronized inverters by investigating their intricate relationship within grid-connected PV systems. The intermittent nature of the DC side of these systems can significantly impact their performance. However, the extent of this impact remains uncertain when employing the stationary reference frame PLL (αβPLL) algorithm for synchronization with the utility grid. Employing simulation in MATLAB 2020a and a Model Based Design approach in the Simscape toolbox of SIMULINK, we conducted this investigation through two test scenarios: one with constant solar irradiance and varying temperature, and the other with varying solar irradiance and constant temperature. Our results indicate that fluctuations in solar irradiance and temperature have minimal effects on the output parameters of grid-connected PV systems when synchronized with the stationary reference frame PLL (αβPLL) algorithm. This conclusion is supported by the total harmonic distortion values, which all fall within the specified limits of IEEE Standard 929- 2000. These findings underscore the potential of αßPLL synchronization as a promising technique, capable of effectively synchronizing grid inverters even in the presence of DC input distortion. This proficiency in grid integration holds promise for enhancing the integration of renewable energy sources into the grid, thereby bolstering power availability for household distribution.

Ultra-sensitive and rapid detection of Salmonella enterica and Staphylococcus aureus to single-cell level by aptamer-functionalized carbon nanotube field-effect transistor biosensors

Foodborne diseases caused by Salmonella enterica (S. enterica) and Staphylococcus aureus (S. aureus) significantly impact public health, underscoring the imperative for highly sensitive, rapid, and accurate detection technologies to ensure food safety and prevent human diseases. Nanomaterials hold great promise in the development of high-sensitivity transistor biosensors. In this work, field-effect transistor (FET) comprising high-purity carbon nanotubes (CNTs) were fabricated and modified with corresponding nucleic acid aptamers for the high-affinity and selective capture of S. enterica and S. aureus. The aptamer-functionalized CNT-FET biosensor demonstrated ultra-sensitive and rapid detection of these foodborne pathogens. Experimental results indicated that the biosensor could detect S. enterica at a limit of detection (LOD) as low as 1 CFU in PBS buffer, and S. aureus at an LOD of 1.2 CFUs, achieving single-cell level detection accuracy with exceptional specificity. The biosensor exhibited a rapid response time, completing single detections within 200 s. Even in the presence of interference from six complex food matrices, the biosensor maintained its ultra-sensitive (3.1 CFUs) and rapid response (within 200 s) characteristics for both pathogens. The developed aptamer-functionalized CNT-FET biosensor demonstrates a capability for low-cost, ultra-sensitive, label-free, and rapid detection of low-abundance S. enterica and S. aureus in both buffer solutions and complex environments. This innovation holds significant potential for applying this detection technology to on-site rapid testing scenarios, offering a promising solution to the pressing need for efficient and reliable pathogen monitoring in various settings.

How would autonomous vehicles behave in real-world crash scenarios?

Autonomous Vehicles (AVs) have the potential to revolutionize transportation systems by enhancing traffic safety. Safety testing is undoubtedly a critical step for enabling large-scale deployment of AVs. High-risk scenarios are particularly important as they pose significant challenges and provide valuable insights into the driving capabilities of AVs. This study presents a novel approach to assess the safety of AVs using in-depth crash data, with a particular focus on real-world crash scenarios. First, based on the high-definition video recording of the whole process prior to the crash occurrences, 453 real-world crashes involving 596 passenger cars from China In-depth Mobility Safety Study-Traffic Accident (CIMSS-TA) database were reconstructed. Pertinent static and dynamic elements needed for the construction of the testing scenarios were extracted. Subsequently, 596 testing scenarios were created via each passenger car’s perspective within the simulation platform. Following this, each of the crash-involved passenger cars was replaced with Baidu Apollo, a famous automated driving system (ADS), for counterfactual simulation. Lastly, the safety performance of the AV was assessed using the simulation results. A logit model was utilized to identify the fifteen crucial scenario elements that have significant impacts on the test results. The findings demonstrated that the AV could avoid 363 real-world crashes, accounting for approximately 60.91% of the total, and effectively mitigated injuries in the remaining 233 unavoidable scenarios compared to a human driver. Moreover, the AV maintain a smoother speed in most of the scenarios. The common feature of these unavoidable scenarios is that the AV is in a passive state, and the crashes are not caused by the AV violating traffic rules, but rather caused by abnormal behavior exhibited by the human drivers. Additionally, seven specific scenarios have been identified wherein AVs are unable to avoid a crash. These findings demonstrate that, compared to human drivers, AVs can avoid crashes that are difficult for humans to avoid, thereby enhancing traffic safety.

Transferability of Machine Learning Models for Crop Classification in Remote Sensing Imagery Using a New Test Methodology: A Study on Phenological, Temporal, and Spatial Influences

Machine learning models are used to identify crops in satellite data, which achieve high classification accuracy but do not necessarily have a high degree of transferability to new regions. This paper investigates the use of machine learning models for crop classification using Sentinel-2 imagery. It proposes a new testing methodology that systematically analyzes the quality of the spatial transfer of trained models. In this study, the classification results of Random Forest (RF), eXtreme Gradient Boosting (XGBoost), Stochastic Gradient Descent (SGD), Multilayer Perceptron (MLP), Support Vector Machines (SVM), and a Majority Voting of all models and their spatial transferability are assessed. The proposed testing methodology comprises 18 test scenarios to investigate phenological, temporal, spatial, and quantitative (quantitative regarding available training data) influences. Results show that the model accuracies tend to decrease with increasing time due to the differences in phenological phases in different regions, with a combined F1-score of 82% (XGBoost) when trained on a single day, 72% (XGBoost) when trained on the half-season, and 61% when trained over the entire growing season (Majority Voting).

CIBSE TM54 energy projections III: A case study using dynamic simulation with detailed system modelling

CIBSE TM54 was recently revised and covers best practice methods to evaluate the operational energy use of buildings. TM54 is a guidance document on performance evaluation at every stage of the design and construction process, and during the occupied stage, to ensure that long-term operational performance is in line with the design intent. The main performance evaluation principles in TM54 are a step-by-step modelling approach and scenario testing, to improve the robustness of the design proposal calculations. The latest version brings an updated perspective to the modelling approaches, including dynamic simulation with Heating, Ventilation and Air Conditioning (HVAC) systems. It also incorporates more detailed guidance around risks, target setting, scenario testing and sensitivity analysis. A case study approach is used to explore some of the important aspects described in TM54. TM54 recommends three modelling approaches (aka implementation routes) that a project can follow depending on its scale and complexity: using quasi-steady state tools; using dynamic simulation with a template HVAC system; and using dynamic simulation with detailed HVAC system modelling. As part of a series of three, this case study provides an application of the third implementation route: dynamic simulation using detailed HVAC modelling.

Data-Driven Identification of Crane Dynamics Using Regularized Genetic Programming

The meaningful problem of improving crane safety, reliability, and efficiency is extensively studied in the literature and targeted via various model-based control approaches. In recent years, crane data-driven modeling has attracted much attention compared to physics-based models, particularly due to its potential in real-time crane control applications, specifically in model predictive control. This paper proposes grammar-guided genetic programming with sparse regression (G3P-SR) to identify the nonlinear dynamics of an underactuated crane system. G3P-SR uses grammars to bias the search space and produces a fixed number of candidate model terms, while a local search method based on an l0-regularized regression results in a sparse solution, thereby also reducing model complexity as well as reducing the probability of overfitting. Identification is performed on experimental data obtained from a laboratory-scale overhead crane. The proposed method is compared with multi-gene genetic programming (MGGP), NARX neural network, and Takagi-Sugeno fuzzy (TSF) ARX models in terms of model complexity, prediction accuracy, and sensitivity. The G3P-SR algorithm evolved a model with a maximum mean square error (MSE) of crane velocity and sway prediction of 1.1860 × 10−4 and 4.8531 × 10−4, respectively, in simulations for different testing data sets, showing better accuracy than the TSF ARX and MGGP models. Only the NARX neural network model with velocity and sway maximum MSEs of 1.4595 × 10−4 and 4.8571 × 10−4 achieves a similar accuracy or an even better one in some testing scenarios, but at the cost of increasing the total number of parameters to be estimated by over 300% and the number of output lags compared to the G3P-SR model. Moreover, the G3P-SR model is proven to be notably less sensitive, exhibiting the least deviation from the nominal trajectory for deviations in the payload mass by approximately a factor of 10.

Small-scale airblast testing for the assessment of multiple perimeter wall barriers on shock wave propagation

Assessment of the impact of structural systems on blast wave propagation has traditionally been explored using experimental, analytical, and/or numerical methods. Though numerical modeling techniques have grown in popularity because of their lower cost and high accuracy, experimental testing remains necessary for verifying these models. Issues of scale, equipment capacity, and the availability of research funding continue to limit full-scale testing of subassemblies or complete structures under blast loads. In addition, full-scale blast testing can be time-consuming, allowing only a handful of tests to be conducted. Small-scale airblast experiments offer an economic alternative to full-scale testing, in terms of material and labor requirements. Additionally, these small-scale experiments can be performed rapidly with repeatable results. The use of a novel reusable tabletop small-scale airblast experiment framework is presented for repeatable, cost-effective, quick turnaround testing of airblast scenarios. This novel setup also allows for reflective surfaces to be included as part of the investigation of the behavior of the shockwave-interaction with structures. The goal is to understand the behavior of the blast shockwave interacting with multiple barriers and the effect of pressure due to those barriers; therefore, the scaled structure remains rigid in the experimental and numerical analysis. Three different wall configurations were used to investigate how the presence of multiple barriers affects the shockwave and subsequent observed pressures around and behind the barriers. The explosives used were hemispherical and elevated spherical C4 charges. Pressure gauges were used to read pressures in front of, between, and behind the barriers on the tabletop. The airblast effects such as pressure and impulse, from the scaled experiments are presented and compared to the analytical predictions using a hydrocode model. It was found that multiple walls are measurably effective in reducing the pressure shockwave compared to no walls. The use of single and double walls reduced the pressure by 50% and 25%, respectively, compared to having no walls at the same scaled distance. The hydrocode model results were generally in agreement with the experimental data. The results can allow engineers and decision makers to understand the impact that properly distanced multiple barriers can have on protection from blast events.

Dual-camera off-axis holographic particle tracking velocimetry: Development and application to air-blast swirl spray measurement

Quantifying the droplet field near the atomizer exit poses a challenge due to its three-dimensional (3D), multiscale and turbulent characteristics. An optical measurement method named dual-camera high-resolution holographic particle tracking velocimetry (DCHR-HPTV) is proposed. This method enables the extraction of near-field spatial Sauter mean diameter (SMD) distribution and three-dimensional two-component (3D-2C) velocity field, from off-axis hologram pairs with a frame interval of 6 μs, recorded using two synchronized industrial cameras and pulsed lasers. The system achieves a resolution of 9344 × 7000 pixels with an individual pixel size (dpix) of 3.2 μm. The droplet size measurement range is from 10 μm to above 500 μm with an absolute error within 3 μm. The velocity measurement range is adjustable and is set to be 0 to 38.4 m/s in this study, with errors of 0.23 m/s and 0.15 m/s for horizontal and axial components, respectively. The method is applied to investigate a spray region of 29 mm × 20 mm with a depth of 35 mm (equivalent to 20.3 cm3) at the exit of an air-blast atomizer. The spatial distribution of circumferentially integrated SMD along radial and axial directions is obtained. Statistical analysis is performed on both spatial and quantity distributions of droplet 3D-2C velocities. Concurrently acquired droplet size and velocity in the central toroidal recirculation zone (CTRZ) indicate that both the increasing air pressure and enlarged size range lead to a weakened droplet backflow motion. This method, distinguished by its large field of view and high resolution for particle velocimetry, is suited for dynamic analysis of near-nozzle droplet fields and can be employed in various testing scenarios involving 3D motion of micron-sized particles within multiscale flow fields.

Deceiving Humans and Machines Alike: Search-based Test Input Generation for DNNs Using Variational Autoencoders

Due to the rapid adoption of Deep Neural Networks (DNNs) into larger software systems, testing of DNN-based systems has received much attention recently. While many different test adequacy criteria have been suggested, we lack effective test input generation techniques. Inputs such as images of real-world objects and scenes are not only expensive to collect but also difficult to randomly sample. Consequently, current testing techniques for DNNs tend to apply small local perturbations to existing inputs to generate new inputs. We propose SINVAD (Search-based Input space Navigation using Variational AutoencoDers), a way to sample from, and navigate over, a space of realistic inputs that resembles the true distribution in the training data. Our input space is constructed using Variational Autoencoders (VAEs), and navigated through their latent vector space. Our analysis shows that the VAE-based input space is well-aligned with human perception of what constitutes realistic inputs. Further, we show that this space can be effectively searched to achieve various testing scenarios, such as boundary testing of two different DNNs or analyzing class labels that are difficult for the given DNN to distinguish. Guidelines on how to design VAE architectures are presented as well. Our results have the potential to open the field to meaningful exploration through the space of highly structured images.

Industry Practices for Challenging Autonomous Driving Systems with Critical Scenarios

Testing autonomous driving systems for safety and reliability is essential, yet complex. A primary challenge is identifying relevant test scenarios, especially the critical ones that may expose hazards or harm to autonomous vehicles and other road users. Although numerous approaches and tools for critical scenario identification are proposed, the industry practices for selection, implementation, and evaluation of approaches, are not well understood. Therefore, we aim at exploring practical aspects of how autonomous driving systems are tested, particularly the identification and use of critical scenarios. We interviewed 13 practitioners from 7 companies in autonomous driving in Sweden. We used thematic modeling to analyse and synthesize the interview data. As a result, we present 9 themes of practices and 4 themes of challenges related to critical scenarios. Our analysis indicates there is little joint effort in the industry, despite every approach has its own limitations, and tools and platforms are lacking. To that end, we recommend the industry and academia combine different approaches, collaborate among different stakeholders, and continuously learn the field. The contributions of our study are exploration and synthesis of industry practices and related challenges for critical scenario identification and testing, and potential increase of industry relevance for future studies.

Enhancing Robustness of Surface Electromyography Pattern Recognition at Different Arm Positions for Transhumeral Amputees Using Deep Adversarial Inception Domain Adaptation

Pattern recognition in myoelectric control that relies on the myoelectric activity associated with arm motions is an effective control method applied to myoelectric prostheses. Individuals with transhumeral amputation face significant challenges in effectively controlling their prosthetics, as muscle activation varies with changes in arm positions, leading to a notable decrease in the accuracy of motion pattern recognition and consequently resulting in a high rejection rate of prosthetic devices. Therefore, to achieve high accuracy and arm position stability in upper-arm motion recognition, we propose a Deep Adversarial Inception Domain Adaptation (DAIDA) based on the Inception feature module to enhance the generalization ability of the model. Surface electromyography (sEMG) signals were collected from 10 healthy subjects and two transhumeral amputees while performing hand, wrist, and elbow motions at three arm positions. The recognition performance of different feature modules was compared, and ultimately, accurate recognition of upper-arm motions was achieved using the Inception C module with a recognition accuracy of 90.70% ± 9.27%. Subsequently, validation was performed using data from different arm positions as source and target domains, and the results showed that compared to the direct use of a convolutional neural network (CNN), the recognition accuracy on untrained arm positions increased by 75.71% (p < 0.05), with a recognition accuracy of 91.25% ± 6.59%. Similarly, in testing scenarios involving multiple arm positions, there was a significant improvement in recognition accuracy, with recognition accuracy exceeding 90% for both healthy subjects and transhumeral amputees.

Evaluation of DAMAGE Algorithm in Frontal Crashes.

With the current trend of including the evaluation of the risk of brain injuries in vehicle crashes due to rotational kinematics of the head, two injury criteria have been introduced since 2013 - BrIC and DAMAGE. BrIC was developed by NHTSA in 2013 and was suggested for inclusion in the US NCAP for frontal and side crashes. DAMAGE has been developed by UVa under the sponsorship of JAMA and JARI and has been accepted tentatively by the EuroNCAP. Although BrIC in US crash testing is known and reported, DAMAGE in tests of the US fleet is relatively unknown. The current paper will report on DAMAGE in NCAP-like tests and potential future frontal crash tests involving substantial rotation about the three axes of occupant heads. Distribution of DAMAGE of three-point belted occupants without airbags will also be discussed. Prediction of brain injury risks from the tests have been compared to the risks in the real world. Although DAMAGE correlates well with MPS in the human brain model across several test scenarios, the predicted risk of AIS2+ brain injuries are too high compared to real-world experience. The prediction of AIS4+ brain injury risk in lower velocity crashes is good, but too high in NCAP-like and high speed angular frontal crashes.

Development and Application of Control Concepts for Twin-Screw Wet Granulation in the ConsiGmaTM-25: Part 1 Granule Composition

Continuous manufacturing of pharmaceuticals offers several benefits, such as increased production efficiency, enhanced product quality control, and lower environmental footprint. To fully exploit these benefits, standard operation mode (production processes with no or minimal disturbance mitigation measures) should be supported by adopting novel quality-by-control (QbC) methodologies. The paper at hand is the first part of a study focused on developing QbC algorithms for optimizing twin-screw wet granulation in the industrial manufacturing line ConsiGmaTM-25, specifically addressing granule composition.This work relies on previously established process-analytical-technology (PAT) equipment for real-time monitoring of the granule composition, i.e., the active pharmaceutical ingredient (API) and liquid content in wet granules. The developed control platform integrates model-based process control algorithms that aim to keep the API- and liquid content at target values through real-time adjustments of the process parameters. Furthermore, the platform integrates a digital operator assistant, which aims to detect and classify granulation disturbances and provides messages and instructions for the plant operator.The present manuscript systematically outlines all design steps from the development phase in the simulation environment to the final real system application and validation. The control platform’s performance is demonstrated through selected test scenarios on the ConsiGmaTM-25 manufacturing line. The obtained results indicate improved disturbance robustness and an increase in intermediate/final product quality (compared to conventional operating modes): The process control algorithms successfully maintained the API- and liquid content at target values despite process disturbances. Furthermore, realistic disturbances (feeder, pump, and material) were accurately detected and classified by the digital assistant algorithm. The information was provided through a user interface, offering real-time support for plant personnel.

Virtual reality testing of emergency scenarios could improve student reactions in the future

Artificial intelligence is infiltrating every sector of college life, from admissions papers to now, research on how virtual reality simulations can improve campus safety. Emergency Management Science and Technology has published a paper entitled “Experimental Research on College Students’ Emergency Ability and Its Influencing Factors in Virtual Emergency Situations” that examines how AI technology, such as virtual reality simulations, can improve understanding of students’ ability to respond to emergency situations.