Simulated Task Research Articles

VTSIM: Attention‐Based Recurrent Neural Network for Intersection Vehicle Trajectory Simulation

ABSTRACTSimulating vehicle trajectories at intersections is one of the challenging tasks in traffic simulation. Existing methods are often ineffective due to the complexity and diversity of lane topologies at intersections, as well as the numerous interactions affecting vehicle motion. To address this issue, we propose a deep learning based vehicle trajectory simulation method. First, we employ a vectorized representation to uniformly extract features from traffic elements such as pedestrians, vehicles, and lanes. By fusing all factors that influence vehicle motion, this representation makes our method suitable for a variety of intersections. Second, we propose a deep learning model, which has an attention network to dynamically extract features from the surrounding environment of the vehicles. To address the issue of vehicles continuously entering and exiting the simulation scene, we employ an asynchronous recurrent neural network for the extraction of temporal features. Comparative evaluations against existing rule‐based and deep learning‐based methods demonstrate our model's superior simulation accuracy. Furthermore, experimental validation on public datasets demonstrates that our model can simulate vehicle trajectories among the urban intersections with different topologies including those not present in the training dataset.

Analysing Virtual Labs Through Integrated Multi-Channel Eye-Tracking Technology: A Proposal for an Explanatory Fit Model

This study deals with an analysis of the cognitive load indicators produced in virtual simulation tasks through supervised and unsupervised machine learning techniques. The objectives were (1) to identify the most important cognitive load indicators through the use of supervised and unsupervised machine learning techniques; (2) to study which type of task presentation was most effective at reducing the task’s intrinsic load and increasing its germane load; and (3) to propose an explanatory model and find its fit indicators. We worked with a sample of 48 health sciences and biomedical engineering students from the University of Burgos (Spain). The results indicate that being able to see the task before performing it increases the germane load and decreases the intrinsic load. Similarly, allowing students a choice of presentation channel for the task respects how they process information. In addition, indicators of cognitive load were found to be grouped into components of position, speed, psychogalvanic response, and skin conductance. An explanatory model was proposed and obtained acceptable fit indicators.

The Impact of Soundscapes on Healthcare Teams: A Literature Review

Healthcare teams often work in complex systems where soundscapes include numerous noise sources and levels which could impact teamwork. While studies have analyzed the impact of sound on patients, articles describing clinician and clinical team experience are relatively sparse. The purpose of this literature review was to determine what is currently known about soundscapes and their impact on teamwork and team performance in hospital-based healthcare settings. Eleven studies met the inclusion criteria. The Input-Process-Output framework and SEIPS 2.0 model guided our review and categorization of the included studies. The work environments studied included the operating room (OR), perioperative area, and a simulation. Noise input was grouped by existing noise, music or controlled sound conditions, and communication wearables during clinical or simulated tasks. Nine of the 11 articles studied the impact sound environment on team communication and three articles measured other team processes. The findings from this review assessed both existing and experimental noise conditions discovering associations with team performance processes and outcomes. Overall, previous studies have found that noise can impact individuals and elements of teamwork, especially communication. Future research is needed to develop best practices and innovative solutions supporting a positive soundscape for teamwork.

FastFlow: GPU Acceleration of Flow and Depression Routing for Landscape Simulation

AbstractTerrain analysis plays an important role in computer graphics, hydrology and geomorphology. In particular, analyzing the path of material flow over a terrain with consideration of local depressions is a precursor to many further tasks in erosion, river formation, and plant ecosystem simulation. For example, fluvial erosion simulation used in terrain modeling computes water discharge to repeatedly locate erosion channels for soil removal and transport. Despite its significance, traditional methods face performance constraints, limiting their broader applicability.In this paper, we propose a novel GPU flow routing algorithm that computes the water discharge in 𝒪(log n) iterations for a terrain with n vertices (assuming n processors). We also provide a depression routing algorithm to route the water out of local minima formed by depressions in the terrain, which converges in 𝒪(log2 n) iterations. Our implementation of these algorithms leads to a 5× speedup for flow routing and 34 × to 52 × speedup for depression routing compared to previous work on a 10242 terrain, enabling interactive control of terrain simulation.

Increasing transparency of computer-aided detection impairs decision-making in visual search.

Recent developments in artificial intelligence (AI) have led to changes in healthcare. Government and regulatory bodies have advocated the need for transparency in AI systems with recommendations to provide users with more details about AI accuracy and how AI systems work. However, increased transparency could lead to negative outcomes if humans become overreliant on the technology. This study investigated how changes in AI transparency affected human decision-making in a medical-screening visual search task. Transparency was manipulated by either giving or withholding knowledge about the accuracy of an 'AI system'. We tested performance in seven simulated lab mammography tasks, in which observers searched for a cancer which could be correctly or incorrectly flagged by computer-aided detection (CAD) 'AI prompts'. Across tasks, the CAD systems varied in accuracy. In the 'transparent' condition, participants were told the accuracy of the CAD system, in the 'not transparent' condition, they were not. The results showed that increasing CAD transparency impaired task performance, producing an increase in false alarms, decreased sensitivity, an increase in recall rate, and a decrease in positive predictive value. Along with increasing investment in AI, this research shows that it is important to investigate how transparency of AI systems affect human decision-making. Increased transparency may lead to overtrust in AI systems, which can impact clinical outcomes.

Thermal hydraulic analysis of a high-temperature gas reactor steam generator after loss of feed water accidents

The helical coil steam generator is widely employed in the energy conversion process of high-temperature gas-cooled reactors for its high thermal efficiency in producing superheated steam within the helical tubes. These tubes necessitate materials specifically designed to endure high temperatures, prevent ruptures, and ensure durability under various operational conditions. This study aims to identify the maximum temperatures arising from potential transients in the secondary system and to propose immediate safety measures for minimizing associated risks. The RELAP5/MOD3.4 code was used to simulate the behavior of the next generation nuclear plant steam generator's conceptual design using steady-state conditions. Following the validation of the model, the established steady-state conditions were utilized to simulate accident scenarios, including the feed water line break and the loss of feed water flow to the steam generator. The transient scenarios assumptions include closed flap valves and retained hot helium in the shell side. The simulation tasks were conducted both with and without activating the depressurization system, in order to assess its effect on the temperature of tubes on the wall side. The analysis results indicate that tube wall temperatures can reach 720 °C at the steam generator outlet region and 620 °C at the weld region. The immediate activation of the depressurization system with a controlled relief valve can effectively reduce these temperatures by 239 °C in the steam generator outlet and by 133 °C in the weld region. This also lowers the steam generator's secondary side pressure. As a result, an upgrade and enhancement of operational procedures is straightforward.

Time on task effects during interactive visual search.

There is a major shift taking place in airports across the globe, changing from 2D dual-view X-ray screening to 3D computed tomography (CT) screening. 3D CT screening is believed to improve target detection since it enables screeners to interact with images of passenger baggage (i.e., rotating and zooming into the displays). The change in screening technology is moving what was once a purely visual search task to an interactive search task. Here, we conducted two experiments with a large sample size during February of 2023 (695 participants) to examine (a) changes in search performance between a simulated dual-view and simulated interactive search task and (b) the effects of time on task upon performance. Consistent with past research, we found that interactive search, when compared with dual-view search, produced higher response accuracy rates coupled with increased reaction times (RTs). However, while we found effects of time on task (RTs reduced, and participants became more likely to respond "absent" as the experiments progressed), there was no evidence that these effects differed across simulated dual-view and simulated interactive searches. The results are discussed in relation to benefits of interactive search for supporting target detection by airport screeners. (PsycInfo Database Record (c) 2024 APA, all rights reserved).

Learning to Play Guitar with Robotic Hands

AbstractPlaying the guitar is a dexterous human skill that poses significant challenges in computer graphics and robotics due to the precision required in finger positioning and coordination between hands. Current methods often rely on motion capture data to replicate specific guitar playing segments, which restricts the range of performances and demands intricate post‐processing. In this paper, we introduce a novel reinforcement learning model that can play the guitar using robotic hands, without the need for motion capture datasets, from input tablatures. To achieve this, we divide the simulation task for playing guitar into three stages. (a): for an input tablature, we first generate corresponding fingerings that align with human habits. (b): based on the generated fingerings as the guidance, we train a neural network for controlling the fingers of the left hand using deep reinforcement learning, and (c): we generate plucking movements for the right hand based on inverse kinematics according to the tablature. We evaluate our method by employing precision, recall, and F1 scores as quantitative metrics to thoroughly assess its performance in playing musical notes. In addition, we conduct qualitative analysis through user studies to evaluate the visual and auditory effects of guitar performance. The results demonstrate that our model excels in playing most moderately difficult and easier musical pieces, accurately playing nearly all notes.

Investigating the effect of template head models on Event-Related Potential source localization: a simulation and real-data study.

Event-Related Potentials (ERPs) are valuable for studying brain activity with millisecond-level temporal resolution. While the temporal resolution of this technique is excellent, the spatial resolution is limited. Source localization aims to identify the brain regions generating the EEG data, thus increasing the spatial resolution, but its accuracy depends heavily on the head model used. This study compares the performance of subject-specific and template-based head models in both simulated and real-world ERP localization tasks. Simulated data mimicking realistic ERPs was created to evaluate the impact of head model choice systematically, after which subject-specific and template-based head models were used for the reconstruction of the data. The different modeling approaches were also applied to a face recognition dataset. The results indicate that the template models capture the simulated activity less accurately, producing more spurious sources and identifying less true sources correctly. Furthermore, the results show that while creating more accurate and detailed head models is beneficial for the localization accuracy when using subject-specific head models, this is less the case for template head models. The main N170 source of the face recognition dataset was correctly localized to the fusiform gyrus, a known face processing area, using the subject-specific models. Apart from the fusiform gyrus, the template models also reconstructed several other sources, illustrating the localization inaccuracies. While template models allow researchers to investigate the neural generators of ERP components when no subject-specific MRIs are available, it could lead to misinterpretations. Therefore, it is important to consider a priori knowledge and hypotheses when interpreting results obtained with template head models, acknowledging potential localization errors.

Interventions to mitigate EHR and documentation burden in health professions trainees: A scoping review.

Health professions trainees (trainees) are unique as they learn a chosen field while working within electronic health records (EHR). Efforts to mitigate EHR burden have been described for the experienced health professional (HP), but less is understood for trainees. EHR or documentation burden (EHR burden) affects trainees, although not all trainees use EHRs, and use may differ for experienced HPs. To develop a model of how interventions to mitigate EHR burden fit within the trainee EHR workflow: the Trainee EHR Burden Model. 1) Examine trainee experiences of interventions aimed at mitigating EHR burden(scoping review). 2) Adapt an existing workflow model by mapping included studies(concept clarification). We conducted a 4-database scoping review applying PRISMA-ScR guidance, examining scholarly, peer-reviewed studies that measured trainee experience of interventions to mitigate EHR burden. We conducted a concept clarification categorizing, then mapping studies to workflow model elements. We adapted the model to intervenable points for trainee EHR burden. We identified 11 studies examining interventions to mitigate EHR burden that measured trainee experience. Interventions included: curriculum, training, coaching on the existing EHR for both simulated or live tasks; evaluating scribes' impact; adding devices or technology tailored to rounds; team communication or data presentation at end-of shift handoffs. Interventions had varying effects on EHR burden, most commonly measured through surveys, and less commonly, direct observation. Most studies had limited sample sizes, focused on inpatient settings, and physician trainees. Few studies measured trainee perspectives of interventions aiming to mitigate EHR burden. Many studies applied quasi-experimental designs and focused on inpatient settings. The Trainee EHR Burden Model, adapted from an existing workflow model, offers a starting place to situate points of intervention in trainee workflow. Further research is needed to design new interventions targeting stages of HP trainee workflow, in a range of clinical settings.

Multimodal Dataset Construction and Validation for Driving-Related Anger: A Wearable Physiological Conduction and Vehicle Driving Data Approach

Anger impairs a driver’s control and risk assessment abilities, heightening traffic accident risks. Constructing a multimodal dataset during driving tasks is crucial for accurate anger recognition. This study developed a multimodal physiological -vehicle driving dataset (DPV-MFD) based on drivers’ self-reported anger during simulated driving tasks. In Experiment 1, responses from 624 participants to anger-inducing videos and driving scenarios were collected via questionnaires to select appropriate materials. In Experiments 2 and 3, multimodal dynamic data and self-reported SAM emotion ratings were collected during simulated and real-vehicle tasks, capturing physiological and vehicle responses in neutral and anger states. Spearman’s correlation coefficient analysis validated the DPV-MFD’s effectiveness and explored the relationships between multimodal data and emotional dimensions. The CNN-LSTM deep learning network was used to assess the emotion recognition performance of the DPV-MFD across different time windows, and its applicability in real-world driving scenarios was validated. Compared to using EEG data alone, integrating multimodal data significantly improved anger recognition accuracy, with accuracy and F1 scores rising by 4.49% and 9.14%, respectively. Additionally, real-vehicle data closely matched simulated data, confirming the dataset’s effectiveness for real-world applications. This research is pivotal for advancing emotion-aware human–machine- interaction and intelligent transportation systems.

Contact-implicit Model Predictive Control: Controlling diverse quadruped motions without pre-planned contact modes or trajectories

This paper presents a contact-implicit model predictive control (MPC) framework for the real-time discovery of multi-contact motions, without predefined contact mode sequences or foothold positions. This approach utilizes the contact-implicit differential dynamic programming (DDP) framework, merging the hard contact model with a linear complementarity constraint. We propose the analytical gradient of the contact impulse based on relaxed complementarity constraints to further the exploration of a variety of contact modes. By leveraging a hard contact model-based simulation and computation of search direction through a smooth gradient, our methodology identifies dynamically feasible state trajectories, control inputs, and contact forces while simultaneously unveiling new contact mode sequences. However, the broadened scope of contact modes does not always ensure real-world applicability. Recognizing this, we implemented differentiable cost terms to guide foot trajectories and make gait patterns. Furthermore, to address the challenge of unstable initial roll-outs in an MPC setting, we employ the multiple shooting variant of DDP. The efficacy of the proposed framework is validated through simulations and real-world demonstrations using a 45 kg HOUND quadruped robot, performing various tasks in simulation and showcasing actual experiments involving a forward trot and a front-leg rearing motion.

Limb Loading Asymmetry During Simulated Daily Functional Tasks

Limb Loading Asymmetry During Simulated Daily Functional Tasks

ВИКОРИСТАННЯ ВІРТУАЛЬНОЇ ЛАБОРАТОРІЇ LABSTER ДЛЯ ВИВЧЕННЯ ХІМІЇ В ТЕХНІЧНОМУ УНІВЕРСИТЕТІ

Immersive virtual labs represent a digital paradigm in education that meets the needs and preferences of today’s students. The main advantage is the ability to conduct laboratory and practical work in the physical absence of educational equipment or the inability to use it, which is especially important in the context of martial law restrictions in Ukraine. The article analyzes the experience of using the Labster web platform, which provides virtual laboratory simulations of natural sciences. The virtual laboratory was used in the educational process of Lutsk National Technical University when teaching chemical disciplines in the autumn semester of the 2023-2024 academic year. The virtual simulation tasks "Introduction to Groups of the Periodic Table" were offered to students as an alternative option for extracurricular independent work. 146 1st year students were registered, of which 99 (67.8%) completed the test, and 47 (32.2 %) partially passed it. The results of the surveys are presented, the first was conducted immediately after work, the second was a questionnaire on the comprehensibility of the content and the perception of the usefulness of Labster modeling – about three weeks after the completion of the Labster simulation. Based on the analysis of the answers of students, the main advantages of using a virtual laboratory are established - gaining new educational experience, improving the knowledge and digital skills of students. Virtual simulations increased students' engagement and confidence. The advantage of working in a virtual laboratory is personalized learning. The main obstacles to using Labster are highlighted: low level of English proficiency (Labster does not involve the use of Ukrainian content) and insufficient digital skills to navigate in the virtual space. It is recommended to use virtual simulations not as a substitute for classroom practical exercises, but as a modern tool to supplement them.

Features of the formation of professional competence of a future foreign language teacher through simulation games

The article emphasizes the importance of using the simulation-game method for the formation of professional competence of future foreign language teachers and describes its effective developmental impact. The principles and methods of the simulation game that contribute to the professional growth of students are considered. The authors of the article emphasize the necessity of professional development of future foreign language teachers and reveal the potential of simulation tasks. It is noted that learning through simulation game allows to achieve two goals at the same time. In addition, the authors note that the use of simulation games gives the learning process an interesting and practically oriented character, contributes to the development of students' universal competencies such as cooperation and critical thinking, which increases their competitiveness in the labor market. In the article the authors describe in detail the main stages of the simulation game method and offer a number of optimal linguistic and content tasks for the development of professional competencies. Based on the above, the authors conclude that it is necessary to introduce the simulation game as an effective method of teaching foreign languages in higher education institutions when training future teachers. The purpose of this article is to analyze the potential of using imitation tasks to improve the effectiveness of foreign language teaching. The main objective of the article is to describe the rules and principles of the method of imitation games, as well as to formulate the didactic foundations for the use of such games in the training of future foreign language teachers. On the basis of the studied theoretical sources and their own experience of using imitation games, the authors offer a set of tasks for teaching a foreign language that meets the requirements of language teaching methodology.

Shadow Simulation of Quantum Processes.

We introduce the task of shadow process simulation, where the goal is to simulate the estimation of the expectation values of arbitrary quantum observables at the output of a target physical process. When the sender and receiver share random bits or other no-signaling resources, we show that the performance of shadow process simulation exceeds that of conventional process simulation protocols in a variety of scenarios including communication, noise simulation, and data compression. Remarkably, we find that there exist scenarios where shadow simulation provides increased statistical accuracy without any increase in the number of required samples.

Cooperation objective evaluation in aviation: validation and comparison of two novel approaches in simulated environment.

In operational environments, human interaction and cooperation between individuals are critical to efficiency and safety. These states are influenced by individuals' cognitive and emotional states. Human factor research aims to objectively quantify these states to prevent human error and maintain constant performances, particularly in high-risk settings such as aviation, where human error and performance account for a significant portion of accidents. Thus, this study aimed to evaluate and validate two novel methods for assessing the degree of cooperation among professional pilots engaged in real-flight simulation tasks. In addition, the study aimed to assess the ability of the proposed metrics to differentiate between the expertise levels of operating crews based on their levels of cooperation. Eight crews were involved in the experiments, consisting of four crews of Unexperienced pilots and four crews of Experienced pilots. An expert trainer, simulating air traffic management communication on one side and acting as a subject matter expert on the other, provided external evaluations of the pilots' mental states during the simulation. The two novel approaches introduced in this study were formulated based on circular correlation and mutual information techniques. The findings demonstrated the possibility of quantifying cooperation levels among pilots during realistic flight simulations. In addition, cooperation time is found to be significantly higher (p < 0.05) among Experienced pilots compared to Unexperienced ones. Furthermore, these preliminary results exhibited significant correlations (p < 0.05) with subjective and behavioral measures collected every 30 s during the task, confirming their reliability.

The Effect of External Distractions on Simulated Laparoscopic Performance.

Background: Surgeons are exposed to unavoidable distractions while operating. Distractions can cause stress, and stress can impair cognition and motor skills to the detriment of surgeon performance. This study assessed the impact of distractions on surgeon stress levels and surgeon performance during simulated laparoscopic tasks. Methods: Twelve surgical trainees completed a peg-thread transfer task three times on a laparoscopic simulator in a neutral environment. Six trainees then completed the task three more times in an environment overlain with distractions commonly found in the operating theatre. Six others completed three more tasks in a neutral environment. Stress was measured by recording heart rate and by assessing responses to the NASA Task Load Index. Performance was measured using instrument tracking metrics and time to complete the task. Results: The distracted participants reported significantly higher effort, frustration, and physical demand than the neutral group, as measured by the NASA Task Load Index, (P = .001, .031, and .044, respectively). The neutral group completed their final task significantly faster compared with baseline (P = .049), while the distracted group failed to show this improvement. The distracted group showed higher hand discordance, suggesting reduced ambidexterity. Conclusion: Distraction negatively impacted some aspects of performance and resulted in subjective increased stress. In future, simulation may have a role in "stress inoculation," enabling surgeons to maintain performance, despite distractions.

A Novel Topology Adaptation Strategy for Dynamic Sparse Training in Deep Reinforcement Learning.

Deep reinforcement learning (DRL) has been widely adopted in various applications, yet it faces practical limitations due to high storage and computational demands. Dynamic sparse training (DST) has recently emerged as a prominent approach to reduce these demands during training and inference phases, but existing DST methods achieve high sparsity levels by sacrificing policy performance as they rely on the absolute magnitude of connections for pruning and randomly generating connections. Addressing this, our study presents a generic method that can be seamlessly integrated into existing DST methods in DRL to enhance their policy performance while preserving their sparsity levels. Specifically, we develop a novel method for calculating the importance of connections within the model. Subsequently, we dynamically adjust the sparse network topology by dropping existing connections and introducing new connections based on their respective importance values. Through validation on eight widely used simulation tasks, our method improves two state-of-the-art (SOTA) DST approaches by up to 70% in episode return and average return across all episodes under various sparsity levels.

Bilateral Proxy Federated Domain Generalization for Privacy-preserving Medical Image Diagnosis.

Contemporary domain generalization methods have demonstrated effectiveness in aiding the generalized diagnosis of medical images with multi-source data by joint optimization. However, the centralized training paradigm employed by these approaches becomes infeasible when data are non-shared across domains due to the high privacy of medical data. Despite attempts by existing federated domain generalization methods to address this issue, the simultaneous attainment of strict privacy protection and a satisfactory level of generalization ability on out-of-distribution data remains a persistent challenge. In this paper, to tackle this challenging problem, we propose a novel approach called the Bilateral Proxy Framework (BPF). The BPF leverages the client-side proxies to facilitate the strict privacy-preserving communications with the server and ensure smoother and more stable convergences of local models through mutual distillation. Meanwhile, the server-side proxy adopts a distance-based strategy and a parameter moving average scheme, which enhances the stability and robustness of the global model, particularly by averting abrupt parameter changes that could result in fluctuations or overfitting. Through these advancements, our framework strives to enhance the generalization capability of the global model, enabling more accurate and reliable medical image diagnosis in federated settings. The effectiveness of our method is demonstrated with superior performance over state-of-the-arts on both simulated and real-world distribution medical image diagnosis tasks.