Simulated Training Environment Research Articles

Stepping into the virtual realm: Examining the utility of non-immersive VR on medical residents' self-efficacy, performance, and satisfaction

Central Venous Catheterization (CVC) is conducted in more than 5 million patients annually in the United States. Currently, CVC theoretical knowledge is typically taught with didactic lectures with minimal assessment of knowledge before simulation training and clinical environment. To assess CVC theoretical knowledge, virtual reality (VR) can develop residents’ surgical skills and can provide feedback on performance. While all types of VR can be used to assess improvements in residents’ knowledge prior to simulation training, few studies have compared the impact of non-immersive VR on improving resident knowledge. The current study was developed to identify the utility of a non-immersive CathSim VR on improvements in resident CVC theoretical knowledge, self-efficacy, and satisfaction when compared to a traditional multiple-choice assessment This was completed through an empirical investigation with 34 medical residents. The results showed that when compared to a traditional multiple-choice assessment, the non-immersive CathSim VR assessment led to improvements in self-efficacy and potentially better learning experience. Meanwhile, results also showed that there were no differences in assessment score, number of attempts, and overall satisfaction. Thus, we can conclude that non-immersive VR has the potential to be more effective than traditional multiple-choice test in improving self-efficacy and is as effective for residents’ assessment score, number of attempts, and overall satisfaction.

Virtual reality to provide caregiver skill development and problem solving

Background:Caring for persons with dementia (PWD) leads to disproportionate vulnerability to physical, mental, and social adverse health consequences among caregivers (CGs). The VR-SIMS CARERS Initiative aims to engage Knowledge Users (KUs), older adults and community stakeholders in the co-design of a Virtual Reality (VR) simulation training environment for dementia caregivers, and to explore end-user’s perspectives, design and implementation challenges and opportunities (e.g. digital literacy, technology readiness, VR acceptability), to ensure that the resulting “Minimally Viable Prototype” is clinically efficacious, scalable and sustainable.Objectives & Methodology:The specific objectives of this study are to: 1.employ a co-design approach to develop and validate an immersive VR simulation training environment for CGs to be in touch with realities of caregiving, practice communications and behavioural management of PWD based on the well-established CARERS Program;2.to evaluate feasibility, acceptability, tolerability informed by VR-CORE Framework and Hybrid development-implementation design, and to explore issues around implementation of the VR simulation training platform; and3.to conduct pilot testing to examine a) initial clinical efficacy of VR-based CG training in improving quality of relationship with PWD, competence, resilience, and reducing depression and stress in dementia CGs and its b) readiness for implementation in the community.Anticipated Outcomes:VR-SIMS CARERS innovation is intended to be an accessible, scalable and sustainable VR simulation training platform that will support CGs in the practice and acquisition of essential dementia caregiving skills, enhancing their caregiving competence and resilience. Training CGs to recognize and manage stressors can lower their risk of overall mental health decline.

Reinforcement learning-based stable jump control method for asteroid-exploration quadruped robots

Unlike the spherical gravitational field of planets and other large solar system bodies, the gravitational field of asteroids is irregular and weak. It is challenging for a planetary rover to obtain sufficient traction forces in this environment. However, this gravitational environment is suitable for legged robots with jumping ability, but it also imposes higher demands on control methods. Therefore, this study aimed to address the problem of jump control method for asteroid-exploration quadruped robots. As the robot jumps off the surface of an asteroid, it would fly for a certain amount of time because of the low gravitational acceleration. The prolonged flight phase underscores the significance of the robot's take off and attitude control. A model-free stable jumping control method was devised in this study. This method can satisfy the control requirements for takeoff, attitude adjustment, and soft landing by using end-to-end multi-agent reinforcement learning (MARL). MARL is more advantageous than single-agent reinforcement learning in dealing with composite motion control problems under similar observation conditions. A simulated training environment was established, incorporating models of the gravitational field, task partitioning for jumping, and design of reward functions, including jump trajectory planning. The efficacy of the proposed jump control method for a quadruped robot was successfully demonstrated in the gravitational environment of an irregular rod-shaped asteroid, 216 Kleopatra.

The Effects of Reflective Pauses on Performance in Simulation Training.

The reflective pause, taking a pause during performance to reflect, is an important practice in simulation-based learning. However, for novice learners, it is a highly complex self-regulatory skill that cannot stand alone without guidance. Using educational theories, we propose how to design cognitive and metacognitive aids to guide learners with the reflective pause and investigate its effects on performance in a simulation training environment. These effects are examined in four aspects of performance: cognitive load, primary performance, secondary performance, and encapsulation. Medical students ( N = 72) performed tasks in simulation training for emergency medicine, under 2 conditions: reflection condition ( n = 36) where reflection was prompted and guided, and control condition ( n = 36) without such reflection. The effects of reflective pauses emerged for 2 aspects of performance: cognitive load decreased and secondary performance improved. However, primary performance and encapsulation did not show significant difference. The results demonstrate that reflective pauses with cognitive and metacognitive aids implemented can enhance some aspects of performance. We suggest that to secure these effects, feedback during reflection and an adaptation period should be provided.

Evaluation of intracranial stenting in a simulated training and assessment environment for neuroendovascular procedures.

Given the inherent complexity of neurointerventional procedures and the associated risks of ionizing radiation exposure, it is crucial to prioritize ongoing training and improve safety protocols. The aim of this study is to assess a training and evaluation in-vitro environment using a vascular model of M1 stenosis, within a clinical angiography suite, without relying on animal models or X-ray radiation. Using a transparent model replicating M1 stenosis, we conducted intracranial stenting procedures with four different setups (Gateway & Wingspan, Gateway & Enterprise, Neurospeed & Acclino, and Pharos Vitesse). A video camera was integrated with the angiography system's monitor for real-time visualization, while a foot switch was employed to simulate live fluoroscopy. Three neuroradiologists with varying levels of expertise performed each procedure for three times. The total duration of fluoroscopy as well as the time from passing the stenosis with the wire to completion of the procedure were recorded using a dedicated software designed for this experimental setup. Compared to the Gateway & Wingspan procedure, the total fluoroscopy time reduced significantly with the Gateway & Enterprise, Neurospeed & Acclino, and Pharos Vitesse procedures by 51.56 s, 111.33 s, and 144.89 s, respectively (p < 0.001). Additionally, physicians with under 2 years and over 5 years of experience reduced FT by 62.83 s and 106.42 s, respectively, (p < 0.001), compared to a novice physician. Similar trends were noted for the time of wire distal to stenosis, with significant reductions for Neurospeed & Acclino and Pharos Vitesse compared to both Gateway & Wingspan as well as Gateway & Enterprise (all p < 0.001). Procedures requiring wire exchange maneuvers exhibited nearly twice the fluoroscopy time in comparison to balloon-mounted stenting or stent-placement via PTA balloon catheters. The more experienced neuroradiologist demonstrated significantly quicker performance in line with expectations in a real-life clinical setting, when compared to the less experienced interventionalist. This in-vitro setup allowed the evaluation of alternative technical approaches and differences in experience of operators without the use of animal models or X-ray. The setup combines advantages of simulators and silicone vessel models in a realistic working environment.

COST-WINNERS: COST reduction WIth Neural NEtworks-based augmented Random Search for simultaneous thermal and electrical energy storage control

The combination of local renewable energy production, dynamic loads, and multiple energy storage systems with different dynamics requires sophisticated control systems to maximize the energy cost efficiency of the combined energy system. Battery and thermal energy storage systems can be combined to increase the local use of on-site renewable energy, reduce peak power demand, and exploit time-of-use energy pricing. In this paper, we focus on how the augmented random search algorithm and artificial neural networks can be used together to solve an energy cost optimization problem involving the control of a battery energy storage system and a thermal energy storage system at the same time in a smart warehouse. As part of this work, a simulated training environment made using the data from the smart warehouse’s operations. In addition to the energy storage systems, the warehouse energy system has integrated a large roof mounted photovoltaic power plant and an industrial-scale cooling system.The developed solution is able to minimize the energy costs by modulating both energy systems, depending on the situation. Additionally, when it is tested against the state-of-the-art solutions, our developed solution at worst matches performance when the alternative algorithm is allowed to increase training time by a factor of nearly three. On average, our presented solution doubles the performance of the benchmark algorithm with much less computational resource expenditure.

Safety Aspects of Supporting Apron Controllers with Automatic Speech Recognition and Understanding Integrated into an Advanced Surface Movement Guidance and Control System

The information air traffic controllers (ATCos) communicate via radio telephony is valuable for digital assistants to provide additional safety. Yet, ATCos have to enter this information manually. Assistant-based speech recognition (ABSR) has proven to be a lightweight technology that automatically extracts and successfully feeds the content of ATC communication into digital systems without additional human effort. This article explains how ABSR can be integrated into an advanced surface movement guidance and control system (A-SMGCS). The described validations were performed in the complex apron simulation training environment of Frankfurt Airport with 14 apron controllers in a human-in-the-loop simulation in summer 2022. The integration significantly reduces the workload of controllers and increases safety as well as overall performance. Based on a word error rate of 3.1%, the command recognition rate was 91.8% with a callsign recognition rate of 97.4%. This performance was enabled by the integration of A-SMGCS and ABSR: the command recognition rate improves by more than 15% absolute by considering A-SMGCS data in ABSR.

Naturalistic observations of multiteam interaction networks: Implications for cognition in crisis management teams

Interaction has been recognised as an essential lens to understand how cognition is formed in a complex adaptive team such as a multidisciplinary crisis management team (CMT). However, little is known about how interactions within and across CMTs give rise to the multi-team system’s overall cognitive functioning, which is essential to avoid breakdowns in coordination. To address this gap, we characterise and compare the component CMTs’ role-as-intended (RAI) and role-as-observed (RAO) in adapting to the complexity of managing informational needs. To characterise RAI, we conducted semi-structured interviews with subject matter experts and then made a qualitative synthesis using a thematic analysis method. To characterise RAO, we observed multiteam interaction networks in real-time at a simulated training environment and then analysed the component CMTs’ relative importance using node centrality measures. The resulting inconsistencies between RAI and RAO imply the need to investigate cognition in multiple CMTs through the lens of interaction. Practitioner summary: When a disaster occurs, multidisciplinary CMTs are expected to serve their roles as described in written or verbal guidelines. However, according to our naturalistic observations of multiteam interaction networks, such descriptions may be (necessary but) insufficient for designing, training, and evaluating CMTs in the complexity of managing informational needs together.

How Hard Is It Really? Assessing Game-Task Difficulty Through Real-Time Measures of Performance and Cognitive Load

Background Serious and entertainment game designers strive to create engaging, immersive, and often, challenging games. This task involves modifying game mechanics or environments to create experiences with differing levels of challenge to meet player skill. The balance between different game mechanics or environments, and the differing levels of challenge they pose, is typically understood through iterative testing. Balance and challenge becomes increasingly important in serious games and simulation training as these games commonly need to be engaging and impart learning content. Overburdening players’ cognitive capacity with either too much gameplay challenge or learning content may reduce the educational effectiveness of the game. Aim. In this research, we develop a game-based driving simulation with different gameplay tasks to explore the impact of different types of challenges and game aesthetics on real-time cognitive load and task performance, which may inform serious game design. We also test the validity of a game-embedded real-time cognitive load measuring method. Method A total of 31 participants undertook the driving simulation experiment under three different aesthetic conditions using a within-subject experimental design. Cognitive load was measured using three different methods, and performance was measured via in-game metrics. Additionally, demographic and engagement surveys were also completed. Results Player performance and cognitive load respond differently to different types of challenge, and an appropriate level of game challenge can lower cognitive load. The embedded cognitive load measure was validated as an effective method for evaluating real-time cognitive load during gameplay. Conclusion The results demonstrate the validity of a dual measure approach for future adaptive serious games and simulation training environments combining performance and cognitive load. An easy to implement, and robust, in-game measure for cognitive load has been validated in real-world conditions. From these results, a system for dynamic difficulty adjustment is proposed tailored towards serious games and simulation.

Generating Flight Illusions Using Galvanic Vestibular Stimulation in Virtual Reality Flight Simulations.

Vestibular flight illusions remain a significant source of concern for aviation training. Most fixed-based simulation training environments, including new virtual reality (VR) technology, lack the ability to recreate vestibular flight illusions as vestibular cues cannot be provided without stimulating the vestibular end organs. Galvanic vestibular stimulation (GVS) has long been used to create vestibular perception. The purpose of this study is to evaluate the ability of GVS to simulate common flight illusions by intentionally providing mismatched GVS during flight simulation scenarios in VR. Nineteen participants performed two flight simulation tasks-take off and sustained turn-during two separate VR flight simulation sessions, with and without GVS (control). In the GVS session, specific multi-axis GVS stimulation (i.e., electric currents) was provided to induce approximate somatogravic and Coriolis illusions during the take-off and sustained turn tasks, respectively. The participants used the joystick to self-report their subjective motion perception. The angular joystick movement along the roll, yaw, and pitch axes was used to measure cumulative angular distance and peak angular velocity as continuous variables of motion perception across corresponding axes. Presence and Simulator Sickness Questionnaires were administered at the end of each session. The magnitude and variability of perceived somatogravic illusion during take-off task in the form of cumulative angular distance (p < 0.001) and peak velocity (p < 0.001) along the pitch-up axis among participants were significantly larger in the GVS session than in the NO GVS session. Similarly, during the sustained turn task, perceived Coriolis illusion in the form of cumulative angular distances (roll: p = 0.005, yaw: p = 0.015, pitch: p = 0.007) and peak velocities (roll: p = 0.003, yaw: p = 0.01, pitch: p = 0.007) across all three axes were significantly larger in the GVS session than in the NO GVS session. Subjective nausea was low overall, but significantly higher in the GVS session than in the NO GVS session (p = 0.026). Our findings demonstrated that intentionally mismatched GVS can significantly affect motion perception and create flight illusion perceptions during fixed-based VR flight simulation. This has the potential to enhance future training paradigms, providing pilots the ability to safely experience, identify, and learn to appropriately respond to flight illusions during ground training.

A Simulated Scenario to Improve Resident Efficiency in an Emergency Department

IntroductionMultitasking is a core competency in emergency medicine. Simulation has been shown to be an effective method of education, which allows learners to prepare for real-world challenges in a controlled environment.MethodsIn this study, trainees were given a scenario that simulated the experience of managing two patient encounters within a time metric while addressing interruptions that take place in a typical ED. Residents were evaluated using an internally developed scoresheet, which assessed task-switching abilities, documentation skills, and adherence to door to disposition time metric. Residents were asked to evaluate their experience with a survey.ResultsAll the participants reported that they would translate some of the skills learned to their daily clinical practice. Five out of six residents reported improvements in their skills as a result of the task-switching training. The following three common themes were pervasive in the debrief discussion: (1) the residents felt the added pressure of the door-to-disposition metric, (2) the objectives of the simulation did not fit within their pre-constructed concept of a successful simulation equating to establishing the correct diagnosis, and (3) the interruptions were very realistic.DiscussionEmergency physicians are interrupted approximately every 9-14 minutes, and this number increases with the number of patients being managed simultaneously. By developing a safe, simulated training environment, we sought to transfer key strategies for improving focus and learning to prioritize while also helping them to identify how certain pressures and interruptions affected their stress levels and concentration.

Development of a veterinary emergency open standard competency framework using a competency-based model of medical education.

To address the shortage of emergency veterinarians, the profession is exploring accelerated training pathways. We sought to contribute to the solution by developing the foundation for an open standard, competency-based veterinary emergency training curriculum for use by any program. We also developed a curricular delivery, tracking, and assessment system to demonstrate how the framework can be integrated into training programs. DESIGN: Hybrid Delphi method. SETTING: Academia and referral practice. ANIMALS: None. None. An emergency veterinary competency framework was developed by adapting the human Model of the Clinical Practice of Emergency Medicine, which aligns with the Competency-Based Veterinary Education framework, to produce 4 areas of core competency: Patient Care, Interpersonal/Communication, Professionalism, and Practice-based Learning/Improvement. A comprehensive list of veterinary emergency skills was generated and organized within the framework utilizing the hybrid Delphi method. An initial survey completed by 133 emergency and critical care specialists and emergency room clinicians produced data regarding the value of specific skills. An 11-member focus group consisting of survey participants iterated upon the survey results to produce a master library of skills and cases, including 56 Patient Care, 43 Interpersonal/Communication, 11 Practice-based Learning/Improvement, and 20 Professionalism skills, as well as 155 case types. The curricular delivery system tracks and assesses case management proficiency and development of knowledge and professional skills using a patient care eLearning program and simulation training environment. CONCLUSIONS: The increasing need for emergency veterinarians is a shared industry-wide challenge. To contribute toward a collective solution, we have undergone an evidence-based process to create the foundation for an open standard competency framework composed of a library of skills and cases. We offer this open standard framework to the veterinary profession and hope it continues to grow and evolve as we drive toward developing competency-based training programs that address the shortage of emergency veterinarians.

Military Use of Point of Care Ultrasound (POCUS).

Point of care ultrasound (POCUS) offers multiple capabilities in a relatively small, lightweight device to military clinicians of all types and levels in multiple environments. Its application in diagnostics, procedural guidance, and patient monitoring has not been fully explored by the Military Health System (MHS). The purpose of this narrative review of the literature was to examine the overall use of POCUS in military settings, as well as the level of ultrasound training provided. Studies related to use of POCUS by military clinicians with reported sensitivity/specificity, accuracy of exam, and/or clinical decision impact met inclusion criteria. After initial topical review and removal of duplicates, two authors selected 17 papers for consideration for inclusion. Four of the authors reviewed the 17 papers and determined the final inclusion of 14 studies. We identified seven prospective studies, of which three randomized subjects to groups. Five reports described use of POCUS in patients, two used healthy volunteers, two were in simulation training environments, four used animal models to simulate specific conditions, and one used a cadaver model. Clinician subjects ranged from one to 34. Conventional medics were subjects in six studies. Four studies included special operations medics. One study included nonmedical food service inspectors. The use of ultrasound in theater by deployed consultant radiologists is described in three reports. Military clinicians demonstrated the ability to perform focused exams, including FAST exams and fracture detection with acceptable sensitivity and specificity. POCUS in the hands of trained military clinicians has the potential to improve diagnostic accuracy and ultimately care of the war fighter.

A systematic literature review of assessment feedback in preclinical dental education.

Development of evaluative judgement abilities through assessment and feedback strategies is crucial in students' progress to become self-regulated lifelong learners. Dentists' ability to appraise the quality of treatment provided to their patients starts with development of competences in a simulated preclinical training environment. However, the effectiveness of these assessment and feedback strategies is not well understood. This literature review aimed to identify the assessment and feedback interventions and their effect on dental students' appraisal and psychomotor skills during preclinical training. A search of the electronic databases PubMed, Ebscohost (Dentistry and Oral Health), Scopus, Web of Science and EMBASE was conducted of studies published until October 2019. Twelve studies met the inclusion criteria. Two studies were randomised controlled trials and ten non-randomised studies. All studies included students' self-assessment and grading criteria as part of their feedback interventions. Feedback utilisation training was reported in 66% of the included studies. Evidence suggests feedback strategies improve psychomotor skills and increase agreement between students' and teachers' awarded grades. However, these improvements vary with the complexity of the task. Only one study shows self-directed learning significantly contributing to students' psychomotor skill improvement. Although assessment and feedback are regarded as crucial for developing students' evaluative judgement capabilities to become self-regulated lifelong learners, there is limited empirical evidence of the assessment and feedback conditions that enhance students' judgement abilities, performance and self-regulation. Further research is needed to investigate and compare the effect of different assessment and feedback interventions on students' appraisal skills, their impact on learning and self-regulation.

Construction of Experiential Learning Space Model Based on Virtual Reality Technology

In order to better help learners to improve their learning experience and learning efficiency, this paper starts from the interaction, immersion and imagination of virtual reality technology, and sorts out the evolutionary process of formal learning space, informal learning space and virtual learning space. It also proposes the conception of experiential learning space with the virtuality and reality combination. Aiming at the application of virtual reality technology in the knowledge presentation, simulation training and experience environment of experiential learning space, an experiential learning space model based on the virtuality and reality combination is constructed to enrich the learning environment and information presentation of learners, enhance learners’ situational experience and improve their learning efficiency.

Hyper-realistic and immersive surgical simulation training environment will improve team performance

BackgroundSurgical trauma care requires excellent multidisciplinary team skills and communication to ensure the highest patient survival rate. This study investigated the effects of Hyper-realistic immersive surgical team training to improve...

A Multi-person collaborative Simulation System for Subway Emergency Based on Virtual Reality

In the operation of urban rail stations, joint emergency drills for different types of work are an important way to ensure the safe operation of urban rail stations. However, due to the lack of equipment and means, at present, the joint emergency drills for urban rail stations are mostly a single-person system. Based on the current status of emergency joint drills in urban rail stations, this article proposes a virtual reality-based multi-person collaborative urban rail station emergency simulation system. Construct a large-scale virtual reality scene through the viewpoint-related LOD quadtree, and use socket technology to achieve multiplayer online interaction. Finally, all models are jointly driven by Unity3d in the simulation scene. An immersive, multi-industry coordinated urban rail station emergency drill simulation system was constructed. Providing a simulation training environment similar to the actual situation for emergency trains in urban rail stations can greatly improve the shortcomings of difficult and inefficient implementation of the organization, and change the difficult situation of insufficient emergency drills for multiple types of rail stations.

The end game – A quantitative assessment tool for anastomosis in simulated microsurgery

With the move towards simulation based microsurgical training and emphasis on the declining usage of animal models, there is a need for an objective method to evaluate microvascular anastomosis in a non-living, simulated microsurgical training environment. Our aim was to create a validated assessment tool to evaluate the intimal surface of the end product to measure skills acquisition. The intimal surface of 200 anastomoses from 23 candidates and 2 experts were assessed using ImageJ to measure 4 parameters: 1) distance between the distal insertion points, 2) distance between the proximal insertion points, 3) length of sutures placed, 4) number of axes. Using these parameters, a 9-component scoring system was produced based on the hypothesis of the ideal anastomosis having equidistance between the above parameters. The scoring system was devised based on population performance to give a maximum score of 100. The EPIA tool demonstrated its ability to differentiate between seniority from undergraduate to expert. Furthermore, predictive validity was shown by demonstrating skill acquisition between day 3 and 5 of the microsurgery course. The EPIA tool is a valid and feasible method to assess and provide feedback regarding the end product as an adjunct to current scoring systems in simulated microsurgery.

Indoor Simulated Training Environment for Brain-Controlled Wheelchair Based on Steady-State Visual Evoked Potentials.

Brain-controlled wheelchair (BCW) has the potential to improve the quality of life for people with motor disabilities. A lot of training is necessary for users to learn and improve BCW control ability and the performances of BCW control are crucial for patients in daily use. In consideration of safety and efficiency, an indoor simulated training environment is built up in this paper to improve the performance of BCW control. The indoor simulated environment mainly realizes BCW implementation, simulated training scenario setup, path planning and recommendation, simulated operation, and scoring. And the BCW is based on steady-state visual evoked potentials (SSVEP) and the filter bank canonical correlation analysis (FBCCA) is used to analyze the electroencephalography (EEG). Five tasks include individual accuracy, simple linear path, obstacles avoidance, comprehensive steering scenarios, and evaluation task are designed, 10 healthy subjects were recruited and carried out the 7-days training experiment to assess the performance of the training environment. Scoring and command-consuming are conducted to evaluate the improvement before and after training. The results indicate that the average accuracy is 93.55% and improves from 91.05% in the first stage to 96.05% in the second stage (p = 0.001). Meanwhile, the average score increases from 79.88 in the first session to 96.66 in the last session and tend to be stable (p < 0.001). The average number of commands and collisions to complete the tasks decreases significantly with or without the approximate shortest path (p < 0.001). These results show that the performance of subjects in BCW control achieves improvement and verify the feasibility and effectiveness of the proposed simulated training environment.

Automatic Detection of Learner Engagement Using Machine Learning and Wearable Sensors

Training can now be delivered on a large scale through mobile and web-based platforms in which the learner is often distanced from the instructor and their peers. In order to optimize learner engagement and maximize learning in these contexts, instructional content and strategies must be engaging. Key to the development and study of such content and strategies, and adaptation of instructional techniques when learners become disengaged, is the ability to objectively assess engagement in real-time. Previous self-reported metrics, or expensive EEG-based engagement measures are not appropriate for large-scale platforms due to their complexity and cost. Here we describe the development and testing of a measurement and classification technique that utilizes non-invasive physiological and behavioral monitoring technology to directly assess engagement in classroom, simulation, and live training environments. An experimental study was conducted with 45 students and first responders in a unmanned aircraft systems (UAS) training program to assess the ability to accurately assess learner engagement and discriminate between levels of learner engagement within classroom, simulation and live environments via physiological and behavioral inputs. A series of engagement classifiers were developed using cardiovascular, respiratory, electrodermal, movement, and eye-tracking features that were able to successfully classify engagement levels at an accuracy level of 85% with eye-tracking features included or 81% without eye-tracking features. This approach is capable of monitoring, assessing, and tracking learner engagement across learning situations and contexts, and providing real-time and after action feedback to support instructors in modulating learner engagement.