Acute stress has the potential to significantly debilitate human performance, both physically and cognitively. For long-duration space flight, the results of such reduced cognitive performance could be life-threatening, and therefore warrants the creation of behavioral countermeasures for mitigating crew health and performance risks. Currently most emergency training focuses on performance outcomes, but new research should be centered on preventing negative performance outcomes through acute stress management techniques. Traditional training can be effective under predictable conditions, but performance can degrade rapidly if unexpected stressors are introduced. Additionally, the proposed system could serve as a preflight screening measure to help identify individuals who are more likely to perform better in high stress situations. The goal of this experiment, using Virtual Reality (VR) simulated situations, was to reduce acute stress response during space flight using an adaptive inoculation approach. Exposure was administered gradually and used a biofeedback system to respond and adapt to individual stress response in a way that promotes learning voluntary physiological control without overwhelming the subject.
APPROACH:
The research team and panel of experts reviewed and identified the stressors associated with emergency spaceflight situations of fire on the International Space Station (ISS) with respect to task and effect on users. Procedural information for virtual reality (VR) training was detailed, including the events likely to occur in the environment, the types of stressors encountered, NASA emergency procedures, resources to respond during the event, and the performance effects the stressors may have. Stress training requires procedural information to be included in the scenarios and conveyed to the user, so the stressors do not interfere with skill/knowledge acquisition. The stressors were categorized by manipulation type (environment or task manipulation), which indicates if a stressor may affect the task and deviate from the selected emergency procedure. From the environmental stressors, a simplified fire procedure was created based on the existing NASA ISS emergency procedures to develop adaptation and Training Module logic. The adaptations used implicit biofeedback, consisting of physiological signals exceeding a threshold “zone” and triggering a change in simulated stressors. The Training Module design was informed by past research on Stress Inoculation Training and Graduated Stress Exposure to implement a stress inoculation training strategy over five training sessions. The adaptation and training module rules taken together were used to produce a training pedagogy for use within the system.
To implement a Prototype Training System, the research team designed and implemented the system architecture for a VR-ISS with a emergency fire simulation. The VR environment was developed for the stressors and emergency procedure selected in the Training Module design. This environment was designed so that users can complete a NASA emergency fire procedure and locate the source of a fire. The procedure requires emergency equipment including a portable breathing apparatus (PBA), portable fire extinguisher (PFE), and Compound Specific Analyzer–Combustion Products (CSA-CP). Three different stressor levels were created in the simulation, involving a combination of stressors of varying intensity, including smoke density, fire alarms, and module power-outages that flickered the lights. The stressor levels were validated through objective physiological measures and subjective stress questionnaires as participants conducted the emergency procedure to locate the fire source. Results showed that the three-stressor levels implemented in a VR environment result in significantly different participant stress, workload, and distress. The adaptive nature of the VR training system required that the trainee’s stress level be measured in real-time, and a stress detection system was created with machine learning methods. Physiological signals were calculated from sensors which include electrocardiogram (ECG), respiration (RSP), electrodermal activity (EDA), and non-invasive blood pressure (NIBP). The physiological signals were streamed in real-time to apply preprocessing, high-dimensional feature extraction, feature selection, and classification using supervised machine learning approaches. Current limitations with supervised machine learning approaches propelled the development of a statistical classification method by our research team, known as Approximate Bayes (ABayes). ABayes uses kernel density probability estimates to find conditional class probabilities for three stress states: low, medium, high. The advantage of ABayes is the direct and transparent calculation of the class probabilities. ABayes was evaluated on its accuracy of predicting stress using cross-validation and hold-out on unseen data.
Three human-in-the-loop experiments were performed to test the components of the Adaptive VR turning system in isolation and as a system. The first experiment assessed the ability to manipulate a person’s stress level in a virtual environment. Specifically, an evaluation was preformed to determine the extent to which operationally relevant VR stressor levels (i.e., low, medium, high) derived from existing emergency spaceflight procedures could evoke a reliable stress response. The second experiment evaluated the ability to reliably detect the stress level of a person in VR using a combination of biophysical sensors and machine learning to correctly classify low, medium, or high stress. The third experiment was conducted to determine if the closed-loop VR training system could successfully inoculate participant’s stress over a series of training trials with graduated stress exposure.
RESULTS:
A physiological-based stress detection system for classifying multiple levels of acute stress was developed with a novel classifier, ABayes, using a personalized time-series interval approach. The approach was evaluated against common machine learning classification systems in their ability to classify stress for two different tasks: a fire response task aboard a VR International Space Station (VR-ISS) or a computer-based (N-back) task. The current findings suggest that three levels of stress can be classified by means of the ABayes approach, providing promising accuracy when compared to past research on multi-class stress detection. Stress was accurately predicted for both the simplified lab task, N-back, and the more complex VR-ISS task. Analysis on the window sizes gave insight into which sensors/features were useful for varying time-intervals. Future work will further investigate these personalized stress detection systems with the aim of implementing real-time stress monitoring.