Real-time Stress Research Articles

Virtual Reality Adaptive Training for Personalized Stress Inoculation.

To evaluate a personalized adaptive training program designed for stress prevention using graduated stress exposure. Astronauts in the high-risk space mission environment are prone to performance-impairing stress responses, making preemptive stress inoculation essential for their training. This work developed an adaptive virtual reality-based system that adjusts environmental stressors based on real-time stress indicators to optimize training stress levels. Sixty-five healthy subjects underwent task training in one of three groups: skill-only (no stressors), fixed-graduated (prescheduled stressor changes), and adaptive. Psychological (subjective stress, task engagement, distress, worry, anxiety, and workload) and physiological (heart rate, heart rate variability, blood pressure, and electrodermal activity) responses were measured. The adaptive condition showed a significant decrease in heart rate and a decreasing trend in heart rate variability ratio, with no changes in the other training conditions. Distress showed a decreasing trend for the graduated and adaptive conditions. Task engagement showed a significant increase for adaptive and a significant decrease for the graduated condition. All training conditions showed a significant decrease in worry and anxiety and a significant increase in the other heart rate variability metrics. Although all training conditions mitigated some stress, the preponderance of trial effects for the adaptive condition supports that it is more successful at decreasing stress. The integration of real-time personalized stress exposure within a VR-based training program not only prepares individuals for high-stress situations by preemptively mitigating stress but also customizes stressor levels to the crew member's current state, potentially enhancing resilience to future stressors.

Real-time stress field reconstruction method using online monitoring parameters for thick-walled power plant components based on gappy proper orthogonal decomposition

The three-dimensional stress distribution information of in-service components is of great significance for the intelligent operation and maintenance of power plants. A real-time stress field reconstruction method based on the gappy proper orthogonal decomposition (POD) and prediction function is proposed for condition monitoring of high-temperature pressured thick-walled components. Based on the “snapshots” method, the standard POD orthogonal basis is extracted from the high-fidelity data obtained from finite element analysis under various hot start load conditions to capture the main features of the stress fields. The complete stress field is reconstructed by the linear combination of the standard POD basis, and the modal coefficients are calculated using the discrete node stresses through the gappy POD procedure. Since only the online monitoring parameters of steam are available in practical operations, the prediction function is used to establish the mapping relationship between the monitoring parameters and node stress. The discrete nodes are determined by the trial-and-error method. The small global relative errors between the reconstructed stress fields and numerical solutions indicate the high accuracy of the proposed method. The spatial error of the entire stress field and the temporal error of the maximum stress were also evaluated. The computation time of the reconstruction process is significantly shorter than the sampling time step. The performance of gappy POD on different numbers of snapshots and modes was also presented.

Biochipping in forensic medicine as a technology for determining readiness to cause harm: a review

This article evaluated the issues of determining consent to harm as grounds for excluding crime through the prism of the totality of mental and physiological processes in the victim’s body, considering the analysis of the emotional attitude to the traumatic situation. Existing practice is based on the testimony and position of the injured party and the absence of physical signs of resistance as an indicator of consent to harm.
 The materials of the study were the norms of the criminal legislation of Kazakhstan and foreign states on the meaning of the victim’s consent to harm his or her peers and interests, particularly in cases of sexual inviolability. A literature review on this topic revealed the relationship between the subjective attitude of the victim of violence and chemical and physiological processes in the body.
 The achievements of scientists in determining chemical and physiological signs of stress in real time using bioanalysts-biochips were analyzed. Based on the results, generalization of scientific works, and analysis of legislation on the subject, the evidentiary value of these technologies to determine the consent of the victim in the absence of signs of stress at the time of exposure were considered.
 The use of biochips with analyzers of chemical and physiological changes in the human body in real time will not only determine the stress state of the victim at the time of the attack, as a sign of consent or refusal to act, but also expand the possibilities of forensic medicine and general practical medicine in early diagnosis of diseases and prompt treatment. Furthermore, a SWOT analysis of the use of biocyping to resolve the issue of determining the victim’s consent to harm, excluding the possibility of manipulation and falsification of evidence, was performed.

Research on the "shape-performance-control" integrated digital twin system for boom-type roadheaders

The boom-type roadheader plays a crucial role in coal mining. However, conducting the real-time monitoring of the mechanical performance and comprehensive adaptive cutting in the dynamic cutting process are challenging. To address these issues, a digital twin system that integrates the elements of “shape, performance, and control” for roadheaders is presented in this paper. The system comprises three components: physical space, service space, and twin space. The service space forms the core of the entire system. Within this space, twin models and control models are created using numerical simulation, artificial intelligence and multi-source data fusion technology. These models serve the purpose of predicting the roadheader’s mechanical performance and controlling the swing speed of the cutting arm. The physical space is built using technologies such as robot kinematics, electrical systems, hydraulic transmission, and other relevant techniques. This approach facilitates the transmission of multi-sensor data to twin models. The control model then manages the roadheader’s function based on the output signals from the control model. The twin space is constructed utilizing physical rendering engines, databases, and 3D modelling tools. This space visualizes and stores the movement, performance, and control parameters of the roadheader. The results demonstrate that the average absolute error between the measured data from the test’s three position strain gauges and the predicted data from the twin system is 10.38 MPa. Furthermore, the twin system achieves an average update interval of 0.34 s, allowing real-time stress monitoring of the structural components of the roadheader and preventing damage caused by overload. The proposed control model enables adaptive adjustment of the swing speed of the cutting arm in approximately 0.3 s. This improvement significantly enhances the adaptive cutting capabilities of roadheaders when dealing with complex coal and rock formations.

Machine learning-based stress classification system using wearable sensor devices

<p>University students often become victims of high-stress levels due to the highly competitive work environment. Unmonitored stress levels in students can inflict severe physiological health problems. This work aims to build a stress classification framework using wearable sensor devices to predict mental stress levels for undergraduate engineering students. It comprises a study to collect a data set of 23 university students using wearable devices for four physiological signals, i.e., electroencephalogram (EEG), electrodermal activity (EDA), skin temperature (SKT), and heart rate (HR), when the students perform the montreal imaging stress task (MIST) for the mental workload. The machine learning models proposed in this work help classify stress into three levels: rest, moderate, and high. The models achieve a classification accuracy of 99.98% using the EEG signals’ time-frequency domain features and an accuracy of 99.51% using the EDA, HR, and SKT signals. The proposed models achieve better scores than all the previous studies on stress classification, using EEG signals and EDA, HR, and SKT signals. This study is novel since it also demonstrates the applicability and proficiency of wearable sensor devices in developing accurate stress classification models to help build real-time stress monitoring systems.</p>

A wearable three-axis force sensor based on deep learning technology for plantar measurement

A challenge in the measurement of plantar shear stress measurement is the absence of wearable and comfortable monitoring devices. In this paper, a wearable three-axis force sensor based on end-to-end deep learning technology is developed for plantar shear stress monitoring. The sensor can convert the three-axis stress it experiences into image signals through the deformation of the pattern layer embedded in the elastomeric probe. These images and three-axis stresses are fed into a convolution neural network for training, establishing a mapping relationship between images and three-axis forces. The prepared sensor has the advantages of small size (1.62 cm3), light weight (1.68 g), and flexibility, which make it possible to form a sensor array in the shoe without affecting the comfort of the wearer. By synchronizing with an action camera, the sensor array can provide real-time three-axis stress in different plantar regions for each frame of motions such as walking, running, playing football or basketball. This work contributes to the advancement of gait analysis, the clinical diagnosis of foot diseases, and the evaluation of athletic training.

Toward Digital Twin Development for Implant Placement Planning Using a Parametric Reduced-Order Model.

Real-time stress distribution data for implants and cortical bones can aid in determining appropriate implant placement plans and improving the post-placement success rate. This study aims to achieve these goals via a parametric reduced-order model (ROM) method based on stress distribution data obtained using finite element analysis. For the first time, the finite element analysis cases for six design variables related to implant placement were determined simultaneously via the design of experiments and a sensitivity analysis. The differences between the minimum and maximum stresses obtained for the six design variables confirm that the order of their influence is: Young's modulus of the cancellous bone > implant thickness > front-rear angle > left-right angle > implant length. Subsequently, a one-dimensional (1-D) CAE solver was created using the ROM with the highest coefficient of determination and prognosis accuracy. The proposed 1-D CAE solver was loaded into the Ondemand3D program and used to implement a digital twin that can aid with dentists' decision making by combining various tooth image data to evaluate and visualize the adequacy of the placement plan in real time. Because the proposed ROM method does not rely entirely on the doctor's judgment, it ensures objectivity.

State-of-the-art AI-enabled mobile device for real-time water stress detection of field crops

An AI-enabled mobile device was developed for real time identification of water stress in field crops with the aim to assist crop breeding and precision irrigation management programs. The device assembles a Raspberry Pi single board computer and a digital RGB camera. A validated, state-of-the-art, transfer-learning based deep learning model GoogLeNet was deployed on-board to process the captured images and classify those into stressed or non-stressed categories in real time. The captured images and results are displayed on a custom graphic user interface. The device is also capable of predicting stress in-house from historically collected images fed as inputs to the device. The results are produced in 200 ms post-capture/feeding of the images. The device was field-tested in wheat and maize crops and pertinent stress identification accuracies were 92.9% and 97.9%, respectively. The developed device offers a user-friendly mode to identify water stress in real time for the crop breeders, researchers, and ultimately growers for timely decision making on plant health and crop yield improvement. The device framework capabilities can be extended in the future for identifying multiple problems of various biotic and abiotic stresses in multiple crops, and their cultivars grown in various agroclimatic conditions.

INTEGRATING HEART RATE VARIABILITY AND PSYCHOMETRIC ASSESSMENTS TO EVALUATE STRESS AND BURNOUT IN ICU NURSING STAFF: A PILOT STUDY

Background: Intensive Care Units (ICUs) are recognized as highly demanding environments that significantly contribute to stress and burnout among nursing staff. Despite increasing concern over burnout in healthcare, the relationship between physiological stress indicators, such as Heart Rate Variability (HRV), and psychometric assessments has not been thoroughly explored in this setting. Objective: This pilot study aimed to evaluate the relationship between HRV metrics and psychometric assessments of stress and anxiety in ICU nursing staff. Additionally, it explored the influence of shift type, shift duration, demographic factors, and lifestyle habits on these stress indicators. Methods: An observational cross-sectional pilot study was conducted with 24 ICU healthcare professionals at a University Hospital in Madrid, Spain. HRV data were collected under controlled conditions, with measurements taken at the beginning and end of shifts. Psychometric assessments were conducted using the State-Trait Anxiety Inventory (STAI), Perceived Stress Scale (PSS-14), Nursing Stress Scale (NSS) and a Visual Analogue Scale for Stress (VASS). Non-parametric statistical tests were used to analyze correlations between HRV metrics, psychometric scores, and demographic/lifestyle variables. Results: Significant negative correlations were observed between HRV metrics and perceived stress levels, particularly between the Low-Frequency to High-Frequency (LF/HF) ratio and stress measures. Night and extended shifts were associated with elevated stress, as indicated by lower HRV and higher psychometric stress scores. These findings suggest that shift type and duration significantly influence stress levels in ICU nursing staff. Conclusion: This pilot study highlights the potential of HRV as an objective measure of stress in ICU nursing staff, with significant correlations observed between HRV metrics and psychometric assessments. The findings suggest that HRV could be a valuable tool for monitoring stress in real time and identifying individuals at risk of burnout. However, further research with larger samples and a longitudinal approach is needed to validate these results and explore their implications for occupational health practices in ICU settings.

A flexible piezoresistive strain sensor based on MXene/bacterial cellulose hydrogel with high mechanical strength for real-time monitoring of human motions

A piezoresistive hydrogel sensor composed of bacterial cellulose and MXene nanosheets shows real-time stress sensing abilities at different amplitudes of human motions and maintains its sensing ability underwater.

Predicting stress levels using physiological data: Real-time stress prediction models utilizing wearable devices.

Stress has emerged as a prominent and multifaceted health concern in contemporary society, manifesting detrimental effects on individuals' physical and mental health and well-being. The ability to accurately predict stress levels in real time holds significant promise for facilitating timely interventions and personalized stress management strategies. The increasing incidence of stress-related physical and mental health issues highlights the importance of thoroughly understanding stress prediction mechanisms. Given that stress is a contributing factor to a wide array of mental and physical health problems, objectively assessing stress is crucial for behavioral and physiological studies. While numerous studies have assessed stress levels in controlled environments, the objective evaluation of stress in everyday settings still needs to be explored, primarily due to contextual factors and limitations in self-report adherence. This short review explored the emerging field of real-time stress prediction, focusing on utilizing physiological data collected by wearable devices. Stress was examined from a comprehensive standpoint, acknowledging its effects on both physical and mental well-being. The review synthesized existing research on the development and application of stress prediction models, underscoring advancements, challenges, and future directions in this rapidly evolving domain. Emphasis was placed on examining and critically evaluating the existing research and literature on stress prediction, physiological data analysis, and wearable devices for stress monitoring. The synthesis of findings aimed to contribute to a better understanding of the potential of wearable technology in objectively assessing and predicting stress levels in real time, thereby informing the design of effective interventions and personalized stress management approaches.

Real-time deformation and stress response of the planar SOFC during sintering

The thermal-mechanical response of the anode-supported planar solid oxide fuel cell (SOFC) during sintering is important for its manufacturing and in-service operation. The integrated micro/nano-indentation and finite element (FE) modeling method was used to characterize the Young’s modulus, yield stress and creeping for the NiO-3YSZ anode and 8YSZ electrolyte at room temperature. Based on the real-time full-field deformation of the half-cell SOFC which was measured using the 3D digital image correlation (DIC), the FE simulation was used to estimate the stress response in a manner of sensitivity study. It shows that the half-cell SOFC warps towards the anode substrate during heating and points in the opposite direction during cooling. The warping deformation of FE simulation matches well with the DIC measurement. In addition, the maximum tensile stress in the electrolyte coat of the half-cell SOFC plate is about 207 MPa if assuming temperature-independence of creeping for the SOFC materials.

Individualized Stress Mobile Sensing Using Self-Supervised Pre-Training.

Stress is widely recognized as a major contributor to a variety of health issues. Stress prediction using biosignal data recorded by wearables is a key area of study in mobile sensing research because real-time stress prediction can enable digital interventions to immediately react at the onset of stress, helping to avoid many psychological and physiological symptoms such as heart rhythm irregularities. Electrodermal activity (EDA) is often used to measure stress. However, major challenges with the prediction of stress using machine learning include the subjectivity and sparseness of the labels, a large feature space, relatively few labels, and a complex nonlinear and subjective relationship between the features and outcomes. To tackle these issues, we examined the use of model personalization: training a separate stress prediction model for each user. To allow the neural network to learn the temporal dynamics of each individual's baseline biosignal patterns, thus enabling personalization with very few labels, we pre-trained a one-dimensional convolutional neural network (1D CNN) using self-supervised learning (SSL). We evaluated our method using the Wearable Stress and Affect Detection(WESAD) dataset. We fine-tuned the pre-trained networks to the stress-prediction task and compared against equivalent models without any self-supervised pre-training. We discovered that embeddings learned using our pre-training method outperformed the supervised baselines with significantly fewer labeled data points: the models trained with SSL required less than 30% of the labels to reach equivalent performance without personalized SSL. This personalized learning method can enable precision health systems that are tailored to each subject and require few annotations by the end user, thus allowing for the mobile sensing of increasingly complex, heterogeneous, and subjective outcomes such as stress.

Low Airspeed Impacts on Tom Turkey Response to Moderate Heat Stress

Heat stress is a concern for turkeys in naturally ventilated houses. Chamber and room studies were used to assess heat stress at moderate temperatures (<25 °C) and low airspeeds on grown tom turkeys. In the chamber study, four ventilation rates × two temperatures (thermal comfort and thermal stress, 11 °C above thermal comfort) were applied to 13- to 19-week birds. Very small differences in airspeeds among the four treatments masked subcutaneous, cloacal, and infrared (IR) temperature differences at both temperatures. In the room study, four ventilation rates (0.07 m3·min−1·kg−1 or 100%, 75%, 50%, and 30% or Control) were applied to 21-week toms housed at <23 °C. The Control treatment had significantly higher whole-body and head temperatures vs. the other treatments. Only 100% had higher weight gain vs. 50%; hematology was unaffected by treatment. Higher ventilation rates reduced heat stress due to lower room temperatures, not airspeed differences, which were very low. The low-cost IR camera detected a heat stress difference ≥ 0.8 °C, corresponding to wind chill of 0.8 °C due to an airspeed of 0.8 m·s−1 vs. still air on the USDA broiler wind chill curve. Machine vision combined with IR thermography could alleviate real-time poultry heat stress.

H2O2-responsive dual-peak ratiometric NIR-II fluorescent probe for in situ hepatic oxidative stress level monitoring

Timely detection of hepatic oxidative stress is effective in preventing the onset and progression of liver disease. However, real-time and dynamic monitoring of oxidative stress in vivo remains challenging. Herein, we report a H2O2-responsive dual-peak ratiometric NIR-II fluorescent probe (Er@Ag2S:Pb), made by combining H2O2-responsive fluorescent Pb-doped Ag2S quantum dots (Ag2S:Pb QDs) with a fluorescence-stabilized reference substrate NaYF4:Yb/Er @NaYF4. By monitoring the change in emitted I1550/I1220 intensities the probe can be used to sense and quantify H2O2 concentrations ranging from 5 to 100 μM with excellent specificity. Experimental studies using mice models have shown that this probe can be used to monitor of hepatic H2O2-related oxidative stress in real time and non-invasively. Thus, the developed probe provides a powerful ratiometric NIR-II fluorescence imaging tool for timely monitoring of oxidative stress in vivo.

A driver stress detection model via data augmentation based on deep convolutional recurrent neural network

Excessive stress generally leads to degraded driving performance, which increases the risk of road accidents. Therefore, real-time driver stress detection is of great significance to improve road safety. To this end, this paper proposes a deep convolutional recurrent neural network with Wasserstein generative adversarial network-based data augmentation (WGAN-DCRNN) for real-time driver stress detection, where only the pupillary response data are used. The proposed model can learn the sequence features from the input data more effectively and address the class-imbalance problem of the dataset. First, two types of DCRNN models (i.e., CNN-LSTM and CNN-GRU) are established and compared with baseline models (i.e., CNN, LSTM and GRU). The best baseline model (i.e., CNN) achieves 93.02% accuracy on the overall samples of the test set, while the CNN-LSTM and CNN-GRU improve the accuracy to 94.68% and 94.71%, respectively. This suggests that the performance of the CNN can be improved by integrating the RNN to consider the temporal dependencies of the pupillary response data. Second, deep generative model-based data augmentation is used to address the class-imbalance problem of the dataset. Specifically, the WGAN is trained to generate new samples, which are used to expand and balance the training set. To validate the effect of the proposed data augmentation method, comparative experiments are further conducted. The results show that the accuracies of CNN-LSTM and CNN-GRU are further improved to 95.39% and 95.30%, respectively. More importantly, the recall rates of minority categories achieve significant improvement. This indicates that the proposed model overcomes the class-imbalance problem and that the generalization ability of the recognition model has been further improved by using data augmentation. In addition, the WGAN-DCRNN outperforms models in existing driver stress detection studies. The proposed model can be used for different classification tasks to reduce road accident risks caused by drivers.

Mechanically robust, flexible hybrid tactile sensor with microstructured sensitive composites for human-cyber-physical systems

Advances in human-cyber-physical system (HCPS) requires multiple and multimodal sensory network to address the challenge of human-machine relationships, posing substantial potential for human health monitoring and human-centric smart manufacturing. However, combining electrical sensitivity and mechanical robustness of flexible sensors with simple device structure is still challenging. This work presents a flexible porous bimodal pressure sensor (PBPS) by fabricating 3D microstructured sensitive porous carbon-nanotubes composites (PCNC). The multi-layered PBPS can offer the ability to switch between piezoresistive and piezocapacitive sensing modes without altering the device structure, enhancing mechanical stability of device under loading/unloading cycles. This versatility allows for the detection of hardness discrimination, grabbing sensing, and dynamic human physiological signal recognition, which possess superior pressure sensing performances with a high sensitivity (0.1059 kPa−1 in piezoresistive mode, 0.2054 kPa−1 in capacitive mode), wide measuring range (0–25 kPa), rapid response time (<130 ms in piezoresistive mode, <55 ms in piezocapacitive mode), and long-term durability (>3000 cycles). Furthermore, we proposed a mechanical constitutive model to elucidate the sensing mechanism of microstructured PCNC by 3D micro-CT based modeling and experimental data. Finally, we employed multiple PBPSs as sensing elements to real-time monitor 3D printing manufacturing stress, structure assembling stress, and human physiology signals in HCPS, indicating the potential applications of PBPS ranging from monitoring human health to facilitating intelligent manufacturing.

Non-invasive, real-time stress measurement: Vocalization compared with thermal imaging in kittens of the domestic cat in response to social separation

Finding tools to assess the stress response which can be easily applied, are non-invasive, reliable and measured in real time is still a relevant topic in many areas of biology. Vocal characteristics and temperature of certain body areas have been suggested to reflect HPA axis and ANS activation. We hypothesized that changes in vocalizations and peripheral body temperature will show the magnitude of the stress response, and that the change in these will covary. Our aim was to measure the change in vocal characteristics and eye and nasal temperature of kittens (n = 43 from nine litters of seven mixed-breed mothers) during a potentially stressful event and to test how these correlated. We found change in several vocal and thermal parameters during a short social separation. Our findings indicate that arousal due to ANS activation in kittens of the domestic cat resulted in an increasing number of vocalisations of longer duration and higher intensity, and in lower and a wider range in fundamental frequency. Calls also became less tonal with more jitter. Change in temperature was generally negative in the lacrimal caruncle as well as in the rhinarium, but with great variance across individuals. Change in eye temperature positively correlated with the intensity of the calls and the change in nose temperature positively correlated with the change in call length. The results suggest the continued difficulty in interpreting both physiological and behavioural data to assess an individual´s stress response.

Real-time stress detection and monitoring system using IoT-based physiological signals

Currently, medical experts use psychophysiological questionnaires to evaluate human stress levels during counseling or interviews. Typically, biochemical samples use urine, saliva, and blood samples to identify the effects of stress on the human body. This research explains that stress detection can be done by analyzing psychological signals and the importance of monitoring stress levels. The authors develop research on stress detection based on psychological signals. The system then processes the recorded data; the android application displays the calculation results. The database can also be accessed as a spreadsheet via a web application. The design of real-time stress detection and monitoring using internet of things (IoT) can work well.

Innovative liquid metal strategy for real-time thermal control in additive manufacturing

Metal additive manufacturing (AM) involves rapid cycles of melting and solidification, often resulting in significant thermal stress variations, microcrack formation, and compromised structural integrity, especially for complex structures. Effective strategies are crucial for regulating temperature and stress distribution during laser-based metal AM processes; however, traditional thermal management approaches suffer from limitations in action area and response speed. In this study, the novel Liquid Metal-Assisted Additive Manufacturing (LMAAM) process is developed to enhance real-time temperature and stress control during deposition. This is the first known attempt to utilize liquid tin as an auxiliary thermal management material for AM. Numerical simulations and experimental analysis are performed to determine the relationship between LMAAM process conditions and resultant material microstructural properties. The results show that compared to AM without active thermal management, the incorporation of liquid tin yields an approximate 20 % increase in the cooling rate, a roughly 30 % reduction in residual tensile stress, a decrease in part grain size, and a roughly 30 % enhancement in microhardness. LMAAM technology opens up new possibilities for metal AM of highly reliable and intricate structures like multi-chambers, multi-channels, and deep blind holes.