Search Results (1,170)

While personal thermal comfort is critical for well-being and productivity, it is often overlooked by traditional building management systems that rely on uniform settings. Modern data-driven approaches often fail to capture the complex interactions between various data streams. This pilot study introduces a high-accuracy, interpretable framework for thermal comfort classification, designed to identify the most significant predictors from a comprehensive suite of environmental, physiological, and anthropometric data in a controlled group of young adults. Initially, an XGBoost model using the full 24-feature dataset achieved the best performance at 91% accuracy. However, after using SHAP analysis to identify and select the most influential features, the performance of our ensemble models improved significantly; notably, a Random Forest model’s accuracy rose from 90% to 94%. Our analysis confirmed that for this homogeneous cohort, environmental parameters—specifically temperature, humidity, and CO₂—were the dominant predictors of thermal comfort. The primary strength of this methodology lies in its ability to create a transparent pipeline that objectively identifies the most critical comfort drivers for a given population, forming a crucial evidence base for model design. The analysis also revealed that the predictive value of heart rate variability (HRV) diminished when richer physiological data, such as diastolic blood pressure, were included. For final validation, the optimized Random Forest model, using only the top 10 features, was tested on a hold-out set of 100 samples, achieving a final accuracy of 95% and an F1-score of 0.939, with all misclassifications occurring only between adjacent comfort levels. These findings establish a validated methodology for creating effective, context-aware comfort models that can be embedded into intelligent building management systems. Such adaptive systems enable a shift from static climate control to dynamic, user-centric environments, laying the critical groundwork for future personalized systems while enhancing occupant well-being and offering significant energy savings. Full article

Background/Objectives: The aim was to identify patterns of autonomic and neuroendocrine reactivity to an immersive virtual reality (VR) social-emotional stressor and explore their associations with perceived stress and eating behavior. Methods: This one-group pretest–posttest study included 30 children and adolescents with obesity (15 boys and 15 girls), aged 8 to 17 years. The VR protocol consisted of two consecutive phases: a 5 min relaxation phase using the Forest application and a 5 min stimulation phase using a cognitively engaging VR game designed to elicit social-emotional stress. Physiological responses were measured using heart rate variability (HRV) indices and salivary stress biomarkers, including cortisol and alpha amylase. Subjective stress and eating responses were assessed via visual analogue scales (VAS) administered immediately post-exposure. The Three-Factor Eating Questionnaire (TFEQ-R21C) was used to evaluate cognitive restraint (CR), uncontrolled eating (UE), and emotional eating (EE). Results: The cortisol reactivity was blunted and may reflect both the attenuated HPA axis responsiveness characteristic of pediatric obesity and the moderate psychological challenge of the VR stressor used in this study. Two distinct autonomic response patterns were identified via exploratory factor analysis: (1) parasympathetic reactivity, associated with increased RMSSD and SDNN and decreased LF/HF, and (2) sympathetic activation, associated with increased heart rate and alpha-amylase levels and reduced RR intervals. Parasympathetic reactivity was correlated with lower perceived stress and anxiety, but also paradoxically with higher uncontrolled eating (UE). In contrast, sympathetic activation was associated with greater cognitive restraint (CR) and higher anxiety ratings. Conclusions: This study demonstrates that immersive VR game exposure elicits measurable autonomic and subjective stress responses in children and adolescents with obesity, and that individual differences in physiological reactivity are relevantly associated with eating behavior traits. The findings suggest that parasympathetic and sympathetic profiles may represent distinct behavioral patterns with implications for targeted intervention. Full article

Background: Emerging evidence indicates that some individuals recovering from COVID-19 develop persistent symptoms, including fatigue, pain, cognitive difficulties, and psychological distress, commonly known as Long COVID. These symptoms often overlap with those seen in Chronic Fatigue Syndrome/Myalgic Encephalomyelitis (CFS/ME), underscoring the need for integrative, non-pharmacological interventions. This Phase II controlled trial aimed to evaluate the feasibility and preliminary efficacy of Heart Rate Variability Biofeedback (HRV-BF) in individuals with Long COVID who meet the diagnostic criteria for CFS/ME. Specific objectives included assessing feasibility indicators (drop-out rates, side effects, participant satisfaction) and changes in fatigue, depression, anxiety, pain, and health-related quality of life. Methods: Participants were assigned alternately and consecutively to the HRV-BF intervention or Treatment-as-usual (TAU), in a predefined 1:1 sequence (quasirandom assignment). The intervention consisted of 10 HRV-BF sessions, held twice weekly over 5 weeks, with each session including a 10 min respiratory preparation and 40 min of active training. Results: The overall drop-out rate was low (5.56%), and participants reported a generally high level of satisfaction. Regarding side effects, the mean total Simulator Sickness Questionnaire score was 24.31 (SD = 35.42), decreasing to 12.82 (SD = 15.24) after excluding an outlier. A significantly greater improvement in severe fatigue was observed in the experimental group (H = 4.083, p = 0.043). When considering all outcomes collectively, a tendency toward improvement was detected in the experimental group (binomial test, p < 0.0001). Conclusions: HRV-BF appears feasible and well tolerated. Findings support the need for Phase III trials to confirm its potential in mitigating fatigue in Long COVID. Full article

Wood, as a natural material that stores carbon, is gaining increasing attention and has potential for use in interior architectural applications. Given the long indoor stay time characteristic of modern society, it is important to scientifically understand the effects of indoor wood application on the occupants. In this study, three residential buildings with an identical area and structure were constructed with different degrees of wood coverage (0%, 45%, 90%) using Larix kaempferi. Subsequently, indoor air quality (IAQ) evaluations and relative humidity measurements were conducted to assess the physical and chemical changes in each environment. The IAQ in wooden and non-wooden environments met the recommended IAQ standards established in South Korea. The results of the 8-month observation showed that, the higher the wood coverage ratio, the more the indoor humidity fluctuations were alleviated, and, in the case of the 90% wood coverage ratio condition, the humidity was maintained 5.2% lower in the summer and 10.9% higher in the winter compared to the 0% condition. To further assess the physiological responses induced by the wooden environment, the heart rate variability (HRV) was measured and compared for 26 participants exposed to each environment for two hours. In environments with a 0% and 90% degree of wood coverage, no statistically significant differences were found in the participants’ HRV indicators. But, in the group exposed to the 45% wooden environment, the results showed an increase in HRV indicators, natural logarithm of high frequency power (lnHF): 4.87 → 5.40 (p < 0.05), and standard deviation of normal-to-normal intervals (SDNN): 30.57 → 38.48 (p < 0.05), which are known indicators of parasympathetic nervous system activation. Full article

Background/Objectives: Heart rate variability (HRV) has been widely investigated as a predictor of disease and mortality across diverse patient populations; however, there remains no consensus on the optimal set or combination of time and frequency domain nor on nonlinear features for reliable prediction across clinical contexts. Given the relevance of the COVID-19 pandemic and the unique clinical profiles of these patients, this retrospective observational study explored the potential of HRV analysis for early prediction of in-hospital mortality using ECG signals recorded during the initial moments of ICU admission in COVID-19 patients. Methods: HRV indices were extracted from four ECG leads (I, II, III, and aVF) using sliding windows of 2, 5, and 7 min across observation intervals of 15, 30, and 60 min. The raw data posed significant challenges in terms of structure, synchronization, and signal quality; thus, from an original set of 381 records from 321 patients, after data pre-processing steps, a final dataset of 82 patients was selected for analysis. To manage data complexity and evaluate predictive performance, two feature selection methods, four feature reduction techniques, and five classification models were applied to identify the optimal approach. Results: Among the feature aggregation methods, compiling feature means across patient windows (Method D) yielded the best results, particularly for longer observation intervals (e.g., using LDA, the best AUC of $0.82\pm 0.13$ was obtained with Method D versus $0.63\pm 0.09$ with Method C using 5 min windows). Linear Discriminant Analysis (LDA) was the most consistent classification algorithm, demonstrating robust performance across various time windows and further improvement with dimensionality reduction. Although Gradient Boosting and Random Forest also achieved high AUCs and F1-scores, their performance outcomes varied across time intervals. Conclusions: These findings support the feasibility and clinical relevance of using short-term HRV as a noninvasive, data-driven tool for early risk stratification in critical care, potentially guiding timely therapeutic decisions in high-risk ICU patients and thereby reducing in-hospital mortality. Full article

Objective: To investigate the effect of an 8-week inspiratory muscle training (IMT) intervention on respiratory muscle strength and cardiovascular autonomic regulation in obese young men. Methods: The study included 36 obese young men who met the inclusion and exclusion criteria. Participants were randomly divided into two groups: the IG (inspiratory muscle training group, n = 17), which underwent high-intensity IMT intervention for 8 weeks, 5 times a week, and the CG (control group, n = 18), which was not given any additional intervention. Assessed parameters included maximum inspiratory pressure (MIP), maximum expiratory pressure (MEP), systolic blood pressure (SBP), diastolic blood pressure (DBP), and heart rate (HR), as well as heart rate variability metrics such as the standard deviation of normal-to-normal intervals (SDNN), root mean square of successive differences (RMSSD), standard deviation of successive differences (SDSD), low-frequency power component (LF), high-frequency power component (HF), and LF/HF ratio. These measurements were taken both at baseline and following the completion of the 8-week intervention period. Results: After 8 weeks of IMT, the MIP and MEP of the IG increased by 31.8% and 26.5%, respectively (p < 0.01). In addition, SBP, DBP, and HR decreased by 2.2%, 3.2%, and 2.1%, respectively (p < 0.01). In the HRV time domain, SDNN and RMSSD increased by 54.1% and 33.5%, respectively (p < 0.01), and there was no significant improvement in SDSD (p > 0.05); in the HRV frequency domain, LF decreased by 40.5%, HF increased by 59.4% (p < 0.01), and the LF/HF ratio decreased by 58.2% (p < 0.05). Conclusion: An 8-week 80%MIP IMT intervention significantly improves respiratory muscle strength and cardiovascular autonomic regulation in obese young men, suggesting that IMT is a promising non-pharmacological strategy for mitigating obesity-related cardiovascular risk. Full article

Heart rate (HR) is strongly affected by the autonomic nervous system (ANS), while its spontaneous fluctuations, called heart rate variability (HRV), report about the dynamics of the complex, vegetative regulation of the heart rhythm. Hence, HRV is widely considered an important marker of the ANS effects on the cardiac system, and as such, a crucial diagnostic tool in cardiology. In order to obtain nontrivial results from HRV analysis, it would be desirable to establish exact, universal interrelations between the typical HRV parameters and HR itself. That, however, has not yet been fully accomplished. Hence, our aim was to perform a comparative statistical analysis of ECG recordings from a public database, with a focus on the HR dependence of typical HRV parameters. We revealed their fundamental connections, which were substantiated by basic mathematical considerations, and were experimentally demonstrated via the analysis of 24 h of ECG recordings of more than 200 healthy individuals. The large database allowed us to perform unique age-cohort analyses. We confirmed the HR dependence of typical time-domain parameters, such as RMSSD and SDNN, frequency-domain parameters such as the VLF, LF, and HF components, and nonlinear indices such as sample entropy and DFA exponents. In addition to shedding light on their relationship, we are the first, to our knowledge, to identify a new, diffuse structure in the VHF regime as an important indicator of SNS activity. In addition, the demonstrated age dependence of the HRV parameters gives important new insight into the long-term changes in the ANS regulation of the cardiac system. As a possible molecular physiological mechanism underlying our new findings, we suggest that they are associated with Piezo2 channel function and its age-related degradation. We expect our results to be utilized in HRV analysis related to both medical research and practice. Full article

Background/Objectives: Heart rate variability (HRV) is a marker of autonomic nervous system function, based on fluctuations in heartbeat intervals. Although several studies have investigated the association between frequency-domain HRV parameters and glaucoma, evidence based on large sample sizes remains limited. Therefore, the present study aimed to examine the relationship between frequency-domain HRV parameters and glaucoma subtypes, including primary open-angle glaucoma (PG) and exfoliation glaucoma (EG), using a larger sample size. Methods: Participants with primary open-angle glaucoma (PG), exfoliation glaucoma (EG), or no ocular disease other than cataract (controls) were recruited at Shimane University between June 2023 and July 2024. Frequency-domain HRV parameters (total power [TP], very-low-frequency [VLF], low-frequency [LF], high-frequency [HF], and LF/HF) were measured using a sphygmograph (TAS9 Pulse Analyzer Plus View). Group comparisons were conducted using unpaired t-tests, Fisher’s exact tests, and Tukey’s HSD test. Multivariate analyses were performed to identify factors associated with each HRV parameter. Results: A total of 809 participants were analyzed, including 522 with PG, 191 with EG, and 96 controls. The EG group showed significantly lower values across all frequency-domain HRV parameters compared to the PG group, and significantly lower LnLF values than the control group (p = 0.012). Multivariate analyses revealed that no significant associations were found between HRV measures and the presence of glaucoma or pseudoexfoliation material (PEM) deposition. Older age was significantly associated with lower values across all HRV parameters. Conclusions: In elderly glaucoma patients, age-related alterations in frequency-domain HRV parameters have been observed. Full article

This study investigates the effects of transcutaneous electroacupuncture stimulation (TEAS) on eyeblink rate, EEG, and heart rate variability (HRV), emphasising whether eyeblink data—often dismissed as artefacts—can serve as useful physiological markers. Sixty-six participants underwent four TEAS sessions with different stimulation frequencies (2.5, 10, 80, and 160 pps, with 160 pps as a low-amplitude sham). EEG, ECG, PPG, and respiration data were recorded before, during, and after stimulation. Using non-parametric statistical analyses, including Friedman’s test, Wilcoxon, Conover–Iman, and bootstrapping, the study found significant changes across eyeblink, EEG, and HRV measures. Eyeblink laterality, particularly at 2.5 and 10 pps, showed strong frequency-specific effects. EEG power asymmetry and spectral centroids were associated with HRV indices, and 2.5 pps stimulation produced the strongest parasympathetic HRV response. Blink rate correlated with increased sympathetic and decreased parasympathetic activity. Baseline HRV measures, such as lower heart rate, predicted participant dropout. Eyeblinks were analysed using BLINKER software (v. 1.1.0), and additional complexity and entropy (‘CEPS-BLINKER’) metrics were derived. These measures were more predictive of adverse reactions than EEG-derived indices. Overall, TEAS modulates multiple physiological markers in a frequency-specific manner. Eyeblink characteristics, especially laterality, may offer valuable insights into autonomic function and TEAS efficacy in neuromodulation research. Full article

Background/Objectives: Bruxism has been associated with dysregulation of the autonomic nervous system (ANS). Visceral manual therapy (VMT) has shown beneficial effects on the vagal tone and modulation of ANS activity. This study aimed to evaluate the immediate and short-term effects of VMT in individuals with clinically based bruxism. Methods: A single-blind randomized controlled trial was conducted including 24 individuals with clinically based bruxism. Participants received two sessions of either VMT or a sham placebo technique. Outcome measures included heart rate variability (HRV), both normal-to-normal intervals (HRV-SDNN), and the root mean square of successive normal-to-normal intervals (HRV-RMSSD), as well as muscle tone and stiffness and pressure pain thresholds (PPTs). Measurements were made at T1 (baseline), T2 (post-first intervention), T3 (pre-second intervention), T4 (post-second intervention), and T5 (4-week follow-up). Results: A significant time*group interaction was observed for HRV-SDNN (p = 0.04, η² = 0.12). No significant changes were found for muscle tone or stiffness. PPTs significantly increased at C4 after the second session (p = 0.049, η² = 0.16) and at the left temporalis muscle after the first session (p = 0.01, η² = 0.07). Conclusions: The findings suggest that two sessions of VMT may lead to significant improvements in HRV-SDNN compared to the placebo, suggesting a modulatory effect on autonomic function. No consistent changes were observed for the viscoelastic properties of the masticatory muscles. Isolated improvements in pressure pain sensitivity were found at C4 and the left temporalis muscle. Further research with larger sample sizes and long-term follow-up is needed to determine the clinical relevance of VMT in the management of signs and symptoms in individuals with bruxism. Full article

Heart rate variability (HRV), particularly the root mean square of successive differences (RMSSD), is widely used as a non-invasive indicator of autonomic nervous system activity and physiological recovery. This study examined whether daily short-term HRV, measured under standardised morning conditions, was associated with self-reported wellness in a non-clinical adult population. Over a 14-day period, 41 participants completed daily five-minute HRV recordings using a Polar H10 chest sensor and the Kubios mobile app, followed by ratings of sleep quality, fatigue, stress, and physical recovery. Bayesian ordinal mixed-effects models revealed that higher RMSSD values were associated with better self-reported sleep (β = 0.510, 95% HDI: 0.239 to 0.779), lower fatigue (β = 0.281, 95% HDI: 0.020 to 0.562), and reduced stress (β = 0.353, 95% HDI: 0.059 to 0.606), even after adjusting for covariates. No association was found between RMSSD and perceived muscle soreness. These findings support the interpretability of RMSSD as a physiological marker of daily recovery and stress in real-world settings. While the effect sizes were modest and individual variability remained substantial, results suggest that consistent HRV monitoring may offer meaningful insight into subjective wellness—particularly when contextualised and tracked over time. Full article

Background: Early identification of left ventricular ejection fraction (LVEF) levels during the progression of hypertension is essential to prevent cardiac deterioration. However, achieving a non-invasive, cost-effective, and definitive assessment is challenging. It has prompted us to develop a comprehensive machine learning framework for the automatic quantitative estimation of LVEF levels from electrocardiography (ECG) signals. Methods: We enrolled 200 hypertensive patients from Zhongshan City, Guangdong Province, China, from 1 November 2022 to 1 January 2025. Participants underwent 24 h Holter monitoring and echocardiography for LVEF estimation. We developed a comprehensive machine learning framework that initiated with preprocessed ECG signal in one-hour intervals to extract CMSE-based heart rate variability (HRV) features, then utilized machine learning models such as linear regression (LR), Support Vector Machines (SVMs), and random forests (RFs) with recursive feature elimination for optimal LVEF estimation. Results: The LR model, notably during early night interval (20:00–21:00), achieved a RMSE of 4.61% and a MAE of 3.74%, highlighting its superiority. Compared with other similar studies, key CMSE parameters (Scales 1, 5, Slope 1–5, and Area 1–5) can effectively enhance regression models’ estimation performance. Conclusion: Our findings suggest that CMSE-derived circadian HRV features from Holter ECG could serve as a non-invasive, cost-effective, and interpretable solution for LVEF assessment in community settings. From a machine learning interpretable perspective, the proposed method emphasized CMSE’s clinical potential in capturing autonomic dynamics and cardiac function fluctuations. Full article

This paper presents a Multimodal Hidden Markov Model (MHMM) framework specifically designed for real-time human proficiency assessment, integrating physiological (Heart Rate Variability (HRV)), behavioral (Task Completion Time (TCT)), and subjective (NASA Task Load Index (NASA-TLX)) data streams to infer latent human proficiency states in industrial settings. Using published empirical data from the surgical training literature, a comprehensive simulation study was conducted, with the MHMM (Trained) achieving 92.5% classification accuracy, significantly outperforming unimodal Hidden Markov Model (HMM) variants 61–63.9% and demonstrating competitive performance with advanced models such as Long Short-Term Memory (LSTM) networks 90%, and Conditional Random Field (CRF) 88.5%. The framework exhibited robustness across stress-test scenarios, including sensor noise, missing data, and imbalanced class distributions. A key advantage of the MHMM over black-box approaches is its interpretability by providing quantifiable transition probabilities that reveal learning rates, forgetting patterns, and contextual influences on proficiency dynamics. The model successfully captures context-dependent effects, including task complexity and cumulative fatigue, through dynamic transition matrices. When demonstrated through simulation, this framework establishes a foundation for developing adaptive operator-AI collaboration systems in Industry 5.0 environments. The MHMM’s combination of high accuracy, robustness, and interpretability makes it a promising candidate for future empirical validation in real-world industrial, healthcare, and training applications in which it is critical to understand and support human proficiency development. Full article

(1) Background: Physiological responses, such as heart rate and heart rate variability, have been increasingly utilized to monitor, detect, and predict mental stress. This review summarizes and synthesizes previous studies which analyzed the impact of mental stress on heart activity as well as mathematical, statistical, and visualization methods employed in such analyses. (2) Methods: A total of 119 articles were reviewed following the Systematic Reviews and Meta-Analyses extension for Scoping Reviews (PRISMA-ScR) guidelines. Non-English documents, studies not related to mental stress, and publications on machine learning techniques were excluded. Only peer-reviewed journals and conference proceedings were considered. (3) Results: The studies revealed that heart activities and behaviors changed during stressful events. The majority of the studies utilized descriptive statistical tests, including t-tests, analysis of variance (ANOVA), and correlation analysis, to assess the statistical significance between stress and non-stress events. However, most of them were performed in controlled laboratory settings. (4) Conclusions: Heart activity shows promise as an indicator for detecting stress events. This review highlights the application of time series techniques, such as autoregressive integrated moving average (ARIMA), detrended fluctuation analysis, and autocorrelation plots, to study heart rate rhythm or patterns associated with mental stress. These models analyze physiological data over time and may help in understanding acute and chronic cardiovascular responses to stress. Full article

This systematic review explores the role of smartwatches in stress management, mental health monitoring, and overall well-being. Drawing from 61 peer-reviewed studies published between 2016 and 2025, this review synthesizes empirical findings across diverse methodologies, including biometric data collection, machine learning algorithms, and user-centered design evaluations. Smartwatches, equipped with sensors for physiological signals such as heart rate, heart rate variability, electrodermal activity, and skin temperature, have demonstrated promise in detecting and predicting stress and mood fluctuations in both clinical and everyday contexts. This review emphasizes the need for interdisciplinary collaboration to advance technological precision, ethical data handling, and user experience design. Moreover, it highlights how different algorithms—such as Support Vector Machines (SVMs), Random Forests, Deep Neural Networks, and Boosting methods—perform across various physiological signals (e.g., HRV, EDA, skin temperature). Furthermore, it identifies performance trends and challenges across lab-based vs. real-world deployments, emphasizing the trade-off between generalizability and personalization in model design. Full article