Search Results (273)

Recent studies have shown that common household activities produce characteristic patterns in indoor air pollutants, enabling activity inference using environmental measurements alone. However, pollutant-based approaches are usually formulated as flat multi-class classification problems, even though indoor environments are dominated by long baseline periods with no emission-generating activity, leading to false alarms and unstable predictions. This work proposes a gated hierarchical inference framework for recognizing activities from indoor air quality data. A first-stage gate detects whether a time window contains activity-induced pollutant dynamics, while a second-stage classifier conditionally identifies the specific activity only when activity relevance is detected. Multivariate time-series measurements of particulate matter, volatile organic compounds, nitrogen oxides, carbon dioxide, temperature and relative humidity were collected using a portable monitoring system during controlled household cooking and cleaning experiments. Temporal windows were processed using recurrent neural network models in both stages. By separating activity detection from activity identification, the proposed method aligns inference with the physical generation of indoor pollutant signals and improves robustness in baseline-dominated monitoring scenarios while maintaining reliable discrimination among activities. The framework supports unobtrusive activity recognition and enables applications in exposure-aware monitoring and intelligent indoor environmental management. Full article

The growing prevalence of chronic diseases, population aging, and the shift toward preventive and personalized care under Healthcare 5.0 have increased the need for continuous health monitoring beyond clinical settings. While wearable devices enable remote monitoring, their long-term use is often limited by user compliance, comfort issues, battery dependence, and disruption of daily routines. To address these limitations, unobtrusive home-based health monitoring systems have emerged, integrating sensing technologies into domestic environments and everyday objects. This review provides a system-level analysis of unobtrusive health monitoring technologies for smart homes. It examines seven major sensing approaches, including camera-, laser-, radar-, infrared-, mechanical-, bioelectrical-, and optical-based sensors, and their integration into four home environments: living areas, bathrooms, bedrooms, and home offices. For each sensing modality, the operating principles, monitored physiological parameters, representative applications, and key advantages and limitations are discussed. Overall, existing solutions reveal trade-offs among measurement accuracy, robustness in real home conditions, energy autonomy, privacy preservation, and user acceptance. Heart rate and respiratory rate are the most commonly monitored parameters, while multimodal and clinically validated systems remain limited. Although unobtrusive sensing technologies show strong potential for proactive and personalized healthcare, challenges related to accuracy, interoperability, privacy, and cost continue to hinder large-scale adoption. Full article

Previous studies on healthy controls suggest the added value of thigh-based Electrocardiography (ECG), which collects data using sensors embedded in a toilet seat for unobtrusive signal acquisition. However, further evidence regarding its clinical feasibility is needed; with this work, we investigated three complementary aspects: signal quality, morphological correlation with standard ECG leads, and the system’s potential for heart rate variability (HRV) analysis in patients undergoing aortic valve replacement. This work was divided into two main phases. In the first, 32 healthy volunteers underwent simultaneous ECG recordings using both a standard 12-lead ECG system and the thigh-based system. Signal Quality Index (SQI) analysis revealed that 56.25% of the experimental signals were classified as excellent, and over 62.5% of recordings showed a strong correlation with Lead I of the clinical ECG. These findings extend the state of the art by further characterising the quality and relevance of the captured signals. In the second phase, two patients with severe aortic stenosis were monitored before and after surgical valve replacement. HRV metrics derived from the thigh-based ECG captured distinct autonomic responses: one patient showed significant postoperative improvement in global and parasympathetic modulation (increased SDNN, RMSSD, and Sample Entropy), while the other exhibited reduced variability and complexity, potentially indicating impaired autonomic recovery. These results highlight the feasibility of thigh-based ECG data acquisition for passive, longitudinal cardiac health monitoring in everyday environments and its applicability for pre- and postoperative autonomic assessment. Full article

Blood pressure monitoring is important for overall health assessment, yet traditional cuff-based methods are intrusive and unsuitable for continuous monitoring. This paper proposes a contactless approach for blood pressure estimation from facial videos using a bidirectional Mamba-based architecture with uncertainty quantification. Our method processes 64-frame video segments through a hierarchical 3D convolutional encoder to extract spatiotemporal features, then applies bidirectional state-space modeling to capture temporal dynamics efficiently. The model was evaluated on the Vitals for Vision (V4V) dataset, achieving mean absolute errors of 13.15 mmHg for systolic and 9.56 mmHg for diastolic blood pressure, outperforming prior methods while requiring significantly fewer computational resources than attention-based approaches. While these results do not meet clinical-grade diagnostic standards, they demonstrate the feasibility of contactless blood pressure estimation for non-clinical applications such as wellness monitoring, preliminary health screening, and continuous remote observation, where unobtrusive and computationally efficient monitoring is desirable. Full article

Accurate sleep stage classification is essential for evaluating sleep quality, yet clinical polysomnography is impractical for continuous home-based monitoring. Ballistocardiography (BCG) enables unobtrusive sleep monitoring through sensors embedded in sleep furniture; however, existing BCG-based approaches either rely on complex physiological feature extraction or employ fixed-parameter signal-to-image transformations that cannot adapt to inter-subject variability. This study proposes a learnable recurrence plot (RP) framework for three-stage sleep classification (Wake, NREM, REM) from single-channel BCG signals. The Learnable RP introduces three innovations: multi-scale phase-space reconstruction at physiologically motivated time delays (τ = 5, 10, 20), differentiable per-scale thresholds optimized end-to-end, and attention-based spatial fusion of multi-scale recurrence maps. The framework was evaluated through 10-fold stratified cross-validation across six backbone architectures using 50 overnight recordings. The Learnable RP consistently outperformed four baseline transformation methods (GAF, MTF, Classical RP, Modified RP), achieving an aggregate mean accuracy of 73.60%, with EfficientNet-B5 reaching 78.91%. and 78.91%. Statistical validation across all 24 pairwise comparisons (4 baselines × 6 backbones) confirmed consistent superiority (all p < 0.001). The proposed framework achieves competitive performance without explicit physiological feature engineering, offering a viable path toward end-to-end unobtrusive sleep monitoring. Full article

The integration of artificial intelligence with unobtrusive sensing technologies is transforming occupational health monitoring by enabling continuous, objective assessment of worker activities in real industrial environments. This study focuses on the accurate recognition of subtle motion actions within logistics workflows using multichannel optical motion-capture data. We investigate several deep learning architectures commonly employed for temporal motion analysis, including tCNN, Transformer, CNN–LSTM, and ConvLSTM. To enhance robustness and fairness across workers with varying movement styles, a subject-independent evaluation protocol is adopted, and a multiscale temporal learning strategy is explored to better capture fine-grained and low-saliency actions. Experimental results show that the proposed multiscale tCNN achieves the highest accuracy, obtaining per-class recall range between 73% and 83% and an overall accuracy of approximately 79%, consistently outperforming recurrent and attention-based architectures. These findings demonstrate the effectiveness of multiscale convolution-based temporal modeling for recognizing subtle motion actions and highlight the potential of combining optical motion capture with AI analytics to support unobtrusive, reliable occupational health monitoring in smart industry environments. Full article

Respiratory rate (RR) is a critical indicator of physiological status, yet unobtrusive and continuous RR monitoring remains challenging, particularly in wearable applications that require soft, lightweight, and low-power sensing systems. This paper presents an integrated approach that combines a textile-embedded embroidered strain-gauge sensor with Tiny Machine Learning (TinyML) to enable real-time, on-device RR estimation. The sensing platform consists of a textile-integrated meander-pattern strain gauge and a fabric-mounted analog readout circuit, which together capture thoracic expansion during breathing. Two lightweight neural network models—a convolutional neural network (CNN) operating on raw respiratory waveforms and a dense neural network (DNN) operating on wavelet features—were developed and trained using a public strain-sensor dataset and a custom dataset collected with the textile system (TexHype dataset). Both models were optimized through 8-bit quantization and deployed to an STM32L4 microcontroller, where end-to-end on-device preprocessing, filtering, segmentation, normalization, and inference were performed. The CNN achieved the highest accuracy, with a mean absolute error (MAE) of 1.23 breaths per minute (BPM) on the TexHype dataset, but exhibited substantial inference latency (5.8–6.2 s) due to its computational complexity. In contrast, the wavelet-based DNN demonstrated lower accuracy (MAE 2.21 BPM) but achieved real-time performance with inference times of 18–96 ms, and a power overhead ($\Delta P=P_{\mathrm{active}}-P_{\mathrm{idle}}$) of approximately 3.3 mW during inference. Cross-dataset testing revealed limited generalization between different strain-sensor platforms. The findings highlight key trade-offs between accuracy, latency, and energy efficiency, and illustrate the potential of combining stretchable electronics with embedded intelligence to enable next-generation wearable respiratory monitoring systems. Full article

Sleep quality is closely associated with cardiovascular, metabolic, and mental health outcomes, yet the clinical gold standard, polysomnography (PSG), is costly and intrusive for long-term home monitoring. Ballistocardiography (BCG) enables unobtrusive in-bed sensing and is therefore attractive for low-burden sleep assessment in natural environments. However, most existing BCG studies are PSG-referenced and mainly focus on sleep staging, while movement and out-of-bed episodes are often treated as artifacts rather than modeled jointly. In this study, we propose an interpretable unsupervised proxy-state modeling framework for three-state in-bed monitoring from BCG signals under an unlabeled setting. BCG recordings were segmented into 30 s windows with 50% overlap, and multi-domain features were extracted from waveform morphology, spectral power, heart rate-related dynamics, and wavelet energy distribution. K-means clustering (K = 3) was used to construct cluster-derived proxy labels, TreeSHAP-based feature ranking together with inner-CV-guided Top-N subset selection was used for training-only feature screening, and multiple classifiers were compared under a strict leave-one-subject-out protocol, with an ROA-optimized RBF-SVM achieving the best overall performance. Using data from 32 volunteers, the framework achieved an accuracy of 0.9932 ± 0.0047 (mean ± SD), together with consistently strong Macro-F1 and MCC scores. Overall, it outperformed the alternative methods compared in this study. Full article

Photoplethysmography (PPG) has emerged as an attractive modality for non-invasive cardiovascular monitoring due to its low cost, unobtrusive nature, and ubiquity in consumer wearable devices. Despite its potential, existing PPG-based arrhythmia detection systems remain limited in scope: (i) most target only atrial fibrillation, (ii) temporal localization of abnormal segments is rarely provided, and (iii) deep learning models lack explainability, hindering adoption in clinical workflows. We present a comprehensive and fully integrated framework for multi-class arrhythmia detection, segmentation, and explainability based on PPG waveforms, Heart Rate Variability (HRV), and structured clinical metadata. The proposed system introduces a CLIP-style contrastive learning module aligning PPG waveforms with clinical variables and rhythm-state textual descriptions using BioBERT; a multitask U-Net architecture performing 4-class classification and 1D segmentation; a Retrieval-Augmented Generation (RAG) pipeline leveraging Gemini Flash large language models to produce guideline-grounded diagnostic reports; and a real-time Streamlit-based web platform supporting inference, visualization, and database storage. The system significantly improves classification accuracy (from 86.27% to 91.19%) and segmentation Dice (from 0.5815 to 0.7167). These results demonstrate the feasibility of a robust, multimodal, and explainable PPG-based arrhythmia monitoring system for real-world applications. Full article

Motion sickness (MS), or kinetosis, is a condition experienced by some individuals in response to rhythmic or irregular body motion. Multiple studies have explored its neurobiological mechanisms and countermeasures, with the sensory-conflict hypothesis remaining the most accepted explanation. Heart-rate variability (HRV) and electrocardiography provide complementary autonomic nervous system perspectives that may support MS assessments. From an applied viewpoint, reliable HRV markers could enable the early detection and continuous monitoring of MS in real-world contexts, such as autonomous vehicles, where passenger comfort and safety are critical, motivating contact-free cardiac sensing for unobtrusive monitoring. This systematic review examines the value of HRV indices in MS, conducted under PRISMA guidelines across PubMed, Scopus, and the Web of Science. The included studies were grouped into four categories based on the methods used to induce MS: mechanical stimulus, real trip, visual stimulus, and virtual reality. Aggregated findings indicate that frequency–domain metrics, particularly the low frequency (LF)/high frequency (HF) ratio, HF power, and mean heart rate (mHR), are most frequently reported in relation to MS. Overall, autonomic dysregulation likely contributes to MS susceptibility, but standardized protocols are needed to validate HRV as a reliable marker. Full article

Falls represent a major health risk for older adults living independently, motivating the development of unobtrusive and privacy-preserving monitoring solutions. This study investigates whether Bluetooth Low Energy (BLE) 6.0 Channel Sounding (CS) can support device-free fall detection using low-complexity signal representations suitable for residential deployment. The proposed system employs two BLE nodes performing periodic channel sounding, from which only scalar distance estimates are extracted. Time-domain and temporal-dynamic features are computed from sliding windows of the distance signal and used for supervised classification. Three widely used classifiers—Support Vector Machine with radial basis function kernel, Random Forest, and gradient-boosted decision trees (XGBoost)—are evaluated under both a default operating point and a sensitivity-first regime achieved through validation-based decision threshold adjustment, reflecting the higher cost of missed fall detections in assisted living scenarios. Experiments conducted in a furnished indoor environment with six participants performing realistic fall and non-fall scenarios demonstrate strong window-level sensitivity under subject-independent evaluation, with XGBoost providing the most favorable sensitivity–specificity balance. Under sensitivity-first operation, very high recall is achieved at the expense of increased false alarms. Given the limited dataset and single-environment setting, the reported results should be interpreted as a proof-of-concept demonstration of feasibility rather than definitive large-scale performance. The findings suggest that BLE CS captures motion-relevant signal variations that may support practical fall detection while maintaining low deployment complexity and privacy preservation. Full article

Gait is a sensitive marker of mobility decline and fall risk, motivating unobtrusive sensing methods that can extract spatiotemporal parameters outside specialized gait laboratories. This paper presents a physics-based comparison of two millimeter-wave frequency-modulated continuous-wave (FMCW) radar deployment paradigms using a low-cost, system-on-chip (SoC) 60 GHz Infineon BGT60TR13C radar sensor: (i) a fixed (tripod-mounted) corridor observer and (ii) a shoe-mounted body-centric configuration attached to the medial side of the left shoe. Four healthy adult author-participants performed repeated 30 s corridor trials under five gait styles (regular, slow, fast, simulated festination, and simulated freezing-of-gait), including brief pauses during turns; an empty-corridor recording was acquired to characterize static clutter. Step events were detected using peak-picking on foot-related velocity envelopes with adaptive thresholds, and step count, cadence, step time, and step-time variability were derived. Performance of the fixed and shoe-mounted configurations was quantitatively compared to video ground truth using mean absolute percentage error (MAPE) for step count estimation. Across all gait styles, the shoe-mounted FMCW radar consistently reduced step-count error relative to the fixed corridor-mounted configuration, with the largest gains under irregular patterns (e.g., festination: 37.1% fixed vs. 9.6% shoe-mounted). These findings highlight the advantages of body-centric millimeter-wave radar sensing and support low-cost SoC radar as a pathway toward wearable, privacy-preserving gait monitoring in real-world environments. Full article

Sleep apnea–hypopnea syndrome (SAHS) is a common sleep-related breathing disorder associated with substantial cardiovascular and neurocognitive risks. Although polysomnography (PSG) remains the clinical gold standard for diagnosis, its cost, operational burden, and limited accessibility hinder scalable and longitudinal home monitoring. Frequency-modulated continuous-wave (FMCW) radar provides unobtrusive, non-contact respiration sensing, yet radar-based event detection is often constrained by scarce annotations and pronounced domain shifts relative to PSG signals. In this work, we propose a deep learning framework for apnea–hypopnea event detection from FMCW radar that combines a 1D U-Net segmentation backbone with multi-head self-attention (MHSA) and cross-modality transfer learning. The model was first pre-trained on a large public PSG dataset to learn transferable respiratory-event representations and then fine-tuned on a smaller clinically annotated radar respiration dataset using synchronized PSG labels. It produced per-sample event probabilities, which were further refined via temporal post-processing to generate event-level detections and apnea–hypopnea index (AHI) estimates. Experimental results demonstrate strong performance in the radar domain, achieving precision of $0.8137\pm 0.0332$, recall of $0.8369\pm 0.0470$, and an F1-score of $0.8167\pm 0.0052$. Overall, these results indicate that PSG-to-radar transfer learning enables accurate, low-cost, and non-contact sleep apnea screening, supporting scalable longitudinal monitoring in home-like settings. Full article

Background/Objectives: Automatic evaluation of Parkinson’s disease (PD) progression is an emerging topic that deserves special attention from the research community. Unobtrusive, low-cost technology is essential for monitoring PD patients in remote areas. This paper proposes the use of phonological posteriors to create models that allow the progression of dysarthria level progression to be modelled based on speech recordings. Methods: Eighteen Gated Recurrent Units (GRUs) are used to estimate an equal number of phonological classes assigned to each phoneme pronounced in a given recording. Classification models of PD vs. healthy control (HC) subjects are trained with recordings of the PC-GITA corpus. This information is used in a separate corpus, with longitudinal recordings, to evaluate whether the progression of the dysarthria level, according to the modified Frenchay Dysarthria Assessment (mFDA), is related to abnormal production of specific phonemes. Results: Strident, dental, pause, back, and continuant phonological classes are the ones that better explain dysarthria level progression within time-frames of at least two years, therefore allowing possible monitoring of disease progression. Conclusions: Speech is a low-cost biosignal that can be used to automatically assess PD progression. In particular, this study shows that such an assessment makes it possible to evaluate dysarthria level progression and to find which phonological classes are contributing the most to such a progression. We believe that the findings reported in this paper provide objective evidence about possible abnormalities in broader speech-related processes like respiration, therefore contributing a better understanding of the relationship between speech production patterns and other speech-related processes affected when suffering from PD. Full article

Background: Cardiovascular disease (CVD) is the leading cause of mortality worldwide, creating demand for continuous, unobtrusive monitoring solutions. This clinical validation evaluates the accuracy of remote photoplethysmography (rPPG), a contactless method using camera video, for measuring pulse rate (PR) in patients with CVD. Methods: We enrolled 50 adults with confirmed CVD at a clinical trial center. In a 6 min rested session, synchronized facial video (under controlled lighting), electrocardiogram (ECG), and photoplethysmography (PPG) signals were recorded. PR was derived from 25 s video segments using rPPG-enabled software and compared to ECG-derived PR via regression and Bland–Altman analysis. Results: Data from 47 participants (n = 817 samples) were analyzed. rPPG-derived PR showed strong agreement with ECG, with a mean absolute error of 1.061 bpm, root-mean-squared error of 2.845 bpm, and Pearson correlation of 0.962. Mixed-effects regression analyses (after 2% outlier removal, n = 782) indicated minimal influence from demographic, environmental, or CVD factors on accuracy. PPG-ECG discrepancies reflected inherent methodological differences. Conclusion: The rPPG method provides accurate, contactless PR monitoring in CVD patients, supporting its potential for remote patient monitoring and early deterioration detection. Future work will validate rPPG for irregular rhythms, additional vital signs, and diverse cohorts to strengthen clinical robustness for cardiometabolic risk assessment. Full article