Non-invasive detection of hemoglobin (Hb) concentration is of great clinical value for health screening and intraoperative blood transfusion. However, the accuracy and stability of non-invasive detection still need to be improved to meet clinical requirement. This paper proposes a non-invasive Hb detection method using ensemble extreme learning machine (EELM) regression based on eight-wavelength PhotoPlethysmoGraphic (PPG) signals. Firstly, a mathematical model for non-invasive Hb detection based on the Beer-Lambert law is established. Secondly, the captured eight-channel PPG signals are denoised and fifty-six feature values are extracted according to the derived mathematical model. Thirdly, a recursive feature elimination (RFE) algorithm is used to select the features that contribute most to the Hb prediction. Finally, a regression model is built by integrating several independent ELM models to improve prediction stability and accuracy. Experiments conducted on 249 clinical data points (199 cases as the training dataset and 50 cases as the test dataset) evaluate the proposed method, achieving a root mean square error (RMSE) of 1.72 g/dL and a Pearson correlation coefficient (PCC) of 0.76 (p < 0.01) between predicted and reference values. The results demonstrate that the proposed non-invasive Hb detection method exhibits a strong correlation with traditional invasive methods, suggesting its potential for non-invasive detection of Hb concentration.
23 January 2026 in The Clinical Respiratory Journal
Background: Traditional biometric systems are vulnerable to forgery, highlighting the need for secure alternatives. Electroencephalography (EEG) offers inherent advantages in liveness detection and antispoofing but typically requires external stimuli. We propose a novel paradigm leveraging intrinsic respiratory‐evoked EEG signals for identity authentication, with potential applications in clinical settings where unobtrusive monitoring is critical. Methods: We developed a 64‐channel EEG acquisition system with synchronized respiratory event monitoring. Thirteen healthy volunteers performed four breathing patterns: oral, nasal, slow nasal, and rapid nasal breathing. A hybrid deep learning model was designed to optimize spatial–temporal feature extraction from EEG signals. Results: The model achieved 98.3% accuracy in identity recognition using rapid nasal breathing‐evoked EEG, outperforming traditional biometric methods. Nasal breathing patterns consistently yielded higher accuracy than oral breathing, with rapid nasal breathing showing the strongest discriminative power. Conclusions: Respiratory‐evoked EEG signals provide a viable, noninvasive biometric identifier. The high accuracy of rapid nasal breathing opens avenues for clinical integration, such as continuous patient authentication in respiratory monitoring devices or secure access to electronic health records.
Objective: To compare electroencephalography (EEG)-based subject-identification and open-set rejection performance across experimental paradigms while examining model robustness and cross-session generalization. Methods: The M3CV database was analyzed across resting state, transient sensory stimulation, steady-state sensory stimulation, P300 Oddball, and motor execution. Closed-set identification was evaluated across feature representations, conventional machine-learning models, and raw-EEG deep-learning baselines. Open-set performance was further assessed using an identity-first leakage-free nested procedure with 60 enrolled identities, 15 development unknown identities, and 20 final-test unknown identities. Results: Under the P4 within-session protocol, transient sensory stimulation achieved the highest Rank-1 accuracy (98.10%). Differential entropy and shrinkage linear discriminant analysis achieved mean Rank-1 accuracies of 98.01% and 98.29%, respectively. Under leakage-free nested open-set evaluation, transient sensory stimulation achieved DIR@FPIR = 5%, DIR@FPIR = 1%, and AU-OSCR values of 91.75%, 77.32%, and 97.36%, respectively. Deep-learning analyses confirmed strong within-session identity discrimination but showed model-dependent open-set paradigm rankings. In contrast, strict cross-session transfer produced marked degradation across all model families, with Rank-1 accuracy falling to approximately 1.9–5.4% and verification AUC to approximately 0.53–0.56; unsupervised target normalization provided little recovery. Conclusions: EEG paradigms exhibited strong but largely session-dependent identity discriminability. Transient sensory stimulation provided the most favorable within-session open-set performance under the primary conventional framework, whereas cross-session variability dominated paradigm-dependent differences under zero-shot transfer.
Electroencephalogram (EEG)-based biometric sensing provides a promising pathway for secure and user-specific human authentication, but practical deployment remains limited by cross-session non-stationarity and potentially optimistic evaluation protocols caused by window- or event-level leakage. This study developed a cross-session EEG biometric sensing framework using interpretable spectral features and target-session calibration, with trial-level non-overlapping data partitioning to prevent overlap between training, calibration, and blind-test sets. Multi-channel EEG events were segmented into non-overlapping 2 s windows and aggregated into event-level samples to ensure strict isolation among training, validation, calibration, and blind testing subsets. Power spectral density, differential entropy, and log-variance features were evaluated using support vector machine, linear discriminant analysis, logistic regression, random forest, and a compact convolutional neural network designed for EEG decoding (EEGNet). Both closed-set identification and biometric verification were assessed using Rank-N accuracy, cumulative match characteristic curves, macro-F1, equal error rate, area under the curve, and true acceptance rate (TAR) at fixed false acceptance rate (FAR) levels. In the in-house cross-day dataset, limited target-session calibration improved Rank-1 accuracy from 44.82% to 98.70% for support vector machine (SVM) and from 19.93% to 99.94% for linear discriminant analysis (LDA). SVM with differential entropy achieved an equal error rate (EER) of 1.04 ± 0.60%, area under the receiver operating characteristic curve (AUC) of 0.9985 ± 0.0008, and TAR@FAR = 0.1% of 98.44 ± 1.06%. External validation on the public multi-session motor imagery dataset confirmed the calibration benefit. These results demonstrate strong closed-set identification and score-level verification performance under a cohort-wide, calibration-assisted cross-session experimental protocol.