Wearable devices are widely used for continuous health monitoring, yet reliable sleep tracking on emerging platforms remains underexplored due to reliance on proprietary algorithms and device-specific activity representations. We present a lightweight and reproducible sleep tracking pipeline that operates directly on raw accelerometer signals. The method converts data into epoch-level activity features, applies temporal smoothing and normalized scoring, and performs sleep/wake classification using a globally calibrated threshold. We calibrate the model on the Multilevel Monitoring of Activity and Sleep in Healthy People (MMASH) dataset and evaluate it in a cross-device study using the WeBe wearable platform and a commercial ActiGraph device. On MMASH, the method achieves a mean absolute error of 41.6 minutes in Total Sleep Time (TST), with onset and offset errors of 6.3 and 7.4 minutes. On real-world WeBe data from three participants across five sessions, it achieves a mean TST error of 27.4 minutes and onset and offset errors of 13.9 and 8.0 minutes. In contrast, a commercial ActiGraph pipeline shows larger discrepancies relative to ground truth. These results demonstrate accurate and generalizable sleep tracking using a simple and reproducible pipeline.

Blood oxygen saturation$(\text{SpO}_{2})$is a vital marker for healthcare monitoring. Traditional$\text{SpO}_{2}$estimation methods often rely on complex clinical calibration, making them unsuitable for low-power, wearable applications. In this paper, we propose a transfer learning-based framework for the rapid adaptation of$\mathrm{SpO}_{2}$estimation to energy-efficient wearable devices using low-sampling-rate (25Hz) dual-channel photoplethysmography (PPG). We first pretrain a bidirectional Long ShortTerm Memory (BiLSTM) model with self-attention on a public clinical dataset, then fine-tune it using data collected from our wearable We-Be band and an FDA-approved reference pulse oximeter. Experimental results show that our approach achieves a mean absolute error (MAE) of 2.967% on the public dataset and 2.624% on the private dataset, significantly outperforming traditional calibration and non-transferred machine learning baselines. Moreover, using 25Hz PPG reduces power consumption by 40% compared to 100 Hz, excluding baseline draw. Our method also attains an MAE of$3.284\%$in instantaneous$\mathrm{SpO}_{2}$prediction, effectively capturing rapid fluctuations. These results demonstrate the rapid adaptation of accurate, low-power$\mathrm{S p O}_{2}$monitoring on wearable devices without the need for clinical calibration.

Accurate and generalizable blood pressure (BP) estimation is vital for the early detection and management of cardiovascular diseases. In this study, we enforce subjectlevel data splitting on a public multi-wavelength photoplethysmography (PPG) dataset and propose a generalizable BP estimation framework based on curriculum-adversarial learning. Our approach combines curriculum learning, which transitions from hypertension classification to BP regression, with domainadversarial training that confuses subject identity to encourage the learning of subject-invariant features. Experiments show that multi-channel fusion consistently outperforms single-channel models. On the four-wavelength PPG dataset, our method achieves strong performance under strict subject-level splitting, with mean absolute errors (MAE) of 14.2mmHg for systolic blood pressure (SBP) and 6.4mmHg for diastolic blood pressure (DBP). Additionally, ablation studies validate the effectiveness of both the curriculum and adversarial components. These results highlight the potential of leveraging complementary information in multi-wavelength PPG and curriculum-adversarial strategies for accurate and robust BP estimation.

Wearable photoplethysmography (PPG) is embedded in billions of devices, yet its optical waveform is easily corrupted by motion, perfusion loss, and ambient light—jeopardizing downstream cardiometric analytics. Existing signal-quality assessment (SQA) methods rely either on brittle heuristics or on data-hungry supervised models. We introduce the first fully unsupervised SQA pipeline for wrist PPG. Stage 1 trains a contrastive 1-D ResNet-18 on 276 h of raw, unlabeled data from heterogeneous sources (varying in device and sampling frequency), yielding optical-emitter- and motioninvariant embeddings (i.e., the learned representation is stable across differences in LED wavelength, drive intensity, and device optics, as well as wrist motion). Stage 2 converts each 512-D encoder embedding into a 4-D topological signature via persistent homology (PH) and clusters these signatures with HDBSCAN. To produce a binary signal-quality index (SQI), the acceptable PPG signals are represented by the densest cluster while the remaining clusters are assumed to mainly contain poor-quality PPG signals. Without re-tuning, the SQI attains Silhouette, Davies-Bouldin, and Calinski-Harabasz scores of$0.72,0.34$, and 6,173, respectively, on a stratified sample of 10,000 windows. In this study, we propose a hybrid self-supervised-learning-topological-dataanalysis (SSL-TDA) framework that offers a drop-in, scalable, cross-device quality gate for PPG signals.

Multimodal unsupervised domain adaptation leverages un-labeled data in the target domain to enhance multimodal systems continuously. While current state-of-the-art methods encourage interaction between sub-models of different modalities through pseudo-labeling and feature-level exchange, varying sample quality across modalities can lead to the propagation of inaccurate information, resulting in error accumulation. To address this, we propose Modal-Affinity Multimodal Domain Adaptation (MODfinity), a method that dynamically manages multimodal information flow through fine-grained control over teacher model selection, guiding information intertwining at both feature and label levels. By treating labels as an independent modality, MODfinity enables balanced performance assessment across modalities, employing a novel modal-affinity measurement to evaluate information quality. Additionally, we introduce a modal-affinity distillation technique to control sample-level information exchange, ensuring reliable multimodal interaction based on affinity evaluations within the feature space. Extensive experiments on three multimodal datasets demonstrate that our framework consistently outperforms state-of-the-art methods, particularly in high-noise environments.

Automatic pain assessment in postoperative children is crucial for monitoring their health and preventing potential complications. However, the automatic pain assessment still faces the following challenges. Firstly, the individual variation of painful expressions in children enhances the difficulty of mapping diverse features of expressions to pain scores accurately. Secondly, the imbalanced label distribution caused by abundant non-painful samples usually makes the model more likely to predict an unexpectedly lower pain score. To address the above challenges, we propose a novel multi-modal multi-expert framework, namelyMMF, for postoperative pain assessment in children. Specifically, the samples are clustered in each modality to train multiple expert models, each focusing on a smaller feature subspace for easier regression of pain scores. Meanwhile, some expert models are allocated to rare painful samples to relieve the side effects caused by the imbalanced distribution of labels. Moreover, a confidence-based integration of multi-modal features from multiple experts is made to achieve a more accurate final prediction. Experimental results show thatMMFexhibits superior accuracy of pain assessment on the multi-modal pain database collected from postoperative children by us. In particular,MMFcan achieve the mean absolute error (MAE) of 1.03 and the Pearson correlation coefficient (PCC) of 0.88.

Soft skills, such as personality characteristics, communication skills and leadership, affect personal career performance greatly. Therefore, predicting the soft skills of interviewees can provide interviewers with a strong reference for the decision of hiring. Nowadays, as asynchronous video interviews have gradually become a popular form of interviews, automatic interview evaluation of soft skills has attracted widespread attention from researchers. However, existing automatic evaluation methods have two significant drawbacks. Firstly, most of them model the problem as multi-modal fusion of long-term sequences, while ignoring the consistency of multi-modal expression in short-time windows, which is a key attribute of the interview scene. Secondly, without embedding of professional knowledge in the interview field, the interpretability of the model is relatively weak. To address the above problems, we propose a novelMulti-modal Window-Consistency Fusionnetwork, namely MWCF, to capture the expression consistency of different modalities in a short-time window and re-weight the language signals to enhance important portions in verbal clues. Meanwhile, in order to enhance the interpretability of the evaluation model, we introduce the professional knowledge of interviewers by proposing a topic generation module based on question attention, and embedding the most representative keywords under different soft skills into the model. Furthermore, a real-world interview dataset is built by developing an asynchronous interview platform, and extensive experiments are conducted to show the superior performance of our proposed model.