This paper presents an end-to-end spatial-temporal transformer framework for remote heart-rate estimation from RGB camera images under varying illumination.

DSTAN-Med is a novel dual-channel attention framework that significantly improves False Data Injection (FDI) attack detection in IoMT medical devices by explicitly separating spatial and temporal depe…

Adaptive data selection significantly improves wearable prediction performance, particularly for individuals with poor baseline health metrics, suggesting that selective data sampling should be tailor…

The paper proposes a novel convolutional block and optimization algorithm to implement resource-efficient 1D-CNNs for atrial fibrillation detection on tiny smart sensor systems, achieving high accurac…

VitalAgent is a novel tool-augmented agentic framework that significantly improves physiological monitoring from wearable health data by enabling both reactive question answering and proactive, long-t…

The paper introduces ArrythML, a highly efficient autoencoder-based TinyML model that enables accurate, low-power arrhythmia detection directly on resource-constrained embedded wearable devices.

This paper introduces LVCG, a novel self-supervised framework that learns unified, view-invariant latent representations of cardiac electrical activity directly in the physically grounded Vectorcardio…

The paper introduces FHRFormer, a masked transformer-based autoencoder designed to accurately reconstruct missing and forecast fetal heart rate (FHR) time-series data, thereby enabling robust AI-based…

The paper introduces CardioLens, a rigorous evaluation testbed for multi-sequence Cardiac MRI, which reveals that current Multimodal Large Language Models (MLLMs) exhibit a significant 'clinical reali…

The paper introduces Score-Guided Classification (SGC), a novel framework that uses an unsupervised anomaly score as a 'Pathological Prior' to guide EEG-based depression detection, overcoming the limi…

The paper formally proves a theorem regarding adversarial noise amplification and proposes a novel, lightweight detection mechanism that uses this enhanced signal for robust adversarial defense.

The paper proposes Family-Grouped Hierarchical Federated Learning (Family-FL) combined with a highly optimized Tiny CNN-LSTM model to enable privacy-preserving ECG monitoring on ultra-resource-constra…

The paper proposes the Distilled Explanation Model (DEM), a novel glass-box framework that achieves high-accuracy, clinically interpretable anomaly detection in physiological sensor data by distilling…

The paper introduces Dual-Spectral Flow Matching (DSFM), a novel generative framework that uses wavelet and cosine transforms to synthesize highly realistic, non-stationary fMRI time series for improv…

The paper proposes an attention-guided hybrid framework combining 1D and 2D CNNs to robustly enhance ECG-based biometric recognition, achieving high accuracy across multiple datasets and demonstrating…

The paper introduces a novel simulation strategy that integrates speckle decorrelation measures from real videos to create a photorealistic dataset, enabling a deep learning algorithm that achieves st…

This paper identifies prediction bias, a failure mode of entropy minimization in test-time adaptation, and proposes Distribution Shift Bias Reduction (DSBR) to stabilize adaptation and prevent model c…