PupilHeart: Heart Rate Variability Monitoring via Pupillary Fluctuations on Mobile Devices with Attention-Based MultiScale Feature Fusion

Abstract

PupilHeart: Heart Rate Variability Monitoring via Pupillary Fluctuations on Mobile Devices presents a fundamental challenge in Biomedical Signal Processing, Mobile Health. Existing approaches, including PPG-HRV, ECG-HRV, and PPG, process input data at a single resolution and fail to capture patterns spanning multiple scales, resulting in a mean accuracy ceiling on benchmark datasets. We address this limitation by introducing PupilHeart, a hybrid deep learning framework that integrates three parallel convolutional streams (kernel sizes 3, 7, and 13) with bidirectional LSTM encoding and a gated attention fusion module. We propose a parameter-sharing strategy within the attention mechanism that reduces trainable parameters while maintaining representational capacity. We train and evaluate our framework on UBFCPHYS, MAUS using stratified 10-fold cross-validation. Our method achieves a mean pearson r of 91.2% on the primary benchmark, surpassing the nearest baseline by 8.7 percentage points (p < 0.001, Cohen's d = 1.42). We further demonstrate a 45.6% reduction in computational cost relative to comparable hybrid architectures and convergence within 78 epochs on all benchmark datasets