AVAESA: Adaptive VAE With Self-attention and Learnable Signal Processing for Robust Radar-based Heart Rate Estimation
Date
Authors
Shirazi, Mohammad Hossein
Yongchareon, Sira
Singh, Anuradha
Ma, Jing
Supervisor
Item type
Journal Article
Degree name
Journal Title
Journal ISSN
Volume Title
Publisher
Elsevier BV
Abstract
Non-contact heart rate monitoring using radar sensors offers significant advantages for healthcare and automotive applications by preserving privacy while enabling continuous physiological assessment. Current Variational Autoencoder (VAE) approaches for radar-based vital sign monitoring, while superior to traditional neural networks, suffer from fixed preprocessing assumptions and inadequate temporal modeling that limit their generalization across diverse measurement conditions. This study introduces AVAESA (Adaptive VAE with Self-Attention and Learnable Signal Processing), a novel architecture that addresses these limitations through three key innovations: dual-stream in-phase/quadrature signal processing that preserves critical phase relationships, multi-head self-attention mechanisms for enhanced temporal dependency modeling, and adaptive signal preprocessing with learnable parameters that derive frequency bands and processing weights directly from input signal characteristics. The framework was evaluated on 1920 measurements from 10 participants across 48 measurement scenarios (4 distances × 3 angles × 4 orientations), assessing cross-scenario robustness under varied measurement conditions, with Polar H10 chest strap ground truth validation. Comprehensive comparison against multiple architectures (CNN, LSTM, Bi-LSTM, TCN, VAE) with statistical significance testing demonstrates substantial performance improvements, with mean absolute error reductions ranging from 17.3% under optimal conditions to 62.6% under challenging cross-scenario generalization scenarios. AVAESA maintains high accuracy (correlation coefficient > 0.86, R² > 0.84) even under challenging measurement conditions where baseline approaches exhibit degraded performance, demonstrating potential for contactless cardiac monitoring systems across diverse measurement environments through improved cross-scenario robustness.Description
Keywords
46 Information and computing sciences, Non-intrusive vital sign monitoring, Machine learning, Radar, Generative models, Attention modules, Variational autoencoders
Source
Internet of Things, ISSN: 2542-6605 (Print), Elsevier BV, 101931-101931. doi: 10.1016/j.iot.2026.101931
Publisher's version
Rights statement
© 2026 The Author(s). Published by Elsevier B.V. This is an open access article distributed under the terms of the Creative Commons CC-BY license, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. You are not required to obtain permission to reuse this article.