From High-SNR Radar Signal to ECG: A Transfer Learning Model with Cardio-Focusing Algorithm for Scenarios with Limited Data

2025-06-24

AI Summary

Radar-based remote electrocardiogram (ECG) estimation faces challenges in new scenarios due to severe scarcity of synchronized radar-ECG paired data and uncontrolled radar signal quality. Method: We propose a few-shot radar-to-ECG recovery framework. First, we design the Cardio-Focusing and Tracking (CFT) algorithm for robust, dynamic localization of the cardiac region. Then, we introduce RFcardi—a sparsity-driven transfer learning architecture—that leverages prior knowledge of cardiac motion dynamics and enables effective fine-tuning with only 5–10 synchronized radar-ECG pairs. This end-to-end method operates reliably even with low-quality radar inputs, significantly reducing reliance on large-scale annotated datasets and high-end hardware. Contribution/Results: CFT achieves sub-3.2 mm localization error; RFcardi attains near–fully supervised performance with just five samples—yielding QRS-complex fidelity with SNR > 28 dB and RMSE < 0.015 mV. Our approach establishes a novel paradigm for contactless, low-barrier ECG monitoring.

Technology Category

• Intelligent Robots: State Estimation
• Machine Learning: Calibration & Uncertainty Quantification
• Planning, Routing, and Scheduling: Activity and Plan Recognition

Application Category

• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments
• Security and Privacy: Large-scale security measurements

Abstract

Electrocardiogram (ECG), as a crucial find-grained cardiac feature, has been successfully recovered from radar signals in the literature, but the performance heavily relies on the high-quality radar signal and numerous radar-ECG pairs for training, restricting the applications in new scenarios due to data scarcity. Therefore, this work will focus on radar-based ECG recovery in new scenarios with limited data and propose a cardio-focusing and -tracking (CFT) algorithm to precisely track the cardiac location to ensure an efficient acquisition of high-quality radar signals. Furthermore, a transfer learning model (RFcardi) is proposed to extract cardio-related information from the radar signal without ECG ground truth based on the intrinsic sparsity of cardiac features, and only a few synchronous radar-ECG pairs are required to fine-tune the pre-trained model for the ECG recovery. The experimental results reveal that the proposed CFT can dynamically identify the cardiac location, and the RFcardi model can effectively generate faithful ECG recoveries after using a small number of radar-ECG pairs for training. The code and dataset are available after the publication.

Problem

• Recover ECG from radar signals with limited data
• Track cardiac location for high-quality radar signals
• Transfer learning model reduces need for ECG ground truth

Innovation

• Cardio-focusing algorithm tracks heart location precisely
• Transfer learning model extracts cardio data without ECG
• Few radar-ECG pairs needed for fine-tuning model