Recover from Horcrux: A Spectrogram Augmentation Method for Cardiac Feature Monitoring from Radar Signal Components

2025-03-25

AI Summary

In radar-based non-contact heart rate monitoring, label scarcity—particularly the challenge of jointly optimizing heartbeat classification and ECG waveform regression—remains a critical bottleneck. To address this, we propose Horcrux, a novel spectrogram augmentation method. Horcrux introduces the first structured time-frequency spectrogram augmentation paradigm explicitly designed for regression tasks: it injects controllable zero-value mask regions into spectrograms to enhance discriminability of subtle cardiac features while preserving ground-truth continuity and increasing augmentation diversity. Integrated with deep neural networks via joint optimization, Horcrux effectively alleviates the small-sample limitation, yielding an overall 16.20% performance gain on the hybrid task. Experiments demonstrate significant improvements in both heartbeat detection accuracy and ECG waveform reconstruction fidelity. Moreover, Horcrux exhibits strong generalizability to other time-frequency spectrogram analysis tasks.

Technology Category

• Search and Optimization: Non-convex Optimization
• Machine Learning: Multi-instance/Multi-view Learning
• Computer Vision: Multi-modal Vision

Application Category

• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Radar-based wellness monitoring is becoming an effective measurement to provide accurate vital signs in a contactless manner, but data scarcity retards the related research on deep-learning-based methods. Data augmentation is commonly used to enrich the dataset by modifying the existing data, but most augmentation techniques can only couple with classification tasks. To enable the augmentation for regression tasks, this research proposes a spectrogram augmentation method, Horcrux, for radar-based cardiac feature monitoring (e.g., heartbeat detection, electrocardiogram reconstruction) with both classification and regression tasks involved. The proposed method is designed to increase the diversity of input samples while the augmented spectrogram is still faithful to the original ground truth vital sign. In addition, Horcrux proposes to inject zero values in specific areas to enhance the awareness of the deep learning model on subtle cardiac features, improving the performance for the limited dataset. Experimental result shows that Horcrux achieves an overall improvement of 16.20% in cardiac monitoring and has the potential to be extended to other spectrogram-based tasks. The code will be released upon publication.

Problem

• Enables radar-based cardiac monitoring with limited data
• Augments spectrograms for both classification and regression tasks
• Improves deep learning model awareness of subtle cardiac features

Innovation

• Spectrogram augmentation for radar cardiac monitoring
• Inject zero values to highlight subtle features
• Supports both classification and regression tasks