Kapture：利用Koopman支配学习捕获心脏动力学，实现基于雷达的高效心电恢复
Kapture: Capturing Cardiac Dynamics with Koopman-Governed Learning for Efficient Radar-Based Electrocardiogram Recovery
浏览论文内容
中文总结 AI 辅助
提出Kapture框架，利用Koopman算子学习低维动态，以参数高效方式从毫米波雷达时频图恢复ECG，在压缩下显著提升性能并大幅减少参数和计算量。
中文摘要 AI 辅助
毫米波（mmWave）雷达能够实现无感、非接触式的心电图（ECG）重建，用于心脏监测。时频频谱图保留了精细的心脏模式，但通常需要大型骨干网络来从呼吸、运动、多径和受试者依赖的干扰中分离出ECG相关特征。我们提出了Kapture，一种参数高效的Koopman支配框架，该框架将雷达隐藏状态投影到低维可观测空间，并从相邻可观测状态中识别出一个正则化的全线性演化算子。Koopman预测的可观测值用于细化后续隐藏状态，以进行ECG重建。为了抑制可预测的干扰动态，一个时间对比目标将相邻状态拉近并分离非相邻状态，而重建监督则保持任务相关性。利用约80分钟的准静态雷达-ECG记录（包含来自身体运动和其他来源的真实噪声），Kapture在匹配的骨干宽度下持续改善重建效果，在激进压缩下获得最大增益。紧凑配置以68.1%更少的参数和91.3%更少的分析器覆盖的浮点运算次数（FLOPs）接近全宽度参考精度，而全宽度配置则提供最强的整体重建性能。我们的代码将在可能发表后公开提供。
英文摘要
Millimeter-wave (mmWave) radar enables unobtrusive, contactless electrocardiogram (ECG) reconstruction for cardiac monitoring. Time-frequency spectrograms preserve fine cardiac patterns but often require large backbones to separate ECG-relevant features from respiration, motion, multipath, and subject-dependent interference. We propose Kapture, a parameter-efficient Koopman-governed framework that projects radar hidden states into a low-dimensional observable space and identifies a regularized full linear evolution operator from adjacent observable states. The Koopman-predicted observables refine subsequent hidden states for ECG reconstruction. To suppress predictable interference dynamics, a temporal contrastive objective pulls neighboring states together and separates non-neighbors, while reconstruction supervision preserves task relevance. Using approximately 80 minutes of quasi-static radar-ECG recordings containing realistic noise from body movements and other sources, Kapture consistently improves reconstruction across matched backbone widths, with the largest gains under aggressive compression. The compact configuration approaches the full-width reference accuracy with 68.1% fewer parameters and 91.3% fewer profiler-covered floating-point operations (FLOPs), while the full-width configuration delivers the strongest overall reconstruction performance. Our code will be made publicly available after potential publication.
发表机构
- Amazon（亚马逊）
- Equitable
- University of Glasgow（格拉斯哥大学）
机构由 AI 辅助整理，请以论文原文为准。
