轻量级模型让可穿戴设备实时分析心电肌电信号
Towards Real-Time ECG and EMG Modeling on $μ$NPUs
- 用可学习的小波滤波器替代动态注意力，适配微型NPU
- 模型仅370KB（8bit量化），性能接近顶级Transformer模型
- 实测在两款μNPU上低功耗运行，适合电池供电可穿戴设备
神经处理单元（NPUs）等低功耗加速器的微型化，使它们能集成到微控制器级可穿戴硬件中，实现近实时、离线且保护隐私的推理。然而，生理信号分析仍难以在该类硬件上实现；近期基于Transformer的模型虽表现优异，但因体积过大、动态注意力操作不兼容，无法部署于μNPUs。本文提出PhysioLite，一种轻量级、NPU兼容的ECG/EMG信号分析模型架构与训练框架。通过可学习的小波滤波器、由CPU承担的位置编码，以及面向硬件的层设计，PhysioLite在ECG和EMG基准测试中性能媲美顶尖Transformer基座模型，模型大小不足其10%（约370KB，8bit量化）。我们还对MAX78000和HX6538 WE2 μNPUs上的组件级延迟与资源消耗进行了分析，验证了其在资源受限、电池供电硬件上的可行性。代码与模型已开源：https://github.com/j0shmillar/physiolite。
原文摘要 · Abstract (English)
The miniaturisation of neural processing units (NPUs) and other low-power accelerators has enabled their integration into microcontroller-scale wearable hardware, supporting near-real-time, offline, and privacy-preserving inference. Yet physiological signal analysis has remained infeasible on such hardware; recent Transformer-based models show state-of-the-art performance but are prohibitively large for resource- and power-constrained hardware and incompatible with $μ$NPUs due to their dynamic attention operations. We introduce PhysioLite, a lightweight, NPU-compatible model architecture and training framework for ECG/EMG signal analysis. Using learnable wavelet filter banks, CPU-offloaded positional encoding, and hardware-aware layer design, PhysioLite reaches performance comparable to state-of-the-art Transformer-based foundation models on ECG and EMG benchmarks, while being <10% of the size ($\sim$370KB with 8-bit quantization). We also profile its component-wise latency and resource consumption on both the MAX78000 and HX6538 WE2 $μ$NPUs, demonstrating its viability for signal analysis on constrained, battery-powered hardware. We release our model(s) and training framework at: https://github.com/j0shmillar/physiolite.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。