# Towards Real-Time ECG and EMG Modeling on μNPUs

arXiv: https://arxiv.org/abs/2604.18067 · HTML: https://mlsanity.com/paper/2604.18067/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 17 of its 55 references that are in the map.
- First posted on arXiv 20 Apr 2026.

## Builds on (most cited first, 17 of 17)

- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [MetaFormer Is Actually What You Need for Vision](https://mlsanity.com/paper/2111.11418/) (2021)
- [TensorFlow Lite Micro: Embedded Machine Learning on TinyML Systems](https://mlsanity.com/paper/2010.08678/) (2020)
- [ECG-FM: An Open Electrocardiogram Foundation Model](https://mlsanity.com/paper/2408.05178/) (2024)
- [Subject-Aware Contrastive Learning for Biosignals](https://mlsanity.com/paper/2007.04871/) (2020)
- [μNAS: Constrained Neural Architecture Search for Microcontrollers](https://mlsanity.com/paper/2010.14246/) (2020)
- [SpArSe: Sparse Architecture Search for CNNs on Resource-Constrained Microcontrollers](https://mlsanity.com/paper/1905.12107/) (2019)
- [Memory-Driven Mixed Low Precision Quantization For Enabling Deep Network Inference On Microcontrollers](https://mlsanity.com/paper/1905.13082/) (2019)
- [Fully Learnable Deep Wavelet Transform for Unsupervised Monitoring of High-Frequency Time Series](https://mlsanity.com/paper/2105.00899/) (2021)
- [Machine Learning for Microcontroller-Class Hardware: A Review](https://mlsanity.com/paper/2205.14550/) (2022)
- [PhysioWave: A Multi-Scale Wavelet-Transformer for Physiological Signal Representation](https://mlsanity.com/paper/2506.10351/) (2025)
- [MCUFormer: Deploying Vision Transformers on Microcontrollers with Limited Memory](https://mlsanity.com/paper/2310.16898/) (2023)
- [Optimizing the Deployment of Tiny Transformers on Low-Power MCUs](https://mlsanity.com/paper/2404.02945/) (2024)
- [Learning Front-end Filter-bank Parameters using Convolutional Neural Networks for Abnormal Heart Sound Detection](https://mlsanity.com/paper/1806.05892/) (2018)
- [A Framework and Call to Action for the Future Development of EMG-Based Input in HCI](https://mlsanity.com/paper/2304.00582/) (2023)
- [BioGAP: a 10-Core FP-capable Ultra-Low Power IoT Processor, with Medical-Grade AFE and BLE Connectivity for Wearable Biosignal Processing](https://mlsanity.com/paper/2307.01619/) (2023)

## Abstract (arXiv)

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 μNPUs 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 (~370KB with 8-bit quantization). We also profile its component-wise latency and resource consumption on both the MAX78000 and HX6538 WE2 μNPUs, 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.