# Q-PPG: Energy-Efficient PPG-based Heart Rate Monitoring on Wearable Devices

arXiv: https://arxiv.org/abs/2203.14907 · HTML: https://mlsanity.com/paper/2203.14907/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 58 references that are in the map.
- First posted on arXiv 24 Mar 2022.

## Builds on (most cited first, 15 of 15)

- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding](https://mlsanity.com/paper/1510.00149/) (2015)
- [An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling](https://mlsanity.com/paper/1803.01271/) (2018)
- [MnasNet: Platform-Aware Neural Architecture Search for Mobile](https://mlsanity.com/paper/1807.11626/) (2018)
- [ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware](https://mlsanity.com/paper/1812.00332/) (2018)
- [PACT: Parameterized Clipping Activation for Quantized Neural Networks](https://mlsanity.com/paper/1805.06085/) (2018)
- [MCUNet: Tiny Deep Learning on IoT Devices](https://mlsanity.com/paper/2007.10319/) (2020)
- [Temporal Convolutional Networks: A Unified Approach to Action Segmentation](https://mlsanity.com/paper/1608.08242/) (2016)
- [FBNetV2: Differentiable Neural Architecture Search for Spatial and Channel Dimensions](https://mlsanity.com/paper/2004.05565/) (2020)
- [MorphNet: Fast & Simple Resource-Constrained Structure Learning of Deep Networks](https://mlsanity.com/paper/1711.06798/) (2017)
- [Rethinking Differentiable Search for Mixed-Precision Neural Networks](https://mlsanity.com/paper/2004.05795/) (2020)
- [DORY: Automatic End-to-End Deployment of Real-World DNNs on Low-Cost IoT MCUs](https://mlsanity.com/paper/2008.07127/) (2020)
- [TROIKA: A General Framework for Heart Rate Monitoring Using Wrist-Type Photoplethysmographic Signals During Intensive Physical Exercise](https://mlsanity.com/paper/1409.5181/) (2014)
- [Photoplethysmography-Based Heart Rate Monitoring in Physical Activities via Joint Sparse Spectrum Reconstruction](https://mlsanity.com/paper/1503.00688/) (2015)
- [A Survey on Deep Learning-based Non-Invasive Brain Signals:Recent Advances and New Frontiers](https://mlsanity.com/paper/1905.04149/) (2019)

## Built on by (most cited first, 14 of 14)

- [Channel-wise Mixed-precision Assignment for DNN Inference on Constrained Edge Nodes](https://mlsanity.com/paper/2206.08852/) (2022)
- [BeliefPPG: Uncertainty-aware Heart Rate Estimation from PPG signals via Belief Propagation](https://mlsanity.com/paper/2306.07730/) (2023)
- [KID-PPG: Knowledge Informed Deep Learning for Extracting Heart Rate from a Smartwatch](https://mlsanity.com/paper/2405.09559/) (2024)
- [EnhancePPG: Improving PPG-based Heart Rate Estimation with Self-Supervision and Augmentation](https://mlsanity.com/paper/2412.17860/) (2024)
- [Efficient Deep Learning Models for Privacy-preserving People Counting on Low-resolution Infrared Arrays](https://mlsanity.com/paper/2304.06059/) (2023)
- [Tiny-PPG: A Lightweight Deep Neural Network for Real-Time Detection of Motion Artifacts in Photoplethysmogram Signals on Edge Devices](https://mlsanity.com/paper/2305.03308/) (2023)
- [Multi-Complexity-Loss DNAS for Energy-Efficient and Memory-Constrained Deep Neural Networks](https://mlsanity.com/paper/2206.00302/) (2022)
- [Multi-Head Cross-Attentional PPG and Motion Signal Fusion for Heart Rate Estimation](https://mlsanity.com/paper/2210.11415/) (2022)
- [Optimization and Deployment of Deep Neural Networks for PPG-based Blood Pressure Estimation Targeting Low-power Wearables](https://mlsanity.com/paper/2409.07485/) (2024)
- [Deriving Health Metrics from the Photoplethysmogram: Benchmarks and Insights from MIMIC-III-Ext-PPG](https://mlsanity.com/paper/2603.21832/) (2026)
- [MoRSE: Deep Learning-based Arm Gesture Recognition for Search and Rescue Operations](https://mlsanity.com/paper/2210.08307/) (2022)
- [Energy-efficient Wearable-to-Mobile Offload of ML Inference for PPG-based Heart-Rate Estimation](https://mlsanity.com/paper/2306.06129/) (2023)
- [Joint Attention Mechanism Learning to Facilitate Opto-physiological Monitoring during Physical Activity](https://mlsanity.com/paper/2502.09291/) (2025)
- [End-to-end Automated Deep Neural Network Optimization for PPG-based Blood Pressure Estimation on Wearables](https://mlsanity.com/paper/2604.10117/) (2026)

## Abstract (arXiv)

Hearth Rate (HR) monitoring is increasingly performed in wrist-worn devices using low-cost photoplethysmography (PPG) sensors. However, Motion Artifacts (MAs) caused by movements of the subject's arm affect the performance of PPG-based HR tracking. This is typically addressed coupling the PPG signal with acceleration measurements from an inertial sensor. Unfortunately, most standard approaches of this kind rely on hand-tuned parameters, which impair their generalization capabilities and their applicability to real data in the field. In contrast, methods based on deep learning, despite their better generalization, are considered to be too complex to deploy on wearable devices. In this work, we tackle these limitations, proposing a design space exploration methodology to automatically generate a rich family of deep Temporal Convolutional Networks (TCNs) for HR monitoring, all derived from a single "seed" model. Our flow involves a cascade of two Neural Architecture Search (NAS) tools and a hardware-friendly quantizer, whose combination yields both highly accurate and extremely lightweight models. When tested on the PPG-Dalia dataset, our most accurate model sets a new state-of-the-art in Mean Absolute Error. Furthermore, we deploy our TCNs on an embedded platform featuring a STM32WB55 microcontroller, demonstrating their suitability for real-time execution. Our most accurate quantized network achieves 4.41 Beats Per Minute (BPM) of Mean Absolute Error (MAE), with an energy consumption of 47.65 mJ and a memory footprint of 412 kB. At the same time, the smallest network that obtains a MAE < 8 BPM, among those generated by our flow, has a memory footprint of 1.9 kB and consumes just 1.79 mJ per inference.