Key result
Lightweight Tiny-PPG achieves ~87% accuracy for real-time PPG artifact segmentation on edge devices.
Why the study?
PPG signals in wearable and smart health devices are easily contaminated by motion artifacts during real-world cardiovascular health monitoring.
Tiny-PPG provides an accurate, lightweight deep learning solution for real-time detection of motion artifacts in PPG signals on resource-constrained IoT edge devices.
May enable real-time PPG monitoring on edge wearables; leaves open clinical validation before cardiovascular adoption.
Photoplethysmogram (PPG) signals are easily contaminated by motion artifacts in real-world settings, despite their widespread use in Internet-of-Things (IoT) based wearable and smart health devices for cardiovascular health monitoring. This study proposed a lightweight deep neural network, called Tiny-PPG, for accurate and real-time PPG artifact segmentation on IoT edge devices. The model was trained and tested on a public dataset, PPG DaLiA, which featured complex artifacts with diverse lengths and morphologies during various daily activities of 15 subjects using a watch-type device (Empatica E4). The model structure, training method and loss function were specifically designed to balance detection accuracy and speed for real-time PPG artifact detection in resource-constrained embedded devices. To optimize the model size and capability in multi-scale feature representation, the model employed depth-wise separable convolution and atrous spatial pyramid pooling modules, respectively. Additionally, the contrastive loss was also utilized to further optimize the feature embeddings. With additional model pruning, Tiny-PPG achieved state-of-the-art detection accuracy of 87.4% while only having 19,726 model parameters (0.15 megabytes), and was successfully deployed on an STM32 embedded system for real-time PPG artifact detection. Therefore, this study provides an effective solution for resource-constraint IoT smart health devices in PPG artifact detection.
No takes yet. Share an insight, caveat, or question.
Zheng et al. (2023) studied Motion artifacts in photoplethysmogram (PPG) signals (n=15). Tiny-PPG (lightweight deep neural network) was evaluated on Detection accuracy of PPG artifact segmentation. Tiny-PPG, a lightweight deep neural network, achieved a state-of-the-art detection accuracy of 87.4% for real-time PPG artifact segmentation on edge devices with only 19,726 parameters.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: