Towards Characterizing Knowledge Distillation of PPG Heart Rate Estimation Models
By: Kanav Arora , Girish Narayanswamy , Shwetak Patel and more
Potential Business Impact:
Makes smartwatches accurately track heart rates.
Heart rate estimation from photoplethysmography (PPG) signals generated by wearable devices such as smartwatches and fitness trackers has significant implications for the health and well-being of individuals. Although prior work has demonstrated deep learning models with strong performance in the heart rate estimation task, in order to deploy these models on wearable devices, these models must also adhere to strict memory and latency constraints. In this work, we explore and characterize how large pre-trained PPG models may be distilled to smaller models appropriate for real-time inference on the edge. We evaluate four distillation strategies through comprehensive sweeps of teacher and student model capacities: (1) hard distillation, (2) soft distillation, (3) decoupled knowledge distillation (DKD), and (4) feature distillation. We present a characterization of the resulting scaling laws describing the relationship between model size and performance. This early investigation lays the groundwork for practical and predictable methods for building edge-deployable models for physiological sensing.
Similar Papers
PPG-Distill: Efficient Photoplethysmography Signals Analysis via Foundation Model Distillation
Machine Learning (CS)
Makes smartwatches understand heartbeats better, faster.
Inferring Optical Tissue Properties from Photoplethysmography using Hybrid Amortized Inference
Machine Learning (CS)
Makes smartwatches understand your body better.
Towards a Real-Time Warning System for Detecting Inaccuracies in Photoplethysmography-Based Heart Rate Measurements in Wearable Devices
Human-Computer Interaction
Warns you when your heart rate watch is wrong.