Deep Learning for Sleep Heart Rate Estimation from Accelerometers: Toward Population-Scale Cardiac Insight Without Optical Sensors

Tanbin Islam Rohan, Pranjol Sen Gupta, Tanusree Debi, Nazmus Sakib|October 5, 2026arXiv

Key Takeaway

You can estimate sleep heart rate from accelerometer motion signals using deep learning, trading off some accuracy for broader coverage—useful for extracting cardiac insights from existing wearable data without optical sensors.

Summary

This paper presents SeqSmoother, a transformer-based model that estimates heart rate during sleep using only wrist accelerometer data, without requiring optical sensors.

training evaluation applications

Key Terms

transformer-architecture spectral-properties harmonic-frequency mean-absolute-error