Deep learning for sleep quality assessment: A CNN‐based approach outperforming traditional algorithms in wearable accelerometer data analysis
Sleep Research · 2026-09 · 3 (3) · 251-257
DOI: 10.1002/slp2.70048 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sleep Research, online erschienen am 30.06.2026. Verfasst von Lin Zhongyue und 4 weiteren Autor:innen. Die Arbeit nennt 18 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Science and Technology Plan Project of Taizhou.
Themen: Schlaf
Abstract (Originalsprache)
Objective
This study evaluates and enhances wearable sleep monitoring by comparing two feature extraction methods: traditional activity counts and deep learning‐derived features. By identifying optimal machine learning architectures, we aim to improve sleep stage classification accuracy, providing a robust, noncontact tool for clinical chronic disease management.
Method
We employed dual feature extraction strategies: (1) traditional activity counts (triaxial acceleration signal summation and windowed averaging) and (2) a two‐tier 1D‐CNN architecture with batch normalization/ReLU/max‐pooling for hierarchical feature learning. The extracted features were subsequently modeled using four machine learning approaches (convolutional neural network [CNN], XGBoost, SVM, RF) to assess their relative performance in sleep stage classification.
Results
The CNN‐derived features consistently outperformed traditional features across all classifiers, achieving superior sleep quality assessment accuracy (Macro AUC: CNN 0.97 vs. XGBoost 0.98 with CNN features). Notably, the CNN model showed particular advantages in capturing transient movement patterns and cross‐channel physiological relationships critical for sleep staging.
Conclusion
This comparative analysis validates that although conventional activity counts maintain interpretability, CNN‐based feature extraction provides significant performance gains for wearable sleep monitoring, especially when integrated with ensemble methods. The findings establish an optimized framework for clinical sleep assessment in chronic disease management, balancing computational efficiency with diagnostic accuracy.
Förderung
- Science and Technology Plan Project of Taizhou
Zitieren
APA
Zhongyue, L., Yi, L., Qing, L., Zhengru, X., & Fenglong, Y. (2026). Deep learning for sleep quality assessment: A CNN‐based approach outperforming traditional algorithms in wearable accelerometer data analysis. Sleep Research, 3(3), 251-257. https://doi.org/10.1002/slp2.70048
Vancouver
Zhongyue L, Yi L, Qing L, Zhengru X, Fenglong Y. Deep learning for sleep quality assessment: A CNN‐based approach outperforming traditional algorithms in wearable accelerometer data analysis. Sleep Research. 2026;3(3):251-257. doi:10.1002/slp2.70048
BibTeX
@article{Zhongyue2026,
author = {Zhongyue, Lin and Yi, Liu and Qing, Liu and Zhengru, Xie and Fenglong, Yang},
title = {Deep learning for sleep quality assessment: A CNN‐based approach outperforming traditional algorithms in wearable accelerometer data analysis},
journal = {Sleep Research},
year = {2026},
volume = {3},
number = {3},
pages = {251--257},
doi = {10.1002/slp2.70048}
}
EUVIMED