aiqbench analysis
NanoSleep introduces a compact hybrid temporal convolutional network designed to optimize sleep stage classification from single-channel EEG data, addressing the critical need for efficient deep learning models on resource-constrained wearable devices. By balancing high accuracy with reduced model size through specialized architectural components like gated dilated convolutions and conditional random fields, this research advances the practical deployment of AI in home-based health monitoring without relying on heavy computational infrastructure.
NanoSleep: A Parameter-Efficient Hybrid Temporal Convolutional Network for Single-Channel Sleep Stage Classification
arXiv:2608.18571v1 Announce Type: new Abstract: Sleep stage classification from single-channel electroencephalography (EEG) is essential for wearable and home-based sleep monitoring. However, many deep learning models achieve high accuracy at the cost of large model sizes, which limits their deployment on resource-constrained devices. In this work, we present NanoSleep, a compact hybrid temporal convolutional network for automatic sleep stage classification. NanoSleep combines a learnable Sinc-convolutional front end, a dual-branch feature extractor that fuses multi-scale temporal and spectral representations, a gated dilated temporal convolutional backbone with channel recalibration, and a conditional random field for sequence-level decoding. We further employ a weighted calibrated focal loss to address class imbalance. We evaluate NanoSleep on the Sleep-EDF and Sleep-EDF-Expanded datasets using subject-wise cross-validation. The proposed model consistently outperforms six representative baseline methods, and an ablation study confirms the contribution of each major component. These results demonstrate that NanoSleep provides an effective balance between accuracy and efficiency, making it well suited for wearable devices, home-based sleep monitoring, and resource-constrained clinical applications.
Abstract:Sleep stage classification from single-channel electroencephalography (EEG) is essential for wearable and home-based sleep monitoring. However, many deep learning models achieve high accuracy at the cost of large model sizes, which limits their deployment on resource-constrained devices. In this work, we present NanoSleep, a compact hybrid temporal convolutional network for automatic sleep stage classification. NanoSleep combines a learnable Sinc-convolutional front end, a dual-branch feature extractor that fuses multi-scale temporal and spectral representations, a gated dilated temporal convolutional backbone with channel recalibration, and a conditional random field for sequence-level decoding. We further employ a weighted calibrated focal loss to address class imbalance. We evaluate NanoSleep on the Sleep-EDF and Sleep-EDF-Expanded datasets using subject-wise cross-validation. The proposed model consistently outperforms six representative baseline methods, and an ablation study confirms the contribution of each major component. These results demonstrate that NanoSleep provides an effective balance between accuracy and efficiency, making it well suited for wearable devices, home-based sleep monitoring, and resource-constrained clinical applications.
Machine Learning (cs.LG)
arXiv:2608.18571 [cs.LG]
(or arXiv:2608.18571v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2608.18571 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 254 words
Related coverage
RhyMix: A Lightweight Adaptive Multi-Rhythm Network for Long-Term Time Series Forecasting
arXiv · Oct 15, 2026
Hybrid Parallel Bessel KAN Model: a Kolmogorov Arnold Network: integrated framework for developing a novel architecture to reconstruct the fused-basis approach via a parameter free quadratic interaction
arXiv · Oct 14, 2026
NVIDIA Nemotron 3 Nano Omni Powers Multimodal Agent Reasoning in a Single Efficient Open Model
NVIDIA · Apr 28, 2026
Beyond the Graph: An Adaptive Meta-Learner Fuses Explainability, Weather, and Dynamics for Robust Bus ETA Prediction
arXiv · Sep 30, 2026