Energy-Efficient Real-Time 4-Stage Sleep Classification at 10-Second Resolution: A Comprehensive Study
- URL: http://arxiv.org/abs/2508.11664v1
- Date: Wed, 06 Aug 2025 06:45:30 GMT
- Title: Energy-Efficient Real-Time 4-Stage Sleep Classification at 10-Second Resolution: A Comprehensive Study
- Authors: Zahra Mohammadi, Parnian Fazel, Siamak Mohammadi,
- Abstract summary: Sleep stage classification is crucial for diagnosing and managing disorders such as sleep apnea and insomnia.<n>We present an energy-efficient pipeline that detects four sleep stages from a single-lead ECG.
- Score: 0.0
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Sleep stage classification is crucial for diagnosing and managing disorders such as sleep apnea and insomnia. Conventional clinical methods like polysomnography are costly and impractical for long-term home use. We present an energy-efficient pipeline that detects four sleep stages (wake, REM, light, and deep) from a single-lead ECG. Two windowing strategies are introduced: (1) a 5-minute window with 30-second steps for machine-learning models that use handcrafted features, and (2) a 30-second window with 10-second steps for deep-learning models, enabling near-real-time 10-second resolution. Lightweight networks such as MobileNet-v1 reach 92 percent accuracy and 91 percent F1-score but still draw significant energy. We therefore design SleepLiteCNN, a custom model that achieves 89 percent accuracy and 89 percent F1-score while lowering energy use to 5.48 microjoules per inference at 45 nm. Applying eight-bit quantization preserves accuracy and further reduces power, and FPGA deployment confirms low resource usage. The proposed system offers a practical solution for continuous, wearable ECG-based sleep monitoring.
Related papers
- ULW-SleepNet: An Ultra-Lightweight Network for Multimodal Sleep Stage Scoring [28.352558247977168]
We propose an ultra-lightweight, multimodal sleep stage scoring framework, ULW-SleepNet.<n>It incorporates a novel Dual-Stream Separable Convolution (DSSC) Block, depthwise separable convolutions, channel-wise parameter sharing, and global average pooling.<n>Compared to state-of-the-art methods, our model reduces parameters by up to 98.6% with only marginal performance loss.
arXiv Detail & Related papers (2026-02-27T09:48:11Z) - Physiology as Language: Translating Respiration to Sleep EEG [43.02603129452492]
This paper introduces a novel cross-physiology translation task: synthesizing sleep electroencephalography (EEG) from respiration signals.<n>We propose a waveform-conditional generative framework that preserves fine-grained respiratory dynamics while constraining the EEG target space through discrete tokenization.<n>Trained on over 28,000 individuals, our model achieves a 7% Mean Absolute Error in EEG spectrogram reconstruction.
arXiv Detail & Related papers (2026-01-31T05:44:45Z) - SleepLiteCNN: Energy-Efficient Sleep Apnea Subtype Classification with 1-Second Resolution Using Single-Lead ECG [0.0]
Sleep apnea is a common sleep disorder characterized by breathing interruptions lasting at least ten seconds and occurring more than five times per hour.<n>This paper presents an energy-efficient method for classifying sleep apnea subtypes using a single-lead electrocardiogram (ECG) with high temporal resolution.<n>We introduce SleepLiteCNN, a compact and energy-efficient convolutional neural network specifically designed for wearable platforms.
arXiv Detail & Related papers (2025-08-01T00:04:40Z) - RestAware: Non-Invasive Sleep Monitoring Using FMCW Radar and AI-Generated Summaries [0.0]
RestAware is a non-invasive, contactless sleep monitoring system based on a 24GHz frequency-modulated continuous wave (FMCW) radar.<n>Our system is evaluated on 25 participants across eight common sleep postures, achieving 92% classification accuracy and an F1-score of 0.91.
arXiv Detail & Related papers (2025-07-10T13:10:50Z) - Optimizing Photoplethysmography-Based Sleep Staging Models by Leveraging Temporal Context for Wearable Devices Applications [0.0]
State-of-the-art sleep staging methods require prolonged continuous signal acquisition, making them impractical for wearable devices due to high energy consumption.
Our work proposes an adapted sleep staging model based on top-performing state-of-the-art methods and evaluates its performance with different segment sizes.
arXiv Detail & Related papers (2024-10-01T13:47:42Z) - EdgeOL: Efficient in-situ Online Learning on Edge Devices [51.86178757050963]
We propose EdgeOL, an edge online learning framework that optimize inference accuracy, fine-tuning execution time, and energy efficiency.<n> Experimental results show that, on average, EdgeOL reduces overall fine-tuning execution time by 64%, energy consumption by 52%, and improves average inference accuracy by 1.75% over the immediate online learning strategy.
arXiv Detail & Related papers (2024-01-30T02:41:05Z) - A Closed-loop Sleep Modulation System with FPGA-Accelerated Deep
Learning [1.5569382274788235]
We develop a sleep modulation system that supports closed-loop operations on a low-power field-programmable gate array (FPGA) device.
Deep learning (DL) model is accelerated by a low-power field-programmable gate array (FPGA) device.
Model has been validated using a public sleep database containing 81 subjects, achieving a state-of-the-art classification accuracy of 85.8% and a F1-score of 79%.
arXiv Detail & Related papers (2022-11-19T01:47:53Z) - SOUL: An Energy-Efficient Unsupervised Online Learning Seizure Detection
Classifier [68.8204255655161]
Implantable devices that record neural activity and detect seizures have been adopted to issue warnings or trigger neurostimulation to suppress seizures.
For an implantable seizure detection system, a low power, at-the-edge, online learning algorithm can be employed to dynamically adapt to neural signal drifts.
SOUL was fabricated in TSMC's 28 nm process occupying 0.1 mm2 and achieves 1.5 nJ/classification energy efficiency, which is at least 24x more efficient than state-of-the-art.
arXiv Detail & Related papers (2021-10-01T23:01:20Z) - ECG-TCN: Wearable Cardiac Arrhythmia Detection with a Temporal
Convolutional Network [14.503893070243585]
Single lead electrocardiogram signals provide ability to detect, classify, and even predict cardiac arrhythmia.
We propose a novel temporal convolutional network (TCN) that achieves high accuracy while still being feasible for wearable platform use.
arXiv Detail & Related papers (2021-03-25T10:39:54Z) - Enabling certification of verification-agnostic networks via
memory-efficient semidefinite programming [97.40955121478716]
We propose a first-order dual SDP algorithm that requires memory only linear in the total number of network activations.
We significantly improve L-inf verified robust accuracy from 1% to 88% and 6% to 40% respectively.
We also demonstrate tight verification of a quadratic stability specification for the decoder of a variational autoencoder.
arXiv Detail & Related papers (2020-10-22T12:32:29Z) - Automatic detection of microsleep episodes with deep learning [55.41644538483948]
Brief fragments of sleep shorter than 15 s are defined as microsleep episodes (MSEs)
maintenance of wakefulness test (MWT) is often used in a clinical setting to assess vigilance.
MSEs are mostly not considered in the absence of established scoring criteria defining MSEs.
We aimed for automatic detection of MSEs with machine learning based on raw EEG and EOG data as input.
arXiv Detail & Related papers (2020-09-07T11:38:40Z) - Improving Efficiency in Large-Scale Decentralized Distributed Training [58.80224380923698]
We propose techniques to accelerate (A)D-PSGD based training by improving the spectral gap while minimizing the communication cost.
We demonstrate the effectiveness of our proposed techniques by running experiments on the 2000-hour Switchboard speech recognition task and the ImageNet computer vision task.
arXiv Detail & Related papers (2020-02-04T04:29:09Z) - REST: Robust and Efficient Neural Networks for Sleep Monitoring in the
Wild [62.36144064259933]
We propose REST, a new method that simultaneously tackles both issues via adversarial training and controlling the Lipschitz constant of the neural network.
We demonstrate that REST produces highly-robust and efficient models that substantially outperform the original full-sized models in the presence of noise.
By deploying these models to an Android application on a smartphone, we quantitatively observe that REST allows models to achieve up to 17x energy reduction and 9x faster inference.
arXiv Detail & Related papers (2020-01-29T17:23:16Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.