Automated Multimodal Sleep Staging Using DWT-Based Wavelet Decomposition and Explainable Machine Learning with Signal Sculpting Topographies.

Overview

1. Department of Electrical and Electronic Engineering, Chittagong University of Engineering and Technology (CUET), Chittagong 4349, Bangladesh; (A.S.S.); (K.M.M.S.)
2. University Dental College Dhaka, Dhaka 1212, Bangladesh
3. Khan Dental Clinic, Dhaka 1212, Bangladesh
4. ELITE Research Lab, Queens, NY 11435, USA
5. Centre for Intelligent Cloud Computing (CICC), COE of Advanced Cloud, Faculty of Information Science and Technology, Multimedia University, Lama Bukit Beruang, Melaka 75450, Malaysia

Abstract

Objectives: Sleep staging from polysomnographic (PSG) recordings is clinically critical for diagnosing sleep-related disorders, yet manual scoring by certified technologists remains time-consuming, costly, and subject to inter-rater variability. Methods: This study presents an automated, explainable, and multimodal framework for five-class sleep stage classification using simultaneously acquired electroencephalography (EEG), electrooculography (EOG), and electromyography (EMG) signals. A total of 1946 annotated 30 s epochs from 30 healthy adult recording sessions (Sleep-EDF Expanded and Sleep Cassette subset) were processed through a 37-dimensional multimodal feature extraction pipeline encompassing temporal amplitude statistics, frequency-domain spectral band powers, nonlinear entropy and complexity measures, and Daubechies-4 discrete wavelet transform (DWT) energy coefficients. Four classical machine learning classifiers -Random Forest (RF), Support Vector Machine with radial basis function kernel (SVM-RBF), Gradient Boosting (GB), and K-Nearest Neighbours (KNN, k = 7) were benchmarked under stratified five-fold cross-validation. Results: SVM-RBF achieved the highest macro-averaged F1-score of 0.7322 (Cohen’s kappa 0.6784, overall accuracy 75.18%). N3 deep slow-wave sleep achieved the highest per-class F1 of 0.879, while N1 light sleep was the most challenging (F1 = 0.668). SHapley Additive exPlanations (SHAP) and RF mean decrease in Gini impurity (MDGI) analysis jointly identified EMG root mean square amplitude (MDGI = 0.0805), gamma band power (0.0784), and permutation entropy (0.0434) as the three most discriminative features. As a novel methodological contribution, sixteen categories of signal sculpting visualisations were developed, translating abstract multivariate features into clinically interpretable graphical representations. Conclusions: The proposed framework achieves substantial kappa agreement approaching the lower bound of expert inter-rater reliability (0.76–0.82) while providing full model transparency, with direct implications for wearable sleep monitoring device design.

Reproduced under the paper's license (CC BY), from the paper cited above.

Code

The paper links to its data, not to its authors' code: see the Data section.

The paper's code and data availability statement is in the Data section.

Tracing map

A tracing map links a paper to the code its authors published: this paper has none, so it has no map.

Data

Datasets cited

• physionet.org/content/sleep-edfx, at PhysioNet; found in “Data Availability Statement”

Data Availability Statement

The Sleep-EDF Expanded dataset is publicly available at https://physionet.org/content/sleep-edfx/ (accessed in 15 March 2026) [10]. Analysis code will be deposited in a public repository upon manuscript acceptance. The fixed random seed (random_state = 42), the complete hyperparameter search grids and selected values (Supplementary Table S1), and the class definitions required to reproduce every reported result are provided in the Supplementary Materials, so that the SVM-RBF and Gradient Boosting configurations can be independently verified.

Reproduced under the paper's license (CC BY), from the paper cited above.

Versions

The history of this record: each version stored by the harvester or made by a correction of its authors or of the maintainers of its code, and what changed in its facts. The texts of the paper (its abstract, its availability statements) are not part of it; versions that changed only those are not listed.

Version 1, 27 September 2026: the first record

Recorded: type, language, journal, volume, issue, pages, dates, 5 authors, 11 keywords, 37 references.

Cite

This paper

Sarker, A. S., Samir, K. M. M., Shakib, Z. K., Morol, M. K., & Liew, T. H. (2026). Automated Multimodal Sleep Staging Using DWT-Based Wavelet Decomposition and Explainable Machine Learning with Signal Sculpting Topographies. Diagnostics (Basel, Switzerland), 16(16), 2609. https://doi.org/10.3390/diagnostics16162609

Similar papers

The papers with a page that share the most with this one: the tools found in their code, their categories, datasets, cited references and authors, the rarest counting most.

[1] doi:10.1371/journal.pone.0353930 [code]

MMFNet: A multi-branch multi-scale framework with adaptive sparse self-attention and cross-modal fusion for sleep stage assessment.

Journal: PloS one

In common: physionet.org/content/sleep-edfx, methods / tools, EEG, 5 references

[2] doi:10.3390/brainsci16080793

Disentangling EEG Fingerprinting and Sleep Biomarkers Using Generalized Weighted Ordinal Patterns.

Journal: Brain sciences

In common: physionet.org/content/sleep-edfx, EEG, 3 references

[3] doi:10.1007/s00422-026-01049-1 [code]

A three-component dynamical index of consciousness-related neural organisation.

Journal: Biological cybernetics

In common: physionet.org/content/sleep-edfx, EEG, 2 references

[4] doi:10.3390/e28080920

XGBoost Classification of Epileptic EEG Using Nonlinear Dynamical Features and SHAP.

Journal: Entropy (Basel, Switzerland)

In common: methods / tools, EEG, 3 references

[5] doi:10.3390/bios16070394

Hybrid Edge-Cloud Asymmetric Analytics for Portable Multimodal BCI Biosensors.

Journal: Biosensors

In common: other, methods / tools, EEG, 3 references

[6] doi:10.1186/s12984-026-01969-w

Improving motor imagery decoding methods for an EEG-based mobile brain-computer interface in the context of the 2024 Cybathlon.

Journal: Journal of neuroengineering and rehabilitation

In common: methods / tools, EEG, 3 references

[7] doi:10.1093/sleep/zsag022

Mamba-based deep learning approach for sleep staging on a wireless multimodal wearable system without electroencephalography.

Journal: Sleep

In common: other, EEG, 2 references

[8] doi:10.3390/s26134091

Hypnogram-Driven Automatic Sleep Staging and a Quality-Index Assessment Through a Two-Stage LSTM-DNN Ensemble Learning Approach Using Multi-Biosignal Features for Sleep Disorder Detection.

Journal: Sensors (Basel, Switzerland)

In common: methods / tools, EEG, 2 references

[9] doi:10.1038/s41598-026-48881-w

SleepPACNet: new convolutional neural network considering phase-amplitude coupling for automatic sleep stage classification using single-channel electroencephalogram.

Journal: Scientific reports

In common: EEG, 2 references

[10] doi:10.1093/pnasnexus/pgag108

Aging disrupts the temporal organization of slow oscillations beyond density reduction.

Journal: PNAS nexus

In common: 3 references

Contribute

The authors of this paper can claim it, correct its record and validate its tracing map, and the maintainers of its code (its owner, or a public member of its organization) correct what it says of their repository; anyone signed in can ask for its removal. Every request goes to OSCR's own machine, which answers it; your account page follows them.

Request its removal

To ask OSCR to remove this record, the copies of its authors' scripts or its tracing map, use the removal request page: signed in, you say who you are, what to remove and why, then review and confirm the request. Published rules decide every request (how).

Discussion: questions and error reports about this paper and its code, from signed-in readers and its authors. It opens with sign-in.

Reproductions: reports from readers who ran the authors' code: what they reproduced, with which environment, commit and data. It opens with sign-in.

Activity: what happens around this paper: new versions of its record, its map's validation, discussions and reproductions. It opens with sign-in.