Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: Apr 16, 2026

Author Spotlight: IntelliSleepScorer — A High-Accuracy, Accessible GUI Software for Automated Sleep Stage Scoring in Mice and its Application in Psychiatric Research

Author Spotlight: IntelliSleepScorer — A High-Accuracy, Accessible GUI Software for Automated Sleep Stage Scoring in Mice and its Application in Psychiatric Research

Published on: November 8, 2024

Hybrid Deep Learning Framework for Sleep Quality Prediction: Integrating Metaheuristic Optimization and Statistical

Ayodele Lasisi¹, Nitasha Rathore², Lalita Gupta³

¹Department of Computer Science, College of Computer Science, King Khalid University, Abha, Saudi Arabia.

Brain and Behavior

|April 15, 2026

Related Concept Videos

Understanding Sleep

Understanding Sleep

Sleep, an essential biological state, involves significant reductions in physical activity, sensory awareness, and interaction with the environment. This complex physiological process is primarily regulated by specific brain regions, notably the hypothalamus and pons, which govern the sleep-wake cycle or circadian rhythm.
The circadian rhythm, a nearly 24-hour cycle, is deeply influenced by environmental light cues. Light exposure directly affects the hypothalamus, which in turn regulates...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Sustainable utilization of fly ash in AA8011 metal matrix composites for enhanced wear performance: implications for energy efficiency and resource optimization.

Scientific reports·2026

Same author

CardioMetaHybridOptimizer as a behaviorally adaptive multi-phase metaheuristic framework for interpretable cardiovascular disease diagnosis.

BMC bioinformatics·2026

Same author

Scalable HMO-CNN-SVM Framework for Skin Lesion Classification: A Metaheuristic-Driven Approach With Parallelizable Optimization for Cluster Deployment.

Biomedical engineering and computational biology·2026

Same author

Proportion of metabolic syndrome and gender differences among information technology professionals undergoing preventive health check-up in Delhi and NCR.

Journal of family medicine and primary care·2026

Same author

Shifting epidemiology and disease severity: Rethinking India's hepatitis A strategy in the context of acute liver failure.

Journal of family medicine and primary care·2026

Same author

Sustainable synthesis and optimization of aluminium matrix composites reinforced with laboratory waste borosilicate glass for resource sustainability circularity.

Scientific reports·2026

Same journal

Korean Red Ginseng Attenuates Dysfunctions and Modulates Inflammatory and Neuroplasticity Markers in the Harmaline-Induced Model of Essential Tremor.

Brain and behavior·2026

Same journal

Pseudohallucination and Pilocytic Astrocytoma in the Pons.

Brain and behavior·2026

Same journal

Volume Alterations in Thalamic Subnuclei in Parkinson's Disease Dementia and Machine Learning-Based Prediction of Diagnosis and Severity.

Brain and behavior·2026

Same journal

ESTELA-Study: Long-Term Effectiveness and Safety of Anti-Calcitonin Gene-Related Peptide Monoclonal Antibodies in Real-World Clinical Practice.

Brain and behavior·2026

Same journal

The "Brain's Traffic Map" Reveals Neural Pathways Linked to Coronary Microvascular Dysfunction in Women.

Brain and behavior·2026

Same journal

Psychedelic Therapy and the Role of Music: A Scoping Review of Quantitative Evidence on Subjective and Objective Outcomes.

Brain and behavior·2026

See all related articles

Summary

This summary is machine-generated.

This study presents a novel hybrid deep learning model for predicting sleep quality using actigraphy data. The advanced method significantly improves accuracy and interpretability in sleep health management.

Area of Science:

Computational neuroscience
Biomedical engineering
Artificial intelligence

Background:

Assessing sleep quality is crucial for overall health, impacting chronic disease prevention and cognitive function.
Current methods for sleep quality prediction using actigraphy data have limitations in accuracy and interpretability.
Deep learning models, particularly Long Short-Term Memory (LSTM) networks, show promise but often function as black boxes.

Purpose of the Study:

To develop and evaluate a sophisticated hybrid deep learning architecture for enhanced sleep quality prediction from actigraphy data.
To improve upon existing techniques by integrating metaheuristic optimization for feature selection and enhancing model interpretability.
To demonstrate the model's effectiveness on a benchmark dataset and assess its potential for individualized sleep health management.

Keywords:

actigraphy data digital biomarkers feature selection hybrid deep learning long short‐term memory metaheuristic optimization sleep quality prediction support vector machine

Related Experiment Videos

Last Updated: Apr 16, 2026

Author Spotlight: IntelliSleepScorer — A High-Accuracy, Accessible GUI Software for Automated Sleep Stage Scoring in Mice and its Application in Psychiatric Research

Author Spotlight: IntelliSleepScorer — A High-Accuracy, Accessible GUI Software for Automated Sleep Stage Scoring in Mice and its Application in Psychiatric Research

Published on: November 8, 2024

Main Methods:

A hybrid deep learning model combining statistical features and complex features extracted by LSTM networks.
Metaheuristic optimization techniques, including genetic algorithms and particle swarm optimization (PSO), were employed for feature selection.
Support Vector Machines (SVMs) were utilized for classifying the optimized feature set.
A novel feature significance analysis was introduced to provide interpretability to the deep learning model's predictions.

Main Results:

The proposed hybrid model significantly outperformed baseline LSTM and other state-of-the-art methods on the MESA Actigraphy dataset.
Achieved high accuracy (84.64% for weekly sleep quality, 68.99% for sleep consistency), F1-scores (0.847, 0.69), and AUC values (0.909, 0.839).
The feature significance analysis successfully provided interpretability, addressing the black-box nature of deep learning.

Conclusions:

Hybrid deep learning frameworks integrating metaheuristic optimization and multimodal data show significant potential for accurate sleep quality prediction.
The developed model offers a promising approach for individualized sleep health management and early diagnosis of sleep disorders.
The enhanced interpretability of the model facilitates trust and clinical application in sleep medicine.