Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

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

Sort by
Same author

Efficacy and effectiveness of melatonin for the management of musculoskeletal pain: a systematic review and meta-analysis of placebo and active controlled trials.

Pain·2026
Same author

Iterative Virtual and Physical Simulation for Staged Separation of Total Vertical Craniopagus: The Avatar Patient Approach to Conjoined Twins.

Operative neurosurgery (Hagerstown, Md.)·2026
Same author

Lipids and glucose fluctuations are associated with clinically diagnosed depression in older adults with type 2 diabetes.

Frontiers in endocrinology·2026
Same author

Effect of insoles with different cushioning properties on knee impact after radial tear of posterior horn of medial meniscus: a finite element analysis.

BMC musculoskeletal disorders·2026
Same author

Pain Trajectories after Orthopedic Surgery in Older Adults: An Analysis of Predictors and Associations with Postoperative Outcomes.

Anesthesiology·2026
Same author

Patients' attitudes toward melatonin for musculoskeletal pain: Insights for rehabilitation practice.

Physiotherapy·2026

Related Experiment Video

Updated: Oct 14, 2025

Multi-Modal Home Sleep Monitoring in Older Adults
07:40

Multi-Modal Home Sleep Monitoring in Older Adults

Published on: January 26, 2019

7.8K

Single-channel EEG based insomnia detection with domain adaptation.

Wei Qu1, Chien-Hui Kao2, Hong Hong3

  • 1School of Computer Science, The University of Sydney, Sydney, New South Wales, Australia.

Computers in Biology and Medicine
|November 5, 2021
PubMed
Summary

This study introduces a novel domain adaptation model for detecting insomnia using electroencephalogram (EEG) data. The method effectively leverages healthy subject data to improve insomnia detection accuracy, addressing data scarcity challenges.

Keywords:
Deep learningDomain adaptationEEG signalInsomnia diagnosis

More Related Videos

Author Spotlight: Therapeutic Benefit of Closed-Loop Deep Brain Stimulation in Depression Treatment
05:19

Author Spotlight: Therapeutic Benefit of Closed-Loop Deep Brain Stimulation in Depression Treatment

Published on: July 7, 2023

2.7K
Manipulation of Epileptiform Electrocorticograms ECoGs and Sleep in Rats and Mice by Acupuncture
09:06

Manipulation of Epileptiform Electrocorticograms ECoGs and Sleep in Rats and Mice by Acupuncture

Published on: December 22, 2016

9.7K

Related Experiment Videos

Last Updated: Oct 14, 2025

Multi-Modal Home Sleep Monitoring in Older Adults
07:40

Multi-Modal Home Sleep Monitoring in Older Adults

Published on: January 26, 2019

7.8K
Author Spotlight: Therapeutic Benefit of Closed-Loop Deep Brain Stimulation in Depression Treatment
05:19

Author Spotlight: Therapeutic Benefit of Closed-Loop Deep Brain Stimulation in Depression Treatment

Published on: July 7, 2023

2.7K
Manipulation of Epileptiform Electrocorticograms ECoGs and Sleep in Rats and Mice by Acupuncture
09:06

Manipulation of Epileptiform Electrocorticograms ECoGs and Sleep in Rats and Mice by Acupuncture

Published on: December 22, 2016

9.7K

Area of Science:

  • Neuroscience
  • Artificial Intelligence
  • Sleep Medicine

Background:

  • Insomnia is a prevalent sleep disorder significantly impacting health and quality of life.
  • Deep learning methods show promise for objective insomnia detection but suffer from data scarcity.
  • Abundant electroencephalogram (EEG) datasets exist for healthy subjects, presenting an opportunity for transfer learning.

Purpose of the Study:

  • To develop a domain adaptation model for insomnia detection using readily available EEG data from healthy subjects.
  • To overcome the limitations of small, insomnia-specific datasets by leveraging larger, healthy-subject datasets.
  • To improve the generalization capacity and performance of deep learning models for subject-level insomnia detection.

Main Methods:

  • Proposed a domain adaptation framework utilizing common and private encoders for feature extraction.
  • Incorporated a domain classifier to distinguish between source (healthy) and target (insomnia) domains.
  • Employed a Long Short-Term Memory (LSTM) network with features from the common encoder for final insomnia detection.
  • Utilized the Montreal Archive of Sleep Studies (MASS) as the source domain and two other datasets as target domains.

Main Results:

  • The model demonstrated strong generalizability across target datasets with varying sampling rates.
  • Achieved significant improvements in insomnia detection accuracy, increasing from 50.0% to 90.9% on one dataset.
  • Further improved accuracy from 66.7% to 79.2% on a second target dataset.
  • This represents the first deep learning domain adaptation model for subject-level insomnia detection using single-channel raw EEG.

Conclusions:

  • Domain adaptation is a viable strategy to address data scarcity in insomnia detection using EEG.
  • The proposed model effectively transfers knowledge from healthy subject data to improve insomnia detection performance.
  • This approach offers a promising solution for more accurate and accessible objective insomnia diagnosis.