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

Sequencing Ablation and Systemic Therapy in Colorectal Liver Oligometastases: An Upfront versus Delayed Approach Nationwide Analysis.

Radiology·2026
Same author

Effectiveness of the dual teachers-three rings-four dimensions teaching model in cultivating nursing students' comprehensive competence: A quasi-experimental study.

Nurse education today·2026
Same author

Engineering an Extremely Hybrid PKS for Adipic Acid Production.

ACS synthetic biology·2026
Same author

Glucocorticoid and mitophagy signaling-based molecular subtyping reveals HMGA1 as a prognostic and immunotherapy biomarker in lung adenocarcinoma.

NPJ precision oncology·2026
Same author

Biomimetic fusion nanosystem from ginger exosomes and tumor cell membranes: boosting PLK1-targeted therapy in BRCA-heterogeneous HGSOC.

Journal of nanobiotechnology·2026
Same author

FlowSDE: a flow-matching-based SDE framework for predicting state transitions.

Philosophical transactions. Series A, Mathematical, physical, and engineering sciences·2026

Related Experiment Video

Updated: Sep 28, 2025

Simultaneous Scalp Electroencephalography EEG, Electromyography EMG, and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding
11:25

Simultaneous Scalp Electroencephalography EEG, Electromyography EMG, and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding

Published on: July 26, 2013

43.5K

Embedding decomposition for artifacts removal in EEG signals.

Junjie Yu1, Chenyi Li1,2, Kexin Lou1

  • 1Shenzhen Key Laboratory of Smart Healthcare Engineering, Department of Biomedical Engineering, Southern University of Science and Technology, Shenzhen 518055, People's Republic of China.

Journal of Neural Engineering
|April 4, 2022
PubMed
Summary
This summary is machine-generated.

DeepSeparator, a novel deep learning framework, effectively removes electroencephalogram (EEG) artifacts like EOG and EMG. This advanced method enhances signal clarity without requiring prior experience, improving EEG data analysis.

Keywords:
EEG denoisingartifact removaldecompositiondeep learningembeddingsignal processing

More Related Videos

Equipment Setup and Artifact Removal for Simultaneous Electroencephalogram and Functional Magnetic Resonance Imaging for Clinical Review in Epilepsy
10:23

Equipment Setup and Artifact Removal for Simultaneous Electroencephalogram and Functional Magnetic Resonance Imaging for Clinical Review in Epilepsy

Published on: June 23, 2023

2.2K
Conscious and Non-conscious Representations of Emotional Faces in Asperger's Syndrome
08:31

Conscious and Non-conscious Representations of Emotional Faces in Asperger's Syndrome

Published on: July 31, 2016

13.7K

Related Experiment Videos

Last Updated: Sep 28, 2025

Simultaneous Scalp Electroencephalography EEG, Electromyography EMG, and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding
11:25

Simultaneous Scalp Electroencephalography EEG, Electromyography EMG, and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding

Published on: July 26, 2013

43.5K
Equipment Setup and Artifact Removal for Simultaneous Electroencephalogram and Functional Magnetic Resonance Imaging for Clinical Review in Epilepsy
10:23

Equipment Setup and Artifact Removal for Simultaneous Electroencephalogram and Functional Magnetic Resonance Imaging for Clinical Review in Epilepsy

Published on: June 23, 2023

2.2K
Conscious and Non-conscious Representations of Emotional Faces in Asperger's Syndrome
08:31

Conscious and Non-conscious Representations of Emotional Faces in Asperger's Syndrome

Published on: July 31, 2016

13.7K

Area of Science:

  • Neuroscience
  • Biomedical Engineering
  • Machine Learning

Background:

  • Electroencephalogram (EEG) recordings are frequently compromised by artifacts, hindering accurate analysis.
  • Existing artifact removal methods often necessitate significant user expertise and prior experience.
  • The need for automated and interpretable artifact removal techniques in EEG is critical.

Purpose of the Study:

  • To introduce DeepSeparator, a deep learning framework for robust separation of neural signals and artifacts in EEG.
  • To develop a method that enhances interpretability by enabling artifact extraction.
  • To provide an automated solution for EEG denoising, reducing reliance on manual intervention.

Main Methods:

  • Proposed a deep learning framework, DeepSeparator, utilizing an encoder-decoder architecture with a specialized decomposer module.
  • The encoder extracts and amplifies salient features from raw EEG data.
  • The decomposer module identifies, suppresses artifacts, and extracts artifactual components, while the decoder reconstructs the denoised signal.

Main Results:

  • DeepSeparator demonstrated superior performance in removing electrooculogram (EOG) and electromyogram (EMG) artifacts compared to conventional methods.
  • Validation was performed on both semi-synthetic and real-world task-related EEG datasets.
  • The framework successfully extracted artifact components, enhancing model interpretability.

Conclusions:

  • DeepSeparator offers an effective and interpretable deep learning approach for EEG artifact removal.
  • The method is adaptable for multi-channel EEG and data of arbitrary lengths.
  • This work paves the way for advanced deep learning applications in EEG signal processing and denoising.