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

Networks of respiratory-muscular coupling in exercise and fatigue in young adults.

Physiological reports·2026
Same author

Cascade Skip-Connection BiLSTM Autoencoder for CPR Artifact Removal Prior to AED Shock Advisory.

IEEE open journal of the Computer Society·2026
Same author

ospEDA: Orthogonal Subspace Projection for Electrodermal Activity Decomposition.

IEEE transactions on bio-medical engineering·2026
Same author

Multimodal Detection of Pain and Anticipation Anxiety from Ultra-Short Duration Wearable Sensors Measurements.

Sensors (Basel, Switzerland)·2026
Same author

ERG-Graph: Graph Signal Processing of the Electroretinogram for Classification of Neurodevelopmental Disorders.

Bioengineering (Basel, Switzerland)·2026
Same author

Continuous Emotion Recognition Using EDA-Graphs: A Graph Signal Processing Approach for Affective Dimension Estimation.

Applied sciences (Basel, Switzerland)·2026

Related Experiment Video

Updated: Aug 29, 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

A Deep Convolutional Autoencoder for Automatic Motion Artifact Removal in Electrodermal Activity Signals: A

Md-Billal Hossain, Hugo F Posada-Quintero, Ki H Chon

    Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference
    |September 10, 2022
    PubMed
    Summary

    This study introduces a deep convolutional autoencoder (DCAE) to automatically remove motion artifacts from electrodermal activity (EDA) signals. The DCAE significantly outperforms existing methods, preserving valuable EDA data for analysis.

    More Related Videos

    Acquisition and Semi-Automated Analysis of Respiratory Muscle Surface Electromyography
    09:42

    Acquisition and Semi-Automated Analysis of Respiratory Muscle Surface Electromyography

    Published on: January 24, 2025

    680
    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

    13.5K

    Related Experiment Videos

    Last Updated: Aug 29, 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
    Acquisition and Semi-Automated Analysis of Respiratory Muscle Surface Electromyography
    09:42

    Acquisition and Semi-Automated Analysis of Respiratory Muscle Surface Electromyography

    Published on: January 24, 2025

    680
    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

    13.5K

    Area of Science:

    • Physiology
    • Biomedical Engineering
    • Signal Processing

    Background:

    • Automatic motion artifact (MA) removal in electrodermal activity (EDA) signals presents a significant challenge due to the irregular nature of EDA.
    • Existing MA removal techniques are often limited, particularly for high-magnitude artifacts, leading to the discarding of valuable data, especially during ambulatory monitoring.
    • The need for robust automated methods is critical to maximize the utility of EDA data in research and clinical applications.

    Purpose of the Study:

    • To develop and evaluate a data-driven deep convolutional autoencoder (DCAE) for automated motion artifact removal in electrodermal activity (EDA) signals.
    • To compare the performance of the proposed DCAE against established state-of-the-art methods for MA removal in EDA.
    • To assess the efficacy of the DCAE in handling both synthetically generated and real-life induced motion artifacts.

    Main Methods:

    • A deep convolutional autoencoder (DCAE) architecture was designed and trained using publicly available electrodermal activity (EDA) datasets.
    • Clean EDA signals were corrupted with both Gaussian white noise (GWN) and laboratory-collected real-life motion artifact (MA) data to simulate artifact contamination.
    • Performance was quantitatively evaluated using signal-to-noise ratio improvement (SNRimp) and mean squared error (MSE) metrics, comparing the DCAE against three contemporary MA removal techniques.

    Main Results:

    • The proposed DCAE model demonstrated significantly superior performance compared to the three state-of-the-art methods.
    • The DCAE achieved a substantially higher signal-to-noise ratio improvement (SNRimp) across both synthetic and real-life motion artifact datasets.
    • The deep convolutional autoencoder (DCAE) yielded a considerably lower mean squared error (MSE), indicating more accurate artifact removal.

    Conclusions:

    • The developed deep convolutional autoencoder (DCAE) presents a promising and effective approach for automated motion artifact removal in electrodermal activity (EDA) signals.
    • This data-driven method significantly enhances the quality of EDA data by reducing artifacts, thereby minimizing data loss during analysis.
    • The DCAE's capability to handle diverse MA types suggests its potential for broad application in processing electrodermal activity data, particularly in ambulatory settings.