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

Generation and Single-Cell Transcriptomic Analysis of Hepatocellular Carcinoma Organoids following Drug Treatment.

Journal of visualized experiments : JoVE·2026
Same author

Factors associated with partial direct breastfeeding at discharge of preterm infants in the Neonatal Intensive Care Unit: a cohort study.

The journal of maternal-fetal & neonatal medicine : the official journal of the European Association of Perinatal Medicine, the Federation of Asia and Oceania Perinatal Societies, the International Society of Perinatal Obstetricians·2026
Same author

Relationships between light exposure and aspects of cognitive function in everyday life.

Communications psychology·2025
Same author

Analysis of the disease burden of vertebral fractures in China and worldwide from 1990 to 2021 and trend forecast to 2035.

Journal of health, population, and nutrition·2025
Same author

Risk Factors for Increased Surgical Drain Output in Patients After Unilateral Expansive Open-Door Cervical Laminoplasty for Cervical Compressive Myelopathy: A Retrospective Study of 341 Patients.

World neurosurgery·2025
Same author

Family Caregiver Perspectives on Digital Methods to Measure Stress: Qualitative Descriptive Study.

Journal of medical Internet research·2025

Related Experiment Video

Updated: Jun 24, 2025

Author Spotlight: Capturing Infant-Caregiver Interactions Through Synchronized Multimodal Data Collection
08:08

Author Spotlight: Capturing Infant-Caregiver Interactions Through Synchronized Multimodal Data Collection

Published on: May 31, 2024

857

Deep Autoencoder for Real-Time Single-Channel EEG Cleaning and Its Smartphone Implementation Using TensorFlow Lite

Le Xing, Alexander J Casson

    IEEE Transactions on Bio-Medical Engineering
    |June 3, 2024
    PubMed
    Summary

    A Deep AutoEncoder (DAE) model effectively removes ocular, motion, and muscular artifacts from electroencephalogram (EEG) signals in real-time on smartphones. This breakthrough enables portable Brain-Computer Interface (BCI) applications with low latency artifact removal.

    More Related Videos

    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

    43.3K
    Author Spotlight: Advancing Large-Scale Neural Dynamics Through HD-MEA Technology
    09:44

    Author Spotlight: Advancing Large-Scale Neural Dynamics Through HD-MEA Technology

    Published on: March 8, 2024

    4.7K

    Related Experiment Videos

    Last Updated: Jun 24, 2025

    Author Spotlight: Capturing Infant-Caregiver Interactions Through Synchronized Multimodal Data Collection
    08:08

    Author Spotlight: Capturing Infant-Caregiver Interactions Through Synchronized Multimodal Data Collection

    Published on: May 31, 2024

    857
    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

    43.3K
    Author Spotlight: Advancing Large-Scale Neural Dynamics Through HD-MEA Technology
    09:44

    Author Spotlight: Advancing Large-Scale Neural Dynamics Through HD-MEA Technology

    Published on: March 8, 2024

    4.7K

    Area of Science:

    • Neuroscience
    • Biomedical Engineering
    • Artificial Intelligence

    Background:

    • Electroencephalogram (EEG) signal quality is often degraded by artifacts from ocular, motion, and muscular activity.
    • Real-time artifact removal is crucial for the development of portable Brain-Computer Interface (BCI) applications.

    Purpose of the Study:

    • To develop a real-time, low-computational overhead method for removing artifacts from EEG signals.
    • To enable portable BCI applications through efficient, channel-independent artifact removal on mobile platforms.

    Main Methods:

    • A Deep AutoEncoder (DAE) neural network was proposed for single-channel EEG artifact removal.
    • The DAE model was implemented on a smartphone using TensorFlow Lite with delegate-based acceleration for real-time performance.
    • Artifact removal efficacy was evaluated by comparing DAE-cleaned EEG with ground-truth clean EEG from public datasets.

    Main Results:

    • The DAE model achieved high correlations with ground-truth clean EEG (0.96 for reconstruction, 0.85 for EOG, 0.70 for motion, 0.79 for EMG artifacts).
    • On-smartphone tests demonstrated real-time processing of a 4-second EEG window within 5 milliseconds.
    • The DAE model significantly outperformed a FastICA artifact removal algorithm in computational efficiency.

    Conclusions:

    • The proposed DAE model effectively removes artifacts from single-channel EEG signals.
    • This represents the first demonstration of a low-computational deep learning model for mobile EEG artifact removal utilizing smartphone hardware/software acceleration.
    • The work facilitates portable BCIs by enabling low-latency, real-time artifact removal and potential operation with fewer EEG channels.