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

Cytotoxic constitutents from Cryptocarya maclurei.

Phytochemistry·2013
Same author

Using molecular docking-based binding energy to predict toxicity of binary mixture with different binding sites.

Chemosphere·2013
Same author

Demonstration of digital phase-sensitive boosting to extend signal reach for long-haul WDM systems using optical phase-conjugated copy.

Optics express·2013
Same author

Both NF-κB and c-Jun/AP-1 involved in anti-β2GPI/β2GPI-induced tissue factor expression in monocytes.

Thrombosis and haemostasis·2013
Same author

New flavonol and diterpenoids from the endophytic fungus Aspergillus sp. YXf3.

Planta medica·2013
Same author

Selective isolation and analysis of glycoprotein fractions and their glycomes from hepatocellular carcinoma sera.

Proteomics·2013

Related Experiment Video

Updated: Jan 2, 2026

Author Spotlight: Enhancing Neurorehabilitation Through EEG, Motor Imagery, and Virtual Reality
10:14

Author Spotlight: Enhancing Neurorehabilitation Through EEG, Motor Imagery, and Virtual Reality

Published on: May 10, 2024

1.7K

Motor imagery EEG recognition with KNN-based smooth auto-encoder.

Xianlun Tang1, Ting Wang1, Yiming Du2

  • 1Chongqing Key Laboratory of Complex Systems and Bionic Control, College of Automation, Chongqing University of Posts and Telecommunications, Nan'an district, Chongqing, 400065, China.

Artificial Intelligence in Medicine
|December 10, 2019
PubMed
Summary
This summary is machine-generated.

This study introduces a novel semi-supervised model, KNN-based smooth auto-encoder (k-SAE), for analyzing electroencephalogram (EEG) signals. The k-SAE model enhances brain-computer interface technology by improving motor imagery EEG signal recognition accuracy.

Keywords:
BCIEEG recognitionFeature extractionKNN-based smooth auto-encoderMotor imagery

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

44.0K
Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches
09:47

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

1.6K

Related Experiment Videos

Last Updated: Jan 2, 2026

Author Spotlight: Enhancing Neurorehabilitation Through EEG, Motor Imagery, and Virtual Reality
10:14

Author Spotlight: Enhancing Neurorehabilitation Through EEG, Motor Imagery, and Virtual Reality

Published on: May 10, 2024

1.7K
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

44.0K
Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches
09:47

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

1.6K

Area of Science:

  • Neuroscience
  • Computer Science
  • Biomedical Engineering

Background:

  • Brain-computer interfaces (BCIs) are emerging technologies for human-computer interaction.
  • Electroencephalogram (EEG) signal analysis offers insights into brain activity and communication.
  • Motor imagery EEG signals are crucial for understanding and controlling BCIs.

Purpose of the Study:

  • To propose an innovative semi-supervised model, KNN-based smooth auto-encoder (k-SAE), for motor imagery EEG signal analysis.
  • To enhance feature representation and improve the accuracy of EEG signal classification.
  • To advance the capabilities of brain-computer interfaces through improved signal processing.

Main Methods:

  • Developed a KNN-based smooth auto-encoder (k-SAE) model for semi-supervised learning.
  • Utilized nearest neighbor values to construct new inputs for robust feature learning.
  • Employed Gaussian filters for noise smoothing and max-pooling/unpooling for information preservation.
  • Applied the k-SAE model to two datasets for feature extraction and classification of motor imagery EEG signals.

Main Results:

  • The k-SAE model demonstrated robust feature representation by reconstructing modified inputs.
  • Gaussian filtering effectively smoothed noise in the EEG signal features.
  • Max-pooling and unpooling preserved crucial data information and spatial positioning.
  • Experimental results showed that k-SAE achieved high recognition accuracy for motor imagery EEG signals.

Conclusions:

  • The proposed k-SAE model offers a significant advancement in motor imagery EEG signal processing.
  • k-SAE outperforms existing state-of-the-art recognition algorithms in terms of accuracy.
  • This research contributes to the development of more effective brain-computer interfaces.