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

[Value of Monochromatic Imaging on Spectral Detector CT in Metal Artifact Reduction of Denture Implants].

Zhongguo yi xue ke xue yuan xue bao. Acta Academiae Medicinae Sinicae·2018
Same author

Observation of Dicke cooperativity in magnetic interactions.

Science (New York, N.Y.)·2018
Same author

VERAM: View-Enhanced Recurrent Attention Model for 3D Shape Classification.

IEEE transactions on visualization and computer graphics·2018
Same author

T<sub>1</sub>-T<sub>2</sub> molecular magnetic resonance imaging of renal carcinoma cells based on nano-contrast agents.

International journal of nanomedicine·2018
Same author

Learning Discriminative 3D Shape Representations by View Discerning Networks.

IEEE transactions on visualization and computer graphics·2018
Same author

Polygalacic acid inhibits MMPs expression and osteoarthritis via Wnt/β-catenin and MAPK signal pathways suppression.

International immunopharmacology·2018

Related Experiment Video

Updated: May 25, 2026

Non-invasive Assessment of Changes in Corticomotoneuronal Transmission in Humans
09:30

Non-invasive Assessment of Changes in Corticomotoneuronal Transmission in Humans

Published on: May 24, 2017

Comparisons between linear and nonlinear methods for decoding motor cortical activities of monkey.

Kai Xu1, Yueming Wang, Shaomin Zhang

  • 1Qiushi Academy for Advanced Studies, Zhejiang University, Hangzhou 310027, PR China.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference
|January 19, 2012
PubMed
Summary
This summary is machine-generated.

Nonlinear models like General Regression Neural Network (GRNN) and Support Vector Regression (SVR) significantly outperform linear Kalman filters for decoding neural signals in Brain Machine Interfaces (BMI). These advanced methods show improved accuracy and robustness, especially with noisy data.

More Related Videos

Functional Near Infrared Spectroscopy of the Sensory and Motor Brain Regions with Simultaneous Kinematic and EMG Monitoring During Motor Tasks
11:31

Functional Near Infrared Spectroscopy of the Sensory and Motor Brain Regions with Simultaneous Kinematic and EMG Monitoring During Motor Tasks

Published on: December 5, 2014

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

Related Experiment Videos

Last Updated: May 25, 2026

Non-invasive Assessment of Changes in Corticomotoneuronal Transmission in Humans
09:30

Non-invasive Assessment of Changes in Corticomotoneuronal Transmission in Humans

Published on: May 24, 2017

Functional Near Infrared Spectroscopy of the Sensory and Motor Brain Regions with Simultaneous Kinematic and EMG Monitoring During Motor Tasks
11:31

Functional Near Infrared Spectroscopy of the Sensory and Motor Brain Regions with Simultaneous Kinematic and EMG Monitoring During Motor Tasks

Published on: December 5, 2014

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

Area of Science:

  • Neuroscience
  • Biomedical Engineering
  • Machine Learning

Background:

  • Brain Machine Interfaces (BMI) facilitate direct communication between the brain and external devices.
  • Decoding neuronal signals is crucial for effective BMI operation.
  • Current decoding methods are broadly classified into linear and nonlinear approaches.

Purpose of the Study:

  • To compare the performance of linear and nonlinear decoding methods for motor cortical activity.
  • To evaluate General Regression Neural Network (GRNN) and Support Vector Regression (SVR) against the Kalman filter (KF).
  • To assess decoding accuracy in reconstructing 2D trajectories during a center-out task.

Main Methods:

  • Utilized Kalman filter (KF) as a representative linear decoding method.
  • Employed General Regression Neural Network (GRNN) and Support Vector Regression (SVR) as nonlinear decoding methods.
  • Conducted experiments on monkey motor cortical activity, reconstructing 2D trajectories.

Main Results:

  • Nonlinear methods (GRNN and SVR) demonstrated superior performance compared to the linear Kalman filter.
  • Average improvements of approximately 30% in correlation coefficient (CC) and 40% in root mean square error (RMSE) were observed.
  • GRNN and SVR showed enhanced effectiveness in decoding neuronal signals from noisy data.

Conclusions:

  • Nonlinear models more effectively capture the complex relationship between neuronal signals and behavioral responses.
  • GRNN and SVR offer a more robust and accurate approach to neural decoding in BMI applications.
  • Nonlinear decoding methods present a significant advancement for Brain Machine Interface technology.