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 Experiment Videos

A comparison of optimal MIMO linear and nonlinear models for brain-machine interfaces.

S-P Kim1, J C Sanchez, Y N Rao

  • 1Department of Electrical and Computer Engineering, University of Florida, Gainesville, 32611, USA.

Journal of Neural Engineering
|May 18, 2006
PubMed
Summary

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

High-specificity identification of large vessel occlusion stroke using D-dimer and NT-proBNP combined with clinical variables.

Frontiers in neurology·2026
Same author

[Electroencephalographic predictors of olfactory stimulus discrimination in COVID-19 survivors].

Zhurnal nevrologii i psikhiatrii imeni S.S. Korsakova·2026
Same author

Impact of SARS-CoV-2 infection on perioperative mortality.

Revista clinica espanola·2025
Same author

[Cerebral persistent primitive arteries. Clinical case of combination with intracranial aneurysm and review of the literature].

Zhurnal voprosy neirokhirurgii imeni N. N. Burdenko·2024
Same author

Discovery and insights from DSX mission's high-power VLF wave transmission experiments in the radiation belts.

Scientific reports·2022
Same author

Interaction of 5-[4'-(<i>N</i>-Methyl-1,3-benzimidazol-2-yl)phenyl]-10,15,20-tri-(<i>N</i>-methyl-3'-pyridyl)porphyrin Triiodide with SARS-CoV-2 Spike Protein.

Russian journal of general chemistry·2022

This study evaluated various brain-machine interface models for decoding hand movements from neural activity. Optimized models showed improved generalization performance compared to the baseline Wiener filter.

Area of Science:

  • Neuroscience
  • Computational Neuroscience
  • Machine Learning

Background:

  • Brain-machine interfaces (BMIs) are crucial for decoding neural signals into motor commands.
  • Accurate estimation of hand kinematics from motor cortex spike trains is essential for BMI development.
  • Future BMIs will utilize large ensembles of simultaneously recorded neurons.

Purpose of the Study:

  • To systematically investigate and compare the generalization performance of linear and nonlinear models for decoding hand kinematics from neural spike trains.
  • To optimize model parameters using advanced signal processing and machine learning techniques.
  • To establish a statistical comparison against a Wiener filter baseline.

Main Methods:

  • Application of diverse linear models (Wiener filter, LMS adaptive filters, gamma filter, subspace Wiener filters) and nonlinear models (time-delay neural network, local linear switching models).

Related Experiment Videos

  • Utilizing datasets from two distinct monkey motor tasks (reaching, target hitting) with simultaneous recordings of 100-200 cortical neurons.
  • Optimal selection of all model parameters, including weights, via signal processing and machine learning.
  • Statistical comparison of model performance against the Wiener filter benchmark.

    • Main Results:

    • All tested optimization procedures yielded performance improvements over the Wiener filter baseline on at least one dataset.
    • The study focused on generalization performance due to the large number of parameters in the models.
    • Both linear and nonlinear models demonstrated potential for accurate kinematic decoding.

    Conclusions:

    • Optimized linear and nonlinear models offer improved generalization for decoding hand kinematics from neural data compared to standard methods.
    • The findings support the development of more sophisticated BMI decoding algorithms.
    • Further research with larger neuronal ensembles is warranted to enhance BMI capabilities.