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

Classification of action potentials in multi-unit intrafascicular recordings using neural network pattern-recognition

K Mirfakhraei, K Horch

    IEEE Transactions on Bio-Medical Engineering
    |January 1, 1994
    PubMed
    Summary
    This summary is machine-generated.

    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

    [Selected aspects of citizen and patient orientation in Germany. Assessment from the point of view of users].

    Bundesgesundheitsblatt, Gesundheitsforschung, Gesundheitsschutz·2012
    Same author

    A collagen and fibrin tube for nerve repair.

    Restorative neurology and neuroscience·2011
    Same author

    [Evaluating the health target "Increasing health competence, strengthening patient sovereignty"].

    Bundesgesundheitsblatt, Gesundheitsforschung, Gesundheitsschutz·2009
    Same author

    [People's interest in health information].

    Bundesgesundheitsblatt, Gesundheitsforschung, Gesundheitsschutz·2005
    Same author

    Evidence for a two pigment visual system in the fiddler crab, Uca thayeri.

    Journal of comparative physiology. A, Neuroethology, sensory, neural, and behavioral physiology·2002
    Same author

    Electrical resistivity of the upper arm and leg yields good estimates of whole body fat.

    Physiological measurement·2001

    Neural networks can identify action potential sources in cat neural recordings. This technology reliably separates 6-7 neural units, demonstrating its utility for classifying complex neural activity.

    Area of Science:

    • Neuroscience
    • Computational Neuroscience
    • Machine Learning

    Background:

    • Identifying individual neural unit activity from multi-unit recordings is crucial for understanding brain function.
    • Intrafascicular electrodes provide high-density recordings but often contain overlapping signals from multiple neurons.

    Purpose of the Study:

    • To apply neural network pattern-recognition techniques to differentiate and identify the sources of action potentials in multi-unit neural recordings.
    • To assess the performance of a neural network in separating individual neural units from complex recordings.

    Main Methods:

    • A three-layer connectionist neural network was designed and trained.
    • Digitized action potentials from multi-unit neural recordings (cats, intrafascicular electrodes) served as input.

    Related Experiment Videos

  • The network's ability to separate distinct neural units was evaluated.

    • Main Results:

    • The neural network reliably separated an average of 6 to 7 individual neural units per recording.
    • Performance plateaued, with the number of separable units remaining constant as the total number of units increased beyond 7.
    • This indicates a limit to the network's capacity for separation in these specific conditions.

    Conclusions:

    • Neural networks are effective tools for classifying neural activity in multi-unit recordings.
    • The study demonstrates the practical utility of artificial intelligence in neurophysiological data analysis.
    • Further research may explore network architectures to improve separation of a higher number of neural units.