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

Neurons of the human subthalamic nucleus engage with local delta frequency processes during action cancellation.

Nature communications·2026
Same author

Local infrared stimulation modulates spontaneous cortical slow wave dynamics in anesthetized rats.

Scientific reports·2026
Same author

TRPV3 channel activity helps cortical neurons stay active during fever.

eLife·2026
Same author

TRPV3 channel activity helps cortical neurons stay active during fever.

bioRxiv : the preprint server for biology·2025
Same author

Overcoming matrix effects in AAV neutralization assays with a constant serum concentration approach.

Gene therapy·2025
Same author

CoreTIA: a modular, statistically robust transduction inhibition assay for AAV neutralization.

Frontiers in immunology·2025

Related Experiment Video

Updated: Aug 6, 2025

A Single-Channel and Non-Invasive Wearable Brain-Computer Interface for Industry and Healthcare
06:34

A Single-Channel and Non-Invasive Wearable Brain-Computer Interface for Industry and Healthcare

Published on: July 7, 2023

2.5K

Edge computing on TPU for brain implant signal analysis.

János Rokai1, István Ulbert2, Gergely Márton2

  • 1Institute of Cognitive Neuroscience and Psychology, Research Centre for Natural Sciences, Magyar tudósok körútja 2, building Q2, H-1117 Budapest, Hungary; János Szentágothai Doctoral School of Neurosciences, Semmelweis University, Üllői út 26, H-1085 Budapest, Hungary.

Neural Networks : the Official Journal of the International Neural Network Society
|March 15, 2023
PubMed
Summary

This study introduces a novel deep learning spike sorting system for neural activity detection. It achieves state-of-the-art accuracy and enables real-time processing on edge devices, advancing brain-computer interfaces.

Keywords:
Brain–computer interfaceDeep learningEdge deviceElectrophysiologyFeature extractionSpike sorting

More Related Videos

Recording Human Electrocorticographic ECoG Signals for Neuroscientific Research and Real-time Functional Cortical Mapping
13:32

Recording Human Electrocorticographic ECoG Signals for Neuroscientific Research and Real-time Functional Cortical Mapping

Published on: June 26, 2012

25.8K
Subdural Soft Electrocorticography ECoG Array Implantation and Long-Term Cortical Recording in Minipigs
08:30

Subdural Soft Electrocorticography ECoG Array Implantation and Long-Term Cortical Recording in Minipigs

Published on: March 31, 2023

2.8K

Related Experiment Videos

Last Updated: Aug 6, 2025

A Single-Channel and Non-Invasive Wearable Brain-Computer Interface for Industry and Healthcare
06:34

A Single-Channel and Non-Invasive Wearable Brain-Computer Interface for Industry and Healthcare

Published on: July 7, 2023

2.5K
Recording Human Electrocorticographic ECoG Signals for Neuroscientific Research and Real-time Functional Cortical Mapping
13:32

Recording Human Electrocorticographic ECoG Signals for Neuroscientific Research and Real-time Functional Cortical Mapping

Published on: June 26, 2012

25.8K
Subdural Soft Electrocorticography ECoG Array Implantation and Long-Term Cortical Recording in Minipigs
08:30

Subdural Soft Electrocorticography ECoG Array Implantation and Long-Term Cortical Recording in Minipigs

Published on: March 31, 2023

2.8K

Area of Science:

  • Neuroscience
  • Artificial Intelligence
  • Signal Processing

Background:

  • Increasing silicon probe density challenges accurate single-unit activity detection.
  • Current spike sorting solutions are either offline or limited by computational resources in embedded systems.

Purpose of the Study:

  • To develop a deep learning-based spike sorting system for accurate and efficient neural activity detection.
  • To enable real-time spike sorting on resource-constrained edge devices.

Main Methods:

  • A hybrid deep learning approach combining unsupervised contrastive learning for feature extraction and a supervised MobileNetV2 architecture.
  • Training on diverse datasets to enhance generalizability.
  • Deployment on edge Tensor Processing Units (TPUs).

Main Results:

  • The proposed system achieves accuracy comparable to state-of-the-art offline spike sorting methods.
  • Demonstrated potential for real-time processing on edge TPUs.
  • Successful comparison with existing solutions on paired and hybrid datasets.

Conclusions:

  • The developed deep learning spike sorting system offers high accuracy and efficiency.
  • It is suitable for deployment on edge devices, enabling integration into wearable electronics.
  • This work is a crucial step towards advanced brain-computer interfaces.