Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

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

Unveiling EMG semantics: a prototype-learning approach to generalizable gesture classification.

Journal of neural engineering·2024

Same author

A bioelectric neural interface towards intuitive prosthetic control for amputees.

Journal of neural engineering·2020

Same author

Ultra-rapid object categorization in real-world scenes with top-down manipulations.

PloS one·2019

Same author

Oral Antibiotics Are Effective for the Treatment of Hand Osteomyelitis in Children.

Hand (New York, N.Y.)·2018

Same author

A Streaming PCA VLSI Chip for Neural Data Compression.

IEEE transactions on biomedical circuits and systems·2017

Same author

Can the SUV<sub>max-liver</sub>-based interpretation improve prognostic accuracy of interim and posttreatment <sup>18</sup>F-FDG PET/CT in patients with diffuse large B-cell lymphoma?

Leukemia & lymphoma·2017

Search research articles

Related Experiment Video

Updated: Oct 18, 2025

Capturing Dynamic Finger Gesturing with High-resolution Surface Electromyography and Computer Vision

Capturing Dynamic Finger Gesturing with High-resolution Surface Electromyography and Computer Vision

Published on: March 28, 2025

A portable, self-contained neuroprosthetic hand with deep learning-based finger control.

Anh Tuan Nguyen^1,2, Markus W Drealan¹, Diu Khue Luu¹

¹Biomedical Engineering, University of Minnesota, Minneapolis, MN, United States of America.

Journal of Neural Engineering

|September 27, 2021

Summary

This study demonstrates a portable, self-contained neuroprosthetic hand controlled by deep learning algorithms deployed on edge computing devices. The system offers robust, high-accuracy, and low-latency control of individual finger movements for amputees.

Keywords:

NVIDIA Jetson Nano artificial intelligence deep learning electroneurography (ENG)motor decoding neuroprosthesis peripheral nerve

More Related Videos

Author Spotlight: Enhancing Grasping Abilities for Hemiplegic Patients with Flexible Robotic Limbs

Author Spotlight: Enhancing Grasping Abilities for Hemiplegic Patients with Flexible Robotic Limbs

Published on: October 27, 2023

The Bionic Clicker Mark I & II

The Bionic Clicker Mark I & II

Published on: August 14, 2017

Related Experiment Videos

Last Updated: Oct 18, 2025

Capturing Dynamic Finger Gesturing with High-resolution Surface Electromyography and Computer Vision

Capturing Dynamic Finger Gesturing with High-resolution Surface Electromyography and Computer Vision

Published on: March 28, 2025

Author Spotlight: Enhancing Grasping Abilities for Hemiplegic Patients with Flexible Robotic Limbs

Author Spotlight: Enhancing Grasping Abilities for Hemiplegic Patients with Flexible Robotic Limbs

Published on: October 27, 2023

The Bionic Clicker Mark I & II

The Bionic Clicker Mark I & II

Published on: August 14, 2017

Area of Science:

Biomedical Engineering
Artificial Intelligence
Neuroscience

Background:

Deep learning neural decoders are key for intuitive neuroprosthetic hand control.
High computational demands of deep learning have limited clinical translation.
Edge computing offers a solution for deploying complex AI models in portable devices.

Purpose of the Study:

To implement a neuroprosthetic hand with embedded deep learning control using edge computing.
To evaluate the system's performance in real-world environments with a transradial amputee.

Main Methods:

Developed a recurrent neural network-based neural decoder.
Deployed the decoder on an NVIDIA Jetson Nano edge computing platform.
Integrated the system into a portable, self-contained neuroprosthetic hand.

Main Results:

Achieved robust, high-accuracy (95%-99%) control of individual finger movements.
Demonstrated low-latency (50-120 ms) performance in diverse environments.
Successfully piloted the system with a transradial amputee using peripheral nerve signals.

Conclusions:

Edge computing platforms enable effective, autonomous deep learning-based neuroprosthesis control.
This work pioneers the clinical application of AI in wearable biomedical devices.
The system represents a new class of intelligent, self-contained neuroprosthetic devices.