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

Search research articles

Related Experiment Video

Updated: Jul 3, 2026

Simultaneous Scalp Electroencephalography (EEG), Electromyography (EMG), and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding

Simultaneous Scalp Electroencephalography (EEG), Electromyography (EMG), and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding

Published on: July 26, 2013

EMG-Based Gait Estimation Using Koopman-Inspired Method.

Chien-Wen Pan, Mehran Rahmani, Sangram Redkar

IEEE Transactions on Bio-Medical Engineering

|July 1, 2026

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

Optimal DMD Koopman Data-Driven Control of a Worm Robot.

Biomimetics (Basel, Switzerland)·2024

Same author

A novel GPI-anchored dominant-negative TGF-β receptor II renders T cells unresponsive to TGF-β signaling.

Molecular therapy oncolytics·2023

Same author

An observational study of engineering online education during the COVID-19 pandemic.

PloS one·2021

Same author

Novel robust control of a 7-DOF exoskeleton robot.

PloS one·2018

Same author

MEMS gyroscope control using a novel compound robust control.

ISA transactions·2017

Same author

Tumor-derived circulating endothelial cell clusters in colorectal cancer.

Science translational medicine·2016

Same journal

Enhancing Volumetric Imaging in Linear-Array Photoacoustic Tomography: multiview fusion with deep learning.

IEEE transactions on bio-medical engineering·2026

Same journal

Robust Rule-based Heuristic Assistance Strategy for a Semi-Active Shoulder Exoskeleton Used in Overhead Work.

IEEE transactions on bio-medical engineering·2026

Same journal

Highly Accelerated 1-mm Isotropic 3D Chemical Exchange Saturation Transfer MRI Using Wave-Co-CAIPI at 5 Tesla.

IEEE transactions on bio-medical engineering·2026

Same journal

Systematic Evaluation of Hip Exoskeleton Assistance Parameters for Enhancing Gait Stability During Ground Slip Perturbations.

IEEE transactions on bio-medical engineering·2026

Same journal

SleepConFormer: A Single-Channel EEG Framework for Sleep Staging and Consciousness Assessment in Patients with Disorders of Consciousness.

IEEE transactions on bio-medical engineering·2026

Same journal

Modeling Partial and Total Support of Left Ventricular Assist Device for Discrete Hemodynamic Control Framework.

IEEE transactions on bio-medical engineering·2026

See all related articles

This study uses surface electromyography (EMG) and Koopman operator theory (KOT) to predict lower-limb joint angles. The approach shows promise for improving control in human-machine interaction and robotics.

Area of Science:

Biomechanics
Robotics
Human-Machine Interaction
Dynamical Systems Theory

Background:

Surface electromyography (EMG) signals offer a non-invasive method for inferring human movement.
Koopman operator theory (KOT) provides a framework for analyzing nonlinear systems by transforming them into a linear representation in a higher-dimensional space.
Accurate estimation and prediction of lower-limb joint states are crucial for advanced prosthetic control, exoskeletons, and human-robot collaboration.

Purpose of the Study:

To develop and validate an EMG-based system for estimating lower-limb joint states using neural networks.
To employ Koopman operator theory to predict near-future joint states based on current EMG signals and gait intentions.
To establish a pioneer study demonstrating the efficacy of EMG-driven Koopman operators for knee and ankle angle prediction.

More Related Videos

Methods to Quantify Pharmacologically Induced Alterations in Motor Function in Human Incomplete SCI

Methods to Quantify Pharmacologically Induced Alterations in Motor Function in Human Incomplete SCI

Published on: April 18, 2011

Related Experiment Videos

Last Updated: Jul 3, 2026

Simultaneous Scalp Electroencephalography (EEG), Electromyography (EMG), and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding

Simultaneous Scalp Electroencephalography (EEG), Electromyography (EMG), and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding

Published on: July 26, 2013

Methods to Quantify Pharmacologically Induced Alterations in Motor Function in Human Incomplete SCI

Methods to Quantify Pharmacologically Induced Alterations in Motor Function in Human Incomplete SCI

Published on: April 18, 2011

Main Methods:

Nonlinear relationships between surface electromyography (sEMG) and lower-limb joint states were captured using neural networks.
Koopman operator theory was implemented to model the temporal dynamics between current and future joint states.
The system was trained and tested for both intra-subject prediction and cross-subject generalization (leave-one-subject-out).

Main Results:

High accuracy was achieved in intra-subject prediction, with Root Mean Square Errors (RMSE) of 3.61° for the knee and 1.78° for the ankle under same-gait conditions.
Transient-gait conditions also showed strong intra-subject prediction performance (RMSE: 3.78° knee, 1.43° ankle).
Cross-subject generalization yielded mean RMSEs of 7.79° for the knee and 2.12° for the ankle in same-gait scenarios.

Conclusions:

EMG-based state estimation using neural networks combined with Koopman operator theory is a viable approach for predicting lower-limb joint angles.
The developed framework demonstrates significant potential for real-time control applications in biomechanics and robotics.
Further research can explore more complex gaits and broader subject populations to enhance generalizability.