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

Flow Cytometry-Based Rapid Assay for Antigen Specific Antibody Relative Affinity in SRBC-Immunized Mouse Models.

International journal of molecular sciences·2025

Same author

Conventional High-Temperature Superconductivity at Ambient Pressure in Zincblende-Like Light-Element Compounds.

Inorganic chemistry·2025

Same author

Pathways to Aromatics in the Catalytic Pyrolysis of a Polyvinylchloride Model Compound Revealed by Operando Photoelectron Photoion Coincidence Spectroscopy.

ChemSusChem·2025

Same author

Autonomous 3D Self-Sensing Hybrid Membrane Actuator for Interactive Communicating.

ACS applied materials & interfaces·2025

Same author

A Lightweight Pig Aggressive Behavior Recognition Model by Effective Integration of Spatio-Temporal Features.

Animals : an open access journal from MDPI·2025

Same author

Enhancing C─C Bond Cleavage of Glycerol Electrooxidation Through Spin-Selective Electron Donation in Pd-PdS<sub>2</sub>-Co<sub>x</sub> Heterostructural Nanosheets.

Angewandte Chemie (International ed. in English)·2025

Same journal

Research on a Regional Availability Evaluation Model for Road-Area High-Entropy Energy Based on Synergy Factors.

Entropy (Basel, Switzerland)·2026

Same journal

Atmospheric Turbulence Channel Modeling and Performance Analysis of a CO-ZP-OFDM Coherent Optical Communication System for UAV Air-to-Ground Scenarios.

Entropy (Basel, Switzerland)·2026

Same journal

Information Geometry and Asymptotic Theory for SMML Estimators.

Entropy (Basel, Switzerland)·2026

Same journal

Correlation Entropy and Power-Law Kinetics.

Entropy (Basel, Switzerland)·2026

Same journal

Research on the Contagion of Systemic Financial Risk Under the Impact of Climate Risks-From the Perspective of Complex Networks and Machine Learning.

Entropy (Basel, Switzerland)·2026

Same journal

The Statistical-Mechanical Meaning of the Wave Function of Quantum Mechanics.

Entropy (Basel, Switzerland)·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Nov 3, 2025

Sit-to-stand-and-walk from 120% Knee Height: A Novel Approach to Assess Dynamic Postural Control Independent of Lead-limb

Sit-to-stand-and-walk from 120% Knee Height: A Novel Approach to Assess Dynamic Postural Control Independent of Lead-limb

Published on: August 30, 2016

Training Data Selection and Optimal Sensor Placement for Deep-Learning-Based Sparse Inertial Sensor Human Posture

Zhaolong Zheng^1,2, Hao Ma^1,2, Weichao Yan^1,2

¹Shenzhen Key Laboratory of Biomimetic Robotics and Intelligent Systems, Department of Mechanical and Energy Engineering, Southern University of Science and Technology, Shenzhen 518055, China.

Entropy (Basel, Switzerland)

|June 2, 2021

Summary

This summary is machine-generated.

This study introduces a deep learning method using sparse inertial sensors for accurate human posture reconstruction. It optimizes training data and sensor placement for improved performance in specific activities like walking and running.

Keywords:

Bi-RNN Max-Relevance and Min-Redundancy optimal sensor placement pose estimation training data selection

More Related Videos

Author Spotlight: Enhancing Remote Rehabilitation with Virtual Reality and Electromyography

Author Spotlight: Enhancing Remote Rehabilitation with Virtual Reality and Electromyography

Published on: January 12, 2024

An Inertial Measurement Unit Based Method to Estimate Hip and Knee Joint Kinematics in Team Sport Athletes on the Field

An Inertial Measurement Unit Based Method to Estimate Hip and Knee Joint Kinematics in Team Sport Athletes on the Field

Published on: May 26, 2020

Related Experiment Videos

Last Updated: Nov 3, 2025

Sit-to-stand-and-walk from 120% Knee Height: A Novel Approach to Assess Dynamic Postural Control Independent of Lead-limb

Sit-to-stand-and-walk from 120% Knee Height: A Novel Approach to Assess Dynamic Postural Control Independent of Lead-limb

Published on: August 30, 2016

Author Spotlight: Enhancing Remote Rehabilitation with Virtual Reality and Electromyography

Author Spotlight: Enhancing Remote Rehabilitation with Virtual Reality and Electromyography

Published on: January 12, 2024

An Inertial Measurement Unit Based Method to Estimate Hip and Knee Joint Kinematics in Team Sport Athletes on the Field

An Inertial Measurement Unit Based Method to Estimate Hip and Knee Joint Kinematics in Team Sport Athletes on the Field

Published on: May 26, 2020

Area of Science:

Biomedical Engineering
Computer Science
Robotics

Background:

Commercial motion capture systems are complex and not consumer-friendly.
Wearable sensors offer a solution for human posture reconstruction.
Existing methods face challenges in data selection and sensor placement.

Purpose of the Study:

To develop a deep learning-based method for human posture reconstruction using sparse inertial sensors.
To address challenges in training data selection and optimal sensor placement for specific scenarios.
To improve accuracy and efficiency in human motion analysis.

Main Methods:

Utilized a bidirectional recurrent neural network (Bi-RNN) for mapping low-dimensional sensor data to whole-body posture.
Formulated data selection as an optimization problem to find independent and identically distributed (IID) data segments.
Employed mutual information to evaluate sensor placement and a greedy search for optimal configuration.
Developed a two-step heuristic algorithm for data selection.

Main Results:

The proposed deep learning method demonstrated advantages in posture reconstruction accuracy and model training time.
Achieved low posture reconstruction errors: 7.25° for walking, 8.84° for running, and 14.13° for basketball with 6 sensors.
Optimized data selection and sensor placement significantly improved reconstruction performance.

Conclusions:

The deep learning approach with sparse inertial sensors provides an effective solution for consumer-level human posture reconstruction.
Optimizing training data and sensor placement are crucial for enhancing model performance in specific applications.
This method offers a promising direction for accessible and accurate human motion analysis.