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 31, 2025

A Method for Quantifying Upper Limb Performance in Daily Life Using Accelerometers

A Method for Quantifying Upper Limb Performance in Daily Life Using Accelerometers

Published on: April 21, 2017

Fingerprinting walking using wrist-worn accelerometers.

Lily Koffman¹, Yan Zhang¹, Jaroslaw Harezlak²

¹Department of Biostatistics, Johns Hopkins Bloomberg School of Public Health, 615 N Wolfe St., Baltimore, MD, USA.

|May 7, 2023

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

Reliable Change of Blood-Based Biomarkers Following Acute Sport-Related Concussion: A CARE Consortium Study.

Sports medicine (Auckland, N.Z.)·2026

Same author

Discussion on "INTACT: a method for integration of longitudinal physical activity data from multiple sources" by Jingru Zhang, Erjia Cui, Hongzhe Li, and Haochang Shou.

Biometrics·2026

Same author

Associations of accelerometry-derived time in major activity intensities with cognitive outcomes: a compositional data analysis approach.

The journals of gerontology. Series A, Biological sciences and medical sciences·2026

Same author

A Beta-Binomial Model for Estimating Zero- or One-inflated Pain Trajectories.

bioRxiv : the preprint server for biology·2026

Same author

The Genetic and Environmental Architecture of the Human Functional Connectome.

ArXiv·2026

Same author

Low cardiac index during periods of arterial hypotension and risk of acute kidney injury in cardiac surgery.

British journal of anaesthesia·2026

Same journal

Effects of auditory perturbations on recovery dynamics as a component of locomotor resilience in healthy young and older adults.

Gait & posture·2026

Same journal

Systematic analysis of success of lower limb muscle combinations in the prediction of ankle biomechanics during stair descent: Guiding input selection in sEMG-based prosthetic control.

Gait & posture·2026

Same journal

Reliability and minimal detectable change of knee mechanics during gait and squatting, using markerless motion capture in the workplace.

Gait & posture·2026

Same journal

An exploration of the association between knee confidence and knee biomechanics in people with knee osteoarthritis.

Gait & posture·2026

Same journal

A balance-weighted gait score (BWGS) reflects biomechanical and control features of gait in older adults.

Gait & posture·2026

Same journal

Incremental predictive value of spatiotemporal gait parameters beyond clinical measures for achieving independent outdoor ambulation in subacute stroke patients: A retrospective cohort study.

Gait & posture·2026

See all related articles

Researchers developed a new method to identify individuals using their unique walking patterns from accelerometer data. This novel approach achieves 100% accuracy in identifying people based on their gait, offering potential for biometric identification and health monitoring.

Area of Science:

Biometrics
Human Motion Analysis
Machine Learning

Background:

Accurate individual identification from walking accelerometry data, without step-cycle detection, remains a challenge.
Existing methods often rely on step-cycle detection, limiting generalizability and accuracy.

Purpose of the Study:

To introduce an open-source, reproducible method for creating person-specific walking fingerprints from wrist-worn accelerometer data.
To accurately predict an individual's identity using their unique walking fingerprint.

Main Methods:

Collected high-resolution accelerometry data during walking from 32 individuals.
Transformed one-second interval time series into 3D images, partitioned these images into grids, and identified predictive cell combinations.
Utilized a training/testing approach (200s/180s) without stride segmentation for enhanced generalizability.

Keywords:

Accelerometry Biometrics Identification Machine learning

More Related Videos

Home-Based Monitor for Gait and Activity Analysis

Home-Based Monitor for Gait and Activity Analysis

Published on: August 8, 2019

Simulation of Human-induced Vibrations Based on the Characterized In-field Pedestrian Behavior

Simulation of Human-induced Vibrations Based on the Characterized In-field Pedestrian Behavior

Published on: April 13, 2016

Related Experiment Videos

Last Updated: Jul 31, 2025

A Method for Quantifying Upper Limb Performance in Daily Life Using Accelerometers

A Method for Quantifying Upper Limb Performance in Daily Life Using Accelerometers

Published on: April 21, 2017

Home-Based Monitor for Gait and Activity Analysis

Home-Based Monitor for Gait and Activity Analysis

Published on: August 8, 2019

Simulation of Human-induced Vibrations Based on the Characterized In-field Pedestrian Behavior

Simulation of Human-induced Vibrations Based on the Characterized In-field Pedestrian Behavior

Published on: April 13, 2016

Main Results:

The proposed method achieved 100% accuracy in identifying participants in the test dataset.
Unique walking features characterizing individuals were successfully highlighted.
Demonstrated the potential for gait-based identification without relying on step-cycle detection.

Conclusions:

This novel method provides a highly accurate and reproducible way to identify individuals based on their walking patterns.
Walking fingerprints offer a promising alternative or complement to traditional biometric methods like fingerprint, voice, and image recognition.
Individual walking fingerprints may serve as valuable biomarkers for monitoring health status changes over time.