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

Infrared and Visible Image Fusion Network Based on Self-Compensating Lightweight Convolution.

Sensors (Basel, Switzerland)·2026
Same author

A new hybrid model of convolutional neural networks and hidden Markov chains for image classification.

Neural computing & applications·2023
Same author

A framework based on hidden Markov trees for multimodal PET/CT image co-segmentation.

Medical physics·2017
Same author

Phasic Triplet Markov Chains.

IEEE transactions on pattern analysis and machine intelligence·2015
Same author

Unsupervised statistical segmentation of nonstationary images using triplet Markov fields.

IEEE transactions on pattern analysis and machine intelligence·2007

Related Experiment Video

Updated: Jan 6, 2026

Home-Based Monitor for Gait and Activity Analysis
07:24

Home-Based Monitor for Gait and Activity Analysis

Published on: August 8, 2019

7.2K

Lower Limb Locomotion Activity Recognition of Healthy Individuals Using Semi-Markov Model and Single Wearable

Haoyu Li1, Stéphane Derrode2, Wojciech Pieczynski3

  • 1LIRIS, CNRS UMR 5205, École Centrale de Lyon, 69130 Ecully, France. haoyuli1990@gmail.com.

Sensors (Basel, Switzerland)
|October 2, 2019
PubMed
Summary

This study introduces a novel semi-Markov model for recognizing lower limb locomotion activities using gait phases. The method achieves high accuracy, demonstrating its effectiveness for human activity recognition.

Keywords:
gait analysislower limb locomotion activityon-line EM algorithmsemi-Markov modeltriplet Markov model

More Related Videos

An Inertial Measurement Unit Based Method to Estimate Hip and Knee Joint Kinematics in Team Sport Athletes on the Field
06:52

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

8.4K
Oscillation and Reaction Board Techniques for Estimating Inertial Properties of a Below-knee Prosthesis
08:08

Oscillation and Reaction Board Techniques for Estimating Inertial Properties of a Below-knee Prosthesis

Published on: May 8, 2014

17.2K

Related Experiment Videos

Last Updated: Jan 6, 2026

Home-Based Monitor for Gait and Activity Analysis
07:24

Home-Based Monitor for Gait and Activity Analysis

Published on: August 8, 2019

7.2K
An Inertial Measurement Unit Based Method to Estimate Hip and Knee Joint Kinematics in Team Sport Athletes on the Field
06:52

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

8.4K
Oscillation and Reaction Board Techniques for Estimating Inertial Properties of a Below-knee Prosthesis
08:08

Oscillation and Reaction Board Techniques for Estimating Inertial Properties of a Below-knee Prosthesis

Published on: May 8, 2014

17.2K

Area of Science:

  • Biomedical Engineering
  • Computer Science
  • Human Activity Recognition

Background:

  • Lower limb locomotion activity is crucial for human activity recognition.
  • Periodic lower limb movements present unique challenges for accurate recognition.

Purpose of the Study:

  • To propose a novel triplet semi-Markov model for recognizing human locomotion activities.
  • To enhance the accuracy and adaptability of activity recognition systems.

Main Methods:

  • Utilized a triplet semi-Markov model incorporating gait phases into hidden states.
  • Employed Gaussian mixture density for complex conditioned observation density.
  • Developed batch mode and on-line Expectation-Maximization (EM) algorithms for training and recognition.

Main Results:

  • Achieved up to 95.16% accuracy in batch mode recognition.
  • Demonstrated adaptive on-line recognition with gradual accuracy improvement.
  • Showcased superior performance compared to existing algorithms on wearable inertial sensor datasets.

Conclusions:

  • The proposed semi-Markov model effectively recognizes lower limb locomotion activities.
  • The method offers robust and adaptive recognition capabilities for real-world applications.
  • This approach advances the field of human activity recognition using sensor data.