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 Experiment Video

Updated: Jul 19, 2025

Biomechanical Changes Related to Low Back Pain: An Innovative Tool for Movement Pattern Assessment and Treatment Evaluation in Rehabilitation
06:28

Biomechanical Changes Related to Low Back Pain: An Innovative Tool for Movement Pattern Assessment and Treatment Evaluation in Rehabilitation

Published on: December 13, 2024

568

Machine learning for lumbar and pelvis kinematics clustering.

Seth Higgins1, Sandipan Dutta2, Rumit Singh Kakar1

  • 1Human Movement Science, Oakland University, Rochester Hills, MI, USA.

Computer Methods in Biomechanics and Biomedical Engineering
|August 7, 2023
PubMed
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

An Association Test for Ordinal Outcomes in Clustered Data With Informative Cluster Size.

Pharmaceutical statistics·2026
Same author

Relationship of Age and Running Biomechanics in Female Recreational Runners.

Journal of applied biomechanics·2025
Same author

The effect of incline walking on lower extremity and trunk mechanics in older adults.

Sports medicine and health science·2024
Same author

Exploring the unfolding pathways of protein families using Elastic Network Model.

Scientific reports·2024
Same author

Evaluating the Experience of Teen-to-Teen Crisis Line Volunteers: A Pilot Study.

Community mental health journal·2024
Same author

Most probable paths for active Ornstein-Uhlenbeck particles.

Physical review. E·2023

This study introduces a method for analyzing time-series kinematic data using clustering algorithms. Utilizing multiple evaluation metrics ensures the best algorithm and cluster number for accurate analysis of lumbar and pelvis movement.

Area of Science:

  • Biomechanics and Data Science
  • Computational analysis of human movement

Background:

  • Time-series kinematic data from lumbar and pelvis movement is complex to analyze.
  • Clustering algorithms offer potential for identifying patterns in such data.
  • Determining the optimal clustering approach requires careful evaluation.

Purpose of the Study:

  • To present a systematic approach for selecting clustering algorithms and determining the optimal number of clusters for time-series kinematic data.
  • To evaluate the effectiveness of various cluster evaluation measures in this context.

Main Methods:

  • Application of k-means and agglomerative hierarchical clustering (HCA) to time-series lumbar and pelvis kinematic data.
  • Utilizing cluster evaluation metrics: silhouette coefficient, elbow method, Dunn Index, and gap statistic.
Keywords:
Biomechanicsclusteringtime-seriestrunk flexion/extension

More Related Videos

In Vivo Quantification of Hip Arthrokinematics during Dynamic Weight-bearing Activities using Dual Fluoroscopy
07:43

In Vivo Quantification of Hip Arthrokinematics during Dynamic Weight-bearing Activities using Dual Fluoroscopy

Published on: July 2, 2021

3.1K

Related Experiment Videos

Last Updated: Jul 19, 2025

Biomechanical Changes Related to Low Back Pain: An Innovative Tool for Movement Pattern Assessment and Treatment Evaluation in Rehabilitation
06:28

Biomechanical Changes Related to Low Back Pain: An Innovative Tool for Movement Pattern Assessment and Treatment Evaluation in Rehabilitation

Published on: December 13, 2024

568
In Vivo Quantification of Hip Arthrokinematics during Dynamic Weight-bearing Activities using Dual Fluoroscopy
07:43

In Vivo Quantification of Hip Arthrokinematics during Dynamic Weight-bearing Activities using Dual Fluoroscopy

Published on: July 2, 2021

3.1K
  • Comparative analysis of algorithm performance and cluster validity.

    • Main Results:

    • The study demonstrates that no single clustering evaluation method is universally superior.
    • Optimal cluster number and algorithm choice are dataset-dependent.
    • A combination of multiple evaluation metrics provides a more robust decision-making process.

    Conclusions:

    • Multiple clustering evaluation methods are essential for reliable analysis of time-series kinematic data.
    • This approach enhances the accuracy and interpretability of kinematic pattern identification.
    • The findings support informed algorithm selection for biomechanical data analysis.