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 Videos

PCA in studying coordination and variability: a tutorial.

Andreas Daffertshofer1, Claudine J C Lamoth, Onno G Meijer

  • 1Faculty of Human Movement Sciences, Institute for Fundamental and Clinical Human Movement Sciences, Van der Boechorststraat 9, Vrije Universiteit, 1081 BT Amsterdam, The Netherlands. A_daffertshofer@fbw.vu.nl

Clinical Biomechanics (Bristol, Avon)
|April 28, 2004
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

A machine learning model to detect falls mimicking cardiac arrest-related collapse based on wrist-derived accelerometry: the DETECT-2 study.

European heart journal. Digital health·2026
Same author

The effects of gait speed on the responses to immediate and prolonged exposure to mediolateral optic flow perturbation in healthy young adults.

Human movement science·2026
Same author

A Comparison of Experimental Methods to Induce Mental Fatigue.

Perceptual and motor skills·2026
Same author

Shoulder elevation and arm extension influence elbow joint loading during door-opening in total elbow arthroplasty: a musculoskeletal modelling study.

Journal of biomechanics·2025
Same author

Classifying Soccer Players Based on Physical Capacities and Match-Specific Running Performance Using Machine Learning.

Journal of sports science & medicine·2025
Same author

Factors contributing to differences in physical activity levels in (pre)frail older adults living in rural areas of China.

PloS one·2025
Same journal

Interlimb differences in knee joint loading and stress distribution following anterior cruciate ligament reconstruction during stair descent.

Clinical biomechanics (Bristol, Avon)·2026
Same journal

Exploring real-world lumbar posture behaviour. A whole day comparison of individuals with low back pain and healthy controls.

Clinical biomechanics (Bristol, Avon)·2026
Same journal

Motor differences in jumping among children with and without autism spectrum disorder.

Clinical biomechanics (Bristol, Avon)·2026
Same journal

Reduced lower extremity strength, altered muscle activation, and unchanged kinetics during single-leg squatting in males with patellofemoral pain versus pain-free males: A cross-sectional analysis.

Clinical biomechanics (Bristol, Avon)·2026
Same journal

Ensuring bone-to-bone contact reduces interfragmentary strain in forearm shaft plating: A finite element study.

Clinical biomechanics (Bristol, Avon)·2026
Same journal

Acute changes in gait biomechanics in children with cerebral palsy due to barefoot vs. footwear condition - An exploratory study.

Clinical biomechanics (Bristol, Avon)·2026
See all related articles

Principal Component Analysis (PCA) effectively reduces complex biomechanical data into key modes. This method also separates stable movement structures from variations, aiding in the analysis of motor variability.

Area of Science:

  • Clinical Biomechanics
  • Human Movement Science
  • Data Analysis

Background:

  • Principal Component Analysis (PCA) is a standard technique for reducing redundant information in multidimensional datasets.
  • PCA is increasingly relevant in human movement studies, necessitating clear explanations of its applications and limitations.
  • Beyond mode reduction, PCA can act as a data-driven filter to separate invariant and variant properties of coordination, crucial for studying motor variability.

Purpose of the Study:

  • To demonstrate Principal Component Analysis (PCA) as an efficient and unbiased method for data reduction in clinical biomechanics.
  • To highlight PCA's utility in identifying underlying modes or structures within high-dimensional datasets.
  • To showcase PCA's capability in distinguishing between structural (invariant) and variable components of movement data.

Related Experiment Videos

Main Methods:

  • Principal Component Analysis (PCA) is formally explained.
  • The method is applied to simulated, kinematic, and electromyographic data for illustrative purposes.
  • PCA is specifically applied to kinematic and electromyographic time series from healthy individuals during treadmill walking.

Main Results:

  • Interpretable common signal structures (modes) were identified in the time series data.
  • Eliminating these coherent modes revealed filtered residual patterns.
  • These residual patterns provide valuable insights into motor variability.

Conclusions:

  • Principal Component Analysis (PCA) successfully detects modes for information reduction in kinematic and electromyographic datasets.
  • PCA enables the separation of invariant structure from variance within movement data.
  • PCA is a valuable tool for feature extraction and data filtering in movement analysis, with significant untapped potential in clinical applications like diagnostics and intervention evaluation.