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

Application of Linearization and Approximation01:29

Application of Linearization and Approximation

37
A drone flying through complex terrain often relies on more than one sensing method to estimate small changes in altitude. Along with direct measurements, air pressure provides a useful indirect indicator of vertical movement. Atmospheric pressure decreases as altitude increases, and this relationship is commonly described using an exponential model. Although accurate, converting pressure measurements into altitude values requires calculations that are too complex to perform repeatedly during...
37
Elevation of Intermediate Points on Vertical Curves01:20

Elevation of Intermediate Points on Vertical Curves

270
Vertical curves are essential in roadway design because they provide smooth transitions between varying roadway grades. Designing vertical curves involves calculating intermediate elevations and identifying the curve's highest or lowest point, which is essential for optimal roadway performance.Intermediate elevations on a vertical curve are determined using the tangent offset method. This method considers the initial elevation at the start of the curve, the grades, and the curve's geometry. The...
270

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Trends in mortality with chronic obstructive pulmonary disease as the underlying cause and chronic kidney disease as a contributing cause among US adults, 1999-2020: a CDC WONDER analysis.

BMC pulmonary medicine·2026
Same author

Evaluating the prognostic value of cuproptosis-related genes and characterizing PDE3B's role in gastric cancer: integrative bioinformatics analysis and experimental validation.

Journal of gastrointestinal oncology·2026
Same author

8-Oxoguanine Modified CircMTUS1 Drives PABPC1 Phase Separation to Promote Gastric Cancer Progression and Cisplatin Resistance via Autophagy.

Advanced science (Weinheim, Baden-Wurttemberg, Germany)·2026
Same author

Low thyroid hormone status as a cardiovascular risk factor: A cross-sectional study from NHANES 2007-2012.

Medicine·2026
Same author

Successful removal of a deeply embedded esophageal foreign body using endoscopic submucosal dissection: a case report.

Endoscopy·2026
Same author

The effects of saddle height and power output on lower-limb muscles and joints during cycling.

BMC sports science, medicine & rehabilitation·2026

Related Experiment Video

Updated: Jan 16, 2026

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines
08:27

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines

Published on: January 5, 2024

1.6K

A machine learning approach for saddle height classification in cycling.

Fangbo Bing1, Guoxin Zhang1, Linjuan Wei1

  • 1Department of Biomedical Engineering, Faculty of Engineering, The Hong Kong Polytechnic University, Hong Kong SAR, China.

Frontiers in Sports and Active Living
|October 3, 2025
PubMed
Summary

This study introduces a machine learning model to determine optimal bike saddle height using joint angle data. The model achieves 99.79% accuracy, offering a personalized approach to cycling efficiency and injury prevention.

Keywords:
cyclingjoint anglelower limbmachine learningsaddle height

More Related Videos

Visualization Method for Proprioceptive Drift on a 2D Plane Using Support Vector Machine
07:05

Visualization Method for Proprioceptive Drift on a 2D Plane Using Support Vector Machine

Published on: October 27, 2016

9.6K
Design and Analysis for Fall Detection System Simplification
08:05

Design and Analysis for Fall Detection System Simplification

Published on: April 6, 2020

11.1K

Related Experiment Videos

Last Updated: Jan 16, 2026

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines
08:27

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines

Published on: January 5, 2024

1.6K
Visualization Method for Proprioceptive Drift on a 2D Plane Using Support Vector Machine
07:05

Visualization Method for Proprioceptive Drift on a 2D Plane Using Support Vector Machine

Published on: October 27, 2016

9.6K
Design and Analysis for Fall Detection System Simplification
08:05

Design and Analysis for Fall Detection System Simplification

Published on: April 6, 2020

11.1K

Area of Science:

  • Biomechanics
  • Sports Science
  • Machine Learning

Background:

  • Saddle height significantly impacts cycling efficiency and injury risk.
  • Traditional bike fitting methods rely on static anthropometrics and joint angles.
  • Existing approaches overlook individual dynamic variations during cycling.

Purpose of the Study:

  • To develop a machine learning (ML) model for calculating optimal saddle height.
  • To utilize easily measurable kinematic data for saddle height determination.
  • To provide a data-driven personalization tool for bike fitting.

Main Methods:

  • 16 subjects underwent cycling tests at varying saddle heights.
  • Motion capture recorded lower limb marker trajectories.
  • Hip, knee, and ankle joint angles were used as features.
  • Forward sequential feature selection identified the optimal feature set.
  • Leave-one-subject-out cross-validation compared four ML models.

Main Results:

  • The optimal feature set included 14 joint angle-related features.
  • Sagittal plane knee angle was most sensitive (80% accuracy).
  • The k-nearest neighbor model achieved 99.79% accuracy with optimal features.

Conclusions:

  • The ML model accounts for individual dynamic differences in cycling.
  • This offers a more objective tool compared to traditional methods.
  • Enables data-driven personalization for improved bike fitting.