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

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

External validation of four models predicting treatment success after interdisciplinary multimodal pain treatment.

Disability and rehabilitation·2026

Same author

Identifying Gait Patterns in Sub-Acute Stroke Patients Based on Open Access Gait Kinematics.

IEEE ... International Conference on Rehabilitation Robotics : [proceedings]·2025

Same author

Machine Learning Clinical Decision Support for Interdisciplinary Multimodal Chronic Musculoskeletal Pain Treatment: Prospective Pilot Study of Patient Assessment and Prognostic Profile Validation.

JMIR rehabilitation and assistive technologies·2025

Same author

Shoulder and Elbow Symptoms in Dutch High School Baseball Pitchers: Results of a Two-Season Prospective Study.

Journal of athletic training·2024

Same author

Using Wearable Sensors to Estimate Mechanical Power Output in Cyclical Sports Other than Cycling-A Review.

Sensors (Basel, Switzerland)·2023

Same author

Cross-Cultural Adaption and Validation of the Dutch Version of the Kerlan-Jobe Orthopaedic Clinic Questionnaire in Juvenile Baseball Pitchers.

Sports (Basel, Switzerland)·2022

Search research articles

Related Experiment Video

Updated: Jul 9, 2025

Author Spotlight: Enhancing Remote Rehabilitation with Virtual Reality and Electromyography

Author Spotlight: Enhancing Remote Rehabilitation with Virtual Reality and Electromyography

Published on: January 12, 2024

Machine Learning Approach for Pitch Type Classification Based on Pelvis and Trunk Kinematics Captured with Wearable

Larisa Gomaz^1,2, Celine Bouwmeester², Erik van der Graaff³

¹Delft Institute of Applied Mathematics, Delft University of Technology, 2628 CD Delft, The Netherlands.

Sensors (Basel, Switzerland)

|December 9, 2023

Summary

Wearable sensors can automatically classify baseball pitch types using pelvis and trunk movement data. Machine learning models like Random Forest offer actionable insights for optimizing pitcher training and performance.

Keywords:

baseball classification pitch types pitching wearables

More Related Videos

Quantified Assessment of Infant's Gross Motor Abilities Using a Multisensor Wearable

Quantified Assessment of Infant's Gross Motor Abilities Using a Multisensor Wearable

Published on: May 17, 2024

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

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

Related Experiment Videos

Last Updated: Jul 9, 2025

Author Spotlight: Enhancing Remote Rehabilitation with Virtual Reality and Electromyography

Author Spotlight: Enhancing Remote Rehabilitation with Virtual Reality and Electromyography

Published on: January 12, 2024

Quantified Assessment of Infant's Gross Motor Abilities Using a Multisensor Wearable

Quantified Assessment of Infant's Gross Motor Abilities Using a Multisensor Wearable

Published on: May 17, 2024

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

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

Area of Science:

Sports Science
Biomechanics
Machine Learning

Background:

Wearable devices generate extensive data for athlete training and performance monitoring.
Individualized insights from data-driven training remain a challenge.
Pitching mechanics and pitch type are crucial for baseball pitcher performance and injury prevention.

Purpose of the Study:

To develop a machine learning approach for classifying baseball pitch types.
To utilize data from wearable sensors (PITCHPERFECT) measuring pelvis and trunk peak angular velocity and separation time.
To provide actionable insights for optimizing pitching performance and injury risk management.

Main Methods:

Employed wearable sensors (PITCHPERFECT) to record kinematic and temporal parameters of pitching.
Applied machine learning algorithms, including Naive Bayes for binary classification and Random Forest for multiclass classification.
Focused on pelvis and trunk peak angular velocity and their separation time as key features.

Main Results:

The Random Forest algorithm achieved the highest accuracy in multiclass pitch type classification.
Fastball classification accuracy reached 71%.
Classification accuracy for three different pitch types was 61.3%.

Conclusions:

Wearable sensor technology shows significant potential for enhancing baseball pitching analysis.
Automatic pitch type detection based on kinematic data can offer valuable feedback for training.
This approach provides actionable insights for pitchers across all competitive levels.