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

Force Classification

Force Classification

Forces play a crucial role in the study of physics and engineering. They are essential in describing the motion, behavior, and equilibrium of objects in the physical world. Forces can be classified based on their origin, type, and direction of action.
Contact and non-contact forces are two of the most widely used categories of forces. As the name suggests, contact forces require physical contact between two objects to act upon each other. Examples of contact forces include frictional,...

You might also read

Related Articles

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

Sort by

Same author

Carbocisteine or Hypertonic Saline for Acute Respiratory Failure.

The New England journal of medicine·2026

Same author

A Machine learning framework for calf muscle fatigue assessment using IMU sensors and EMG-Based labeling.

Journal of electromyography and kinesiology : official journal of the International Society of Electrophysiological Kinesiology·2026

Same author

Effectiveness of mucoactives (carbocisteine and hypertonic saline) in addition to usual airway clearance management with usual airway clearance management alone in acute respiratory failure (MARCH): study protocol for a multi-centre 2x2 factorial, randomised, controlled, open-label, Phase 3, pragmatic, clinical and cost-effectiveness trial with internal pilot.

NIHR open research·2025

Same author

Stress ulcer prophylaxis practice in UK critical care units: A comparison of cross-sectional surveys between 2020 and 2024.

Journal of the Intensive Care Society·2025

Same author

Critical care pharmacy workforce: a 2020 re-evaluation of the UK deployment and characteristics.

Human resources for health·2023

Same author

Using Electronic Prescribing to Create a Patient Fingerprint: A New Quality Improvement Method.

American journal of medical quality : the official journal of the American College of Medical Quality·2021

Search research articles

Related Experiment Video

Updated: Jul 9, 2026

Author Spotlight: Enhancing Post-Stroke Upper Limb Rehabilitation with Robotic Technologies for Improved Motor Recovery and Functional Outcomes

Author Spotlight: Enhancing Post-Stroke Upper Limb Rehabilitation with Robotic Technologies for Improved Motor Recovery and Functional Outcomes

Published on: September 6, 2024

An active machine learning framework for automatic boxing punch recognition and classification using upper limb

Saravanan Manoharan¹, John Warburton², Ravi Sadananda Hegde³

¹Department of Applied Mechanics and Biomedical Engineering, Indian Institute of Technology Madras, Chennai, India.

|May 8, 2025

Summary

This summary is machine-generated.

This study introduces an automated system for boxing punch classification using both sensor and video data. The Smart Boxer system significantly reduces manual labeling, achieving high accuracy in recognizing and classifying punches for improved athlete performance.

More Related Videos

Brain-Computer Interface-controlled Upper Limb Robotic System for Enhancing Daily Activities in Stroke Patients

Brain-Computer Interface-controlled Upper Limb Robotic System for Enhancing Daily Activities in Stroke Patients

Published on: April 18, 2025

Capturing Dynamic Finger Gesturing with High-resolution Surface Electromyography and Computer Vision

Capturing Dynamic Finger Gesturing with High-resolution Surface Electromyography and Computer Vision

Published on: March 28, 2025

Related Experiment Videos

Last Updated: Jul 9, 2026

Author Spotlight: Enhancing Post-Stroke Upper Limb Rehabilitation with Robotic Technologies for Improved Motor Recovery and Functional Outcomes

Author Spotlight: Enhancing Post-Stroke Upper Limb Rehabilitation with Robotic Technologies for Improved Motor Recovery and Functional Outcomes

Published on: September 6, 2024

Brain-Computer Interface-controlled Upper Limb Robotic System for Enhancing Daily Activities in Stroke Patients

Brain-Computer Interface-controlled Upper Limb Robotic System for Enhancing Daily Activities in Stroke Patients

Published on: April 18, 2025

Capturing Dynamic Finger Gesturing with High-resolution Surface Electromyography and Computer Vision

Capturing Dynamic Finger Gesturing with High-resolution Surface Electromyography and Computer Vision

Published on: March 28, 2025

Area of Science:

Sports Science
Biomechanical Analysis
Machine Learning in Sports

Background:

Punch classification and kinematic analysis are crucial for boxing performance improvement.
Current methods using sensor or video data lack full automation and face accuracy limitations (e.g., motion blur) or high annotation demands.
Supervised learning requires extensive expert labeling (70-80%), which is time-consuming and prone to inconsistency.

Purpose of the Study:

To develop a fully automated multimodal system for boxing punch recognition and classification.
To improve classification accuracy by integrating wearable sensor and video data with automatic video segmentation.
To significantly reduce the manual data labeling effort required for model training.

Main Methods:

A novel multimodal approach integrating wearable sensor and video data for automatic punch recognition and classification.
Implementation of automatic segmentation of punch videos to enhance classification accuracy.
Application of a Query by Committee-based active learning technique to minimize labeling requirements.

Main Results:

The Smart Boxer system achieved high accuracy: 91.41% for rear-hand punch recognition, 91.91% for lead-hand punch recognition, and 92.33%-94.56% for punch classification.
The active learning technique reduced labeling effort by one-sixth (using only 15% of typical effort).
The multimodal approach and automatic segmentation improved overall classification performance.

Conclusions:

The proposed system offers an effective and efficient solution for automated boxing punch analytics.
This technology can provide valuable insights for training optimization and performance enhancement in boxing.
The Smart Boxer system has the potential to increase fan engagement through improved sports analytics.