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

Fully-Gated Denoising Auto-Encoder for Artifact Reduction in ECG Signals.

Sensors (Basel, Switzerland)·2025

Same author

Prognostic value of P-wave morphology in general population.

Europace : European pacing, arrhythmias, and cardiac electrophysiology : journal of the working groups on cardiac pacing, arrhythmias, and cardiac cellular electrophysiology of the European Society of Cardiology·2022

Same author

Cardiovascular brain impulses in Alzheimer's disease.

Brain : a journal of neurology·2021

Same author

Antioxidant and angiotensin I-converting enzyme inhibitory activities of Xuanwei ham before and after cooking and <i>in vitro</i> simulated gastrointestinal digestion.

Royal Society open science·2018

Same author

The Pathogenesis of Diabetes Mellitus by Oxidative Stress and Inflammation: Its Inhibition by Berberine.

Frontiers in pharmacology·2018

Same author

Effects of lily/maize intercropping on rhizosphere microbial community and yield of Lilium davidii var. unicolor.

Journal of basic microbiology·2018

Search research articles

Related Experiment Video

Updated: Dec 24, 2025

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

A Video-Based DT-SVM School Violence Detecting Algorithm.

Liang Ye^1,2, Le Wang^1,3, Hany Ferdinando^2,4

¹Department of Information and Communication Engineering, Harbin Institute of Technology, Harbin150080, China.

Sensors (Basel, Switzerland)

|April 9, 2020

Summary

This summary is machine-generated.

This study introduces an AI-powered video analysis system to detect school violence. The advanced Decision Tree-SVM model significantly improves accuracy in identifying harmful activities, enhancing student safety.

Keywords:

activity recognition image processing pattern recognition school violence detecting

More Related Videos

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

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

Published on: January 5, 2024

Related Experiment Videos

Last Updated: Dec 24, 2025

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

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

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

Published on: January 5, 2024

Area of Science:

Computer Science
Artificial Intelligence
Machine Learning

Background:

School bullying, particularly physical violence, poses a significant threat to teenagers.
Existing methods for detecting school violence are limited, necessitating advanced technological solutions.
Artificial Intelligence (AI) offers promising avenues for developing sophisticated detection systems.

Purpose of the Study:

To propose and evaluate a novel video-based algorithm for detecting school violence.
To enhance the accuracy and precision of school violence detection using machine learning techniques.
To develop a robust system capable of distinguishing between violent and daily-life activities.

Main Methods:

Utilized K-Nearest Neighbor (KNN) for foreground target detection and morphological processing for preprocessing.
Developed an integrated method for optimizing rectangular frames around moving targets.
Extracted rectangular frame and optical-flow features, employing Relief-F and Wrapper algorithms for feature selection.
Implemented Support Vector Machine (SVM) and a two-layer Decision Tree-SVM (DT-SVM) classifier with 5-fold cross-validation.

Main Results:

The initial SVM classifier achieved 89.6% accuracy and 94.4% precision.
The enhanced DT-SVM classifier demonstrated superior performance, reaching 97.6% accuracy and 97.2% precision.
The DT layer effectively distinguished between physical violence and daily activities, with the SVM layer classifying remaining activities.

Conclusions:

The proposed video-based AI algorithm, particularly the DT-SVM classifier, significantly improves the detection of school violence.
This technology offers a promising tool for enhancing safety and security in educational environments.
The findings highlight the potential of AI in addressing critical issues like school violence through advanced video analysis.