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

Predicting future dementia from routine clinical MRI and linked healthcare data.

Alzheimer's research & therapy·2026

Same author

FunduSegmenter: Leveraging the RETFound Foundation Model for Joint Optic Disc and Optic Cup Segmentation in Retinal Fundus Images.

Translational vision science & technology·2026

Same author

Ground truth data set of Gas Chromatography Mass Spectrometry (GCMS) analysed synthesised methylamphetamine.

Data in brief·2026

Same author

Letter to the Editor: The International Forensic Strategic Alliance - A model in global forensic collaboration.

Forensic science international·2026

Same author

Evaluation of nitazene immunoassay test strips for rapid in-situ detection of nitazene and nitazene analogs in illicit drug samples.

Harm reduction journal·2025

Same author

Automated segmentation of the breech and firing pin faces of fired cartridge case images.

Forensic science international·2025

Search research articles

Related Experiment Video

Updated: Jul 28, 2025

Author Spotlight: Development of an Automated Camera-Based System for Real-Time Blast Overpressure Monitoring and TBI Risk Assessment in Military Training

Author Spotlight: Development of an Automated Camera-Based System for Real-Time Blast Overpressure Monitoring and TBI Risk Assessment in Military Training

Published on: December 6, 2024

Identification of bullets fired from air guns using machine and deep learning methods.

Muthu Rama Krishnan Mookiah¹, Roberto Puch-Solis¹, Niamh Nic Daeid¹

¹Leverhulme Research Centre for Forensic Science, School of Science and Engineering, University of Dundee, Nethergate Dundee DD1 4HN, Scotland, UK.

Forensic Science International

|June 2, 2023

Summary

This study introduces an automated method using machine and deep learning to classify bullets based on surface topography and Land Engraved Area (LEA) images. The deep learning approach demonstrated superior performance in linking projectiles to firearms for ballistic examinations.

Keywords:

Air weapons Automated feature extraction Deep learning Empirical mode decomposition Firearm identification Image analysis Machine learning Surface topography measurements

More Related Videos

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

Asthma Detection Research Based on Voice Signal Processing and Machine Learning

Asthma Detection Research Based on Voice Signal Processing and Machine Learning

Published on: July 22, 2025

Related Experiment Videos

Last Updated: Jul 28, 2025

Author Spotlight: Development of an Automated Camera-Based System for Real-Time Blast Overpressure Monitoring and TBI Risk Assessment in Military Training

Author Spotlight: Development of an Automated Camera-Based System for Real-Time Blast Overpressure Monitoring and TBI Risk Assessment in Military Training

Published on: December 6, 2024

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

Asthma Detection Research Based on Voice Signal Processing and Machine Learning

Asthma Detection Research Based on Voice Signal Processing and Machine Learning

Published on: July 22, 2025

Area of Science:

Forensic Science
Computer Science
Mechanical Engineering

Background:

Ballistics, the linkage of bullets and cartridge cases to firearms, is crucial in criminal investigations worldwide.
Determining if bullets originate from the same firearm is a common forensic challenge.
Existing methods for ballistic analysis can be time-consuming and require specialized expertise.

Purpose of the Study:

To propose and evaluate an automated method for classifying bullets using surface topography and Land Engraved Area (LEA) images.
To compare the effectiveness of machine learning and deep learning techniques for ballistic identification.
To develop a proof-of-concept system for expedited firearm linkage and ballistic examinations.

Main Methods:

Surface topography data was processed by removing curvature using loess fit.
Features were extracted using Empirical Mode Decomposition (EMD) and entropy measures, with informative features selected via minimum Redundancy Maximum Relevance (mRMR).
Classifications were performed using Support Vector Machines (SVM), Decision Tree (DT), and Random Forest (RF), alongside the deep learning model DenseNet121 for LEA image classification. Grad-CAM was used for visualization.

Main Results:

Both machine learning and deep learning methods showed good predictive performance in classifying bullets.
The DenseNet121 deep learning model achieved higher predictive performance compared to SVM, DT, and RF classifiers.
Grad-CAM successfully visualized discriminative regions within LEA images, aiding in understanding classification decisions.

Conclusions:

The proposed automated method, particularly the deep learning approach, can significantly expedite the linkage of projectiles to firearms.
The developed techniques show promise for assisting and improving the accuracy of ballistic examinations.
The methodology, tested on air pellets, is expandable to bullet and cartridge case identification from various types of weapons.