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

Search research articles

Related Experiment Video

Updated: Oct 15, 2025

DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning

DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning

Published on: May 10, 2024

Using a multi-head, convolutional neural network with data augmentation to improve electropherogram classification

Duncan Taylor¹

¹Forensic Science South Australia, 21 Divett Place, Adelaide, SA 5000, Australia; Flinders University, GPO Box 2100, Adelaide, SA 5001, Australia.

Forensic Science International. Genetics

|October 23, 2021

Summary

This summary is machine-generated.

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

Using hierarchical Bayesian modelling to assess shedder test suitability.

Forensic science international. Genetics·2026

Same author

Probabilistic searching of databases compared to binary CODIS eligibility: An improved methodology for maximizing investigative leads using short tandem repeat DNA profiles.

Forensic science international. Genetics·2026

Same author

deepNoC: A deep learning system to assign the number of contributors to a short tandem repeat DNA profile.

Forensic science international. Genetics·2026

Same author

A matter of age: Investigation of the ability to classify epithelial cells of different anatomical origin in aged samples using imaging flow cytometry.

Forensic science international·2026

Same author

STR-Uggles: Overcoming Humic Acid Inhibition Using Combined STR & qPCR Kit Chemistries.

Genes·2025

Same author

An investigation into the background levels of DNA and saliva typically detectable on penises.

International journal of legal medicine·2025

Same journal

Comparison of key diagnostics for probabilistic interpretation of STR mixture data generated with length-based and MPS methodologies.

Forensic science international. Genetics·2026

Same journal

Likelihood Ratios Given Activity-Level Propositions for DNA Transfer Evidence: Theoretical Foundations of the HaloGen Framework (Part I).

Forensic science international. Genetics·2026

Same journal

Likelihood Ratios Given Activity-Level Propositions for DNA Transfer Evidence: Practical Implementation and Simulation Studies Using the HaloGen Engine (Part II).

Forensic science international. Genetics·2026

Same journal

Forensic evaluation of 101 identity-informative SNPs in a Filipino population using massively parallel sequencing.

Forensic science international. Genetics·2026

Same journal

Reprocessing of hair roots using conventional forensic DNA analysis following RapidHIT® ID processing.

Forensic science international. Genetics·2026

Same journal

Analysis of low-input and degraded forensic DNA trace samples with NGS using the MiSeq FGx platform.

Forensic science international. Genetics·2026

See all related articles

A new neural network model improves DNA profile analysis in forensic labs. This AI tool enhances the classification of fluorescence in DNA electropherograms, particularly for low-intensity profiles, aiding forensic biology.

Area of Science:

Forensic Biology
Bioinformatics
Machine Learning

Background:

DNA profiles are crucial in forensic biology, often requiring manual interpretation by multiple analysts.
Existing automated systems using neural networks have limitations, especially with low-intensity DNA peaks.

Purpose of the Study:

To develop an improved neural network model for classifying DNA profile electropherograms.
To enhance the accuracy and efficiency of DNA profile analysis in forensic applications.

Main Methods:

Development of a novel neural network architecture incorporating convolutional layers and a multi-head design.
Implementation of data augmentation techniques to improve model robustness.
Validation of the model's performance on DNA profile electropherograms.

Keywords:

Convolutional neural network Data augmentation Electropherogram FaSTR DNA

More Related Videos

A Computer-assisted Multi-electrode Patch-clamp System

A Computer-assisted Multi-electrode Patch-clamp System

Published on: October 18, 2013

Computer-based Multitaper Spectrogram Program for Electroencephalographic Data

Computer-based Multitaper Spectrogram Program for Electroencephalographic Data

Published on: November 13, 2019

Related Experiment Videos

Last Updated: Oct 15, 2025

DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning

DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning

Published on: May 10, 2024

A Computer-assisted Multi-electrode Patch-clamp System

A Computer-assisted Multi-electrode Patch-clamp System

Published on: October 18, 2013

Computer-based Multitaper Spectrogram Program for Electroencephalographic Data

Computer-based Multitaper Spectrogram Program for Electroencephalographic Data

Published on: November 13, 2019

Main Results:

The new model demonstrates improved performance, particularly for low-intensity DNA profiles.
The enhanced architecture addresses limitations of previous neural network approaches.
The system shows potential for replacing or assisting human interpretation in forensic DNA analysis.

Conclusions:

The developed neural network offers a more effective automated solution for DNA profile analysis.
This advancement can lead to more reliable and efficient forensic casework.
Further integration into forensic software like FaSTR™ DNA is promising.