Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

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

Impact of 2'-fluoro nucleobase modifications on CD detection, sensitivity and specificity of short oligonucleotides bound to alginate hydrogels.

Journal of materials chemistry. B·2026
Same author

Encapsulation of degraded DNA in alginate hydrogels: Rheological characterization and applicability to forensic science.

Science & justice : journal of the Forensic Science Society·2026
Same author

DNA methylation and epigenomic profiling post-mortem of human remain analogs (Sus scrofa) in southern Ontario, Canada.

Journal of forensic sciences·2026
Same author

Alginate-based forensic blood substitutes mimicking whole blood clotting and drying properties in drip stains and pools.

Science & justice : journal of the Forensic Science Society·2026
Same author

Responsible adoption of multimodal artificial intelligence in health care: promises and challenges.

The Lancet. Digital health·2025
Same author

Technical note: The impact of image size on bloodstain pattern analysis using machine learning.

Forensic science international·2025

Related Experiment Video

Updated: Jan 16, 2026

Supervised Machine Learning for Semi-Quantification of Extracellular DNA in Glomerulonephritis
09:16

Supervised Machine Learning for Semi-Quantification of Extracellular DNA in Glomerulonephritis

Published on: June 18, 2020

7.3K

Unsupervised machine learning for the detection and interpretation of key features in drip patterns.

Stanard M Pachong1, Ainaz Alavi1, Shaijieni Kannan2

  • 1Faculty of Business and Information Technology, Ontario Tech University, 2000 Simcoe St N, Oshawa, Canada; Faculty of Science, Ontario Tech University, 2000 Simcoe St N, Oshawa, Ontario L1G 0C5, Canada.

Forensic Science International
|October 1, 2025
PubMed
Summary

Unsupervised machine learning (ML) identifies key bloodstain features for objective pattern classification. Circularity, intensity, and area are crucial for distinguishing drip patterns, enhancing forensic analysis.

Keywords:
Bloodstain pattern analysisMachine learningUnsupervised learning

More Related Videos

Chromatographic Fingerprinting by Template Matching for Data Collected by Comprehensive Two-Dimensional Gas Chromatography
10:14

Chromatographic Fingerprinting by Template Matching for Data Collected by Comprehensive Two-Dimensional Gas Chromatography

Published on: September 2, 2020

5.4K
Design and Analysis for Fall Detection System Simplification
08:05

Design and Analysis for Fall Detection System Simplification

Published on: April 6, 2020

11.1K

Related Experiment Videos

Last Updated: Jan 16, 2026

Supervised Machine Learning for Semi-Quantification of Extracellular DNA in Glomerulonephritis
09:16

Supervised Machine Learning for Semi-Quantification of Extracellular DNA in Glomerulonephritis

Published on: June 18, 2020

7.3K
Chromatographic Fingerprinting by Template Matching for Data Collected by Comprehensive Two-Dimensional Gas Chromatography
10:14

Chromatographic Fingerprinting by Template Matching for Data Collected by Comprehensive Two-Dimensional Gas Chromatography

Published on: September 2, 2020

5.4K
Design and Analysis for Fall Detection System Simplification
08:05

Design and Analysis for Fall Detection System Simplification

Published on: April 6, 2020

11.1K

Area of Science:

  • Forensic Science
  • Computer Science
  • Biophysics

Background:

  • Bloodstain pattern analysis (BPA) is moving towards objective methods.
  • Image processing and machine learning (ML) offer new tools for BPA.
  • Identifying key bloodstain features is essential for accurate classification.

Purpose of the Study:

  • To explore unsupervised ML frameworks for identifying bloodstain features.
  • To analyze drip patterns using image-processing techniques.
  • To establish objective criteria for bloodstain pattern classification.

Main Methods:

  • Analyzed 398 laboratory-generated drip patterns.
  • Extracted observable features like size and shape.
  • Applied SHAP analysis to rank feature importance.

Main Results:

  • Circularity, mean intensity, and parent stain area were the most significant features.
  • These features contributed 60%, 28%, and 28% to distinguishing drip patterns, respectively.
  • Unsupervised ML successfully identified key features for classification.

Conclusions:

  • Unsupervised ML frameworks can objectively identify critical bloodstain features.
  • This approach supports the development of image-processing based BPA.
  • The findings align with existing forensic analysis properties and taxonomies.