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: Jun 4, 2026

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

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

Published on: June 18, 2020

Semi-automated detection of cleaning interactions using supervised machine learning.

Raul Oliveira¹, Nuno Cruz Garcia², José Ricardo Paula^3,4

¹MARE - Marine and Environmental Sciences Centre & ARNET - Aquatic Research Network, Laboratório Marítimo da Guia, Faculdade de Ciências Universidade de Lisboa, Av. Nossa Senhora do Cabo 939, 2750-374, Cascais, Portugal.

Scientific Reports

|June 2, 2026

Summary

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

Developmental and transcriptomic responses of Hawaiian bobtail squid early stages to ocean warming and acidification.

Proceedings. Biological sciences·2026

Same author

The impact of pre-processing techniques on deep learning breast image segmentation.

Scientific reports·2025

Same author

Fourier Transforms the way we see B-lines in Lung Ultrasound.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference·2025

Same author

Neck Pain in Dental Education: A Cross-Sectional Analysis of Neck Strength Differences.

Muscles (Basel, Switzerland)·2025

Same author

Depression- and exercise-associated stimuli exert contrasting effects on neural stem cell activity and paracrine signaling.

Biochimica et biophysica acta. Molecular basis of disease·2025

Same author

Hypoxia impairs survival and alters immune and iron metabolism gene expression during shark early ontogeny.

Comparative biochemistry and physiology. Part A, Molecular & integrative physiology·2025

This summary is machine-generated.

Researchers developed a semi-automated system using deep learning to track and classify cleaner fish interactions. This method significantly reduces manual labor and improves the efficiency of analyzing mutualistic behaviors in marine ecosystems.

Area of Science:

Marine Biology
Ethology
Bio-acoustics

Background:

Cleaner fish and client species exhibit mutualistic interactions vital for marine ecosystem health.
Traditional manual video analysis for quantifying these interactions is labor-intensive, time-consuming, and prone to errors.
Automated behavioral analysis tools are needed to improve efficiency and accuracy in ecological research.

Purpose of the Study:

To develop and validate a semi-automated system for tracking and classifying cleaning interactions between cleaner wrasse and powder blue tang.
To reduce the reliance on manual video analysis for behavioral quantification in marine mutualisms.
To establish a foundation for automated ethological analysis in marine environments.

Main Methods:

Utilized DeepLabCut (DLC), a deep learning-based tool for markerless pose estimation, to track both fish species in a 3D laboratory setting.

Keywords:

Labroides dimidiatus Animal behaviour Automation Cleaning mutualisms DeepLabCut Interaction classification

Related Experiment Videos

Last Updated: Jun 4, 2026

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

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

Published on: June 18, 2020

Developed a classification algorithm using the generated tracking data to identify cleaning interactions.

Quantified the accuracy of the tracking model and the classification algorithm in detecting interactions.

Main Results:

The DLC model reliably tracked both cleaner wrasse and powder blue tang with low error rates.
The classification algorithm achieved 90% accuracy in detecting cleaning interactions.
The system reduced the need for manual annotation by 75%, identifying 25% of video content as interactions.

Conclusions:

The developed semi-automated system significantly decreases human labor in behavioral analysis while maintaining high classification performance.
This approach offers a valuable advancement for automating behavioral analysis in marine mutualisms.
The system can be adapted for broader applications in ethology and marine conservation research.