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

Effects of temperature on the life-history traits of <i>Myzus persicae</i> and its efficiency in transmitting potato virus Y (PVY) in potato crops.

PeerJ·2026
Same author

Modelling the temporal dynamics of Microsporidia MB prevalence in Anopheles mosquitoes under environmental variability.

Scientific reports·2026
Same author

Spatial-temporal coupling of malaria vector habitat suitability and biting probability.

Spatial and spatio-temporal epidemiology·2026
Same author

Mapping Robusta coffee (Coffea canephora) cropping systems in Uganda: A two-step pixel and sub-pixel based approach with Sentinel-2 data.

PloS one·2026
Same author

Roadmap for mainstreaming integrated pest management (IPM) into a climate smart one-health (CS-OH) framework.

One health (Amsterdam, Netherlands)·2025
Same author

An eco-epidemiological model for malaria with <i>Microsporidia MB</i> as bio-control agent.

Modeling earth systems and environment·2025

Related Experiment Video

Updated: Sep 24, 2025

Two Algorithms for High-throughput and Multi-parametric Quantification of Drosophila Neuromuscular Junction Morphology
12:29

Two Algorithms for High-throughput and Multi-parametric Quantification of Drosophila Neuromuscular Junction Morphology

Published on: May 3, 2017

10.7K

Leveraging machine learning tools and algorithms for analysis of fruit fly morphometrics.

Daisy Salifu1, Eric Ali Ibrahim2,3, Henri E Z Tonnang2

  • 1International Centre of Insect Physiology and Ecology (icipe), P.O. Box 30772-00100, Nairobi, Kenya. dsalifu@icipe.org.

Scientific Reports
|May 3, 2022
PubMed
Summary

Machine learning models, specifically Support Vector Machines (SVM) and Artificial Neural Networks (ANNs), accurately identify fruit flies using morphometric data. These advanced methods outperform traditional analyses for insect identification and taxonomic studies.

More Related Videos

Author Spotlight: Quantifying Rough Eye Phenotypes in Drosophila Models of Amyotrophic Lateral Sclerosis with Frontotemporal Dementia
05:25

Author Spotlight: Quantifying Rough Eye Phenotypes in Drosophila Models of Amyotrophic Lateral Sclerosis with Frontotemporal Dementia

Published on: October 4, 2024

1.1K
Experimental Manipulation of Body Size to Estimate Morphological Scaling Relationships in Drosophila
06:00

Experimental Manipulation of Body Size to Estimate Morphological Scaling Relationships in Drosophila

Published on: October 1, 2011

14.0K

Related Experiment Videos

Last Updated: Sep 24, 2025

Two Algorithms for High-throughput and Multi-parametric Quantification of Drosophila Neuromuscular Junction Morphology
12:29

Two Algorithms for High-throughput and Multi-parametric Quantification of Drosophila Neuromuscular Junction Morphology

Published on: May 3, 2017

10.7K
Author Spotlight: Quantifying Rough Eye Phenotypes in Drosophila Models of Amyotrophic Lateral Sclerosis with Frontotemporal Dementia
05:25

Author Spotlight: Quantifying Rough Eye Phenotypes in Drosophila Models of Amyotrophic Lateral Sclerosis with Frontotemporal Dementia

Published on: October 4, 2024

1.1K
Experimental Manipulation of Body Size to Estimate Morphological Scaling Relationships in Drosophila
06:00

Experimental Manipulation of Body Size to Estimate Morphological Scaling Relationships in Drosophila

Published on: October 1, 2011

14.0K

Area of Science:

  • Entomology
  • Bioinformatics
  • Computational Biology

Background:

  • Morphometric analysis is a traditional method for insect identification, often complemented by DNA barcoding.
  • Statistical analysis of morphometrics has historically relied on methods like Principal Component Analysis (PCA) and Canonical Variate Analysis (CVA).
  • Advancements in computing power enable the application of modern machine learning tools to biological data analysis.

Purpose of the Study:

  • To evaluate the predictive performance of four machine learning classifiers (KNN, RF, SVM, ANN) on fruit fly morphometric data.
  • To compare the efficacy of machine learning models against traditional statistical approaches (PCA, CVA) for insect identification.
  • To identify key morphometric variables important for discriminating fruit fly species.

Main Methods:

  • Applied K-nearest neighbor (KNN), random forest (RF), Support Vector Machine (SVM) with linear, polynomial, and radial kernels, and Artificial Neural Network (ANN) classifiers.
  • Utilized landmark-based morphometric measurements of fruit fly body parts.
  • Assessed model performance using accuracy, Kappa statistic, and Area Under the Curve (AUC) of receiver operating characteristic curves.

Main Results:

  • KNN and RF models showed poor performance, with accuracy below the 'no-information rate' (NIR).
  • SVM models achieved >95% predictive accuracy, significantly outperforming NIR (p < 0.001), with Kappa > 0.78 and AUC > 0.91.
  • The ANN model demonstrated 96% predictive accuracy, with Kappa of 0.83 and AUC of 0.98, significantly higher than NIR.
  • Wing vein measurements (2, 3, 8, 10, 14) and tibia length were identified as crucial variables by both SVM and ANN models.

Conclusions:

  • Support Vector Machine (SVM) and Artificial Neural Network (ANN) models are effective for discriminating fruit fly species using morphometric data, particularly wing vein and tibia length.
  • These machine learning algorithms show promise for developing integrated, smart application software for insect identification.
  • Variable importance analysis provides valuable insights for future studies, guiding the selection of essential morphometric measurements for pest taxa identification.