Cargando…

Artificial intelligence versus natural selection: Using computer vision techniques to classify bees and bee mimics

Many groups of stingless insects have independently evolved mimicry of bees to fool would-be predators. To investigate this mimicry, we trained artificial intelligence (AI) algorithms—specifically, computer vision—to classify citizen scientist images of bees, bumble bees, and diverse bee mimics. For...

Descripción completa

Detalles Bibliográficos
Autores principales: Bhuiyan, Tanvir, Carney, Ryan M., Chellappan, Sriram
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Elsevier 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9437854/
https://www.ncbi.nlm.nih.gov/pubmed/36060073
http://dx.doi.org/10.1016/j.isci.2022.104924
_version_ 1784781704262582272
author Bhuiyan, Tanvir
Carney, Ryan M.
Chellappan, Sriram
author_facet Bhuiyan, Tanvir
Carney, Ryan M.
Chellappan, Sriram
author_sort Bhuiyan, Tanvir
collection PubMed
description Many groups of stingless insects have independently evolved mimicry of bees to fool would-be predators. To investigate this mimicry, we trained artificial intelligence (AI) algorithms—specifically, computer vision—to classify citizen scientist images of bees, bumble bees, and diverse bee mimics. For detecting bees and bumble bees, our models achieved accuracies of [Formula: see text] and [Formula: see text] , respectively. As a proxy for a natural predator, our models were poorest in detecting bee mimics that exhibit both aggressive and defensive mimicry. Using the explainable AI method of class activation maps, we validated that our models learn from appropriate components within the image, which in turn provided anatomical insights. Our t-SNE plot yielded perfect within-group clustering, as well as between-group clustering that grossly replicated the phylogeny. Ultimately, the transdisciplinary approaches herein can enhance global citizen science efforts as well as investigations of mimicry and morphology of bees and other insects.
format Online
Article
Text
id pubmed-9437854
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher Elsevier
record_format MEDLINE/PubMed
spelling pubmed-94378542022-09-03 Artificial intelligence versus natural selection: Using computer vision techniques to classify bees and bee mimics Bhuiyan, Tanvir Carney, Ryan M. Chellappan, Sriram iScience Article Many groups of stingless insects have independently evolved mimicry of bees to fool would-be predators. To investigate this mimicry, we trained artificial intelligence (AI) algorithms—specifically, computer vision—to classify citizen scientist images of bees, bumble bees, and diverse bee mimics. For detecting bees and bumble bees, our models achieved accuracies of [Formula: see text] and [Formula: see text] , respectively. As a proxy for a natural predator, our models were poorest in detecting bee mimics that exhibit both aggressive and defensive mimicry. Using the explainable AI method of class activation maps, we validated that our models learn from appropriate components within the image, which in turn provided anatomical insights. Our t-SNE plot yielded perfect within-group clustering, as well as between-group clustering that grossly replicated the phylogeny. Ultimately, the transdisciplinary approaches herein can enhance global citizen science efforts as well as investigations of mimicry and morphology of bees and other insects. Elsevier 2022-08-13 /pmc/articles/PMC9437854/ /pubmed/36060073 http://dx.doi.org/10.1016/j.isci.2022.104924 Text en © 2022 The Authors https://creativecommons.org/licenses/by-nc-nd/4.0/This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).
spellingShingle Article
Bhuiyan, Tanvir
Carney, Ryan M.
Chellappan, Sriram
Artificial intelligence versus natural selection: Using computer vision techniques to classify bees and bee mimics
title Artificial intelligence versus natural selection: Using computer vision techniques to classify bees and bee mimics
title_full Artificial intelligence versus natural selection: Using computer vision techniques to classify bees and bee mimics
title_fullStr Artificial intelligence versus natural selection: Using computer vision techniques to classify bees and bee mimics
title_full_unstemmed Artificial intelligence versus natural selection: Using computer vision techniques to classify bees and bee mimics
title_short Artificial intelligence versus natural selection: Using computer vision techniques to classify bees and bee mimics
title_sort artificial intelligence versus natural selection: using computer vision techniques to classify bees and bee mimics
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9437854/
https://www.ncbi.nlm.nih.gov/pubmed/36060073
http://dx.doi.org/10.1016/j.isci.2022.104924
work_keys_str_mv AT bhuiyantanvir artificialintelligenceversusnaturalselectionusingcomputervisiontechniquestoclassifybeesandbeemimics
AT carneyryanm artificialintelligenceversusnaturalselectionusingcomputervisiontechniquestoclassifybeesandbeemimics
AT chellappansriram artificialintelligenceversusnaturalselectionusingcomputervisiontechniquestoclassifybeesandbeemimics