A mobile hybrid deep learning approach for classifying 3D-like representations of Amazonian lizards

Image classification is a highly significant field in machine learning (ML), especially when applied to address longstanding and challenging issues in the biological sciences, such as specie recognition and biodiversity conservation. In this study, we present the development of a hybrid machine lear...

Full description

Saved in:
Bibliographic Details
Main Authors: Arthur Gonsales da Silva, Roger Pinho de Oliveira, Caio de Oliveira Bastos, Elena Almeida de Carvalho, Bruno Duarte Gomes
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-08-01
Series:Frontiers in Artificial Intelligence
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/frai.2025.1524380/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849391304641871872
author Arthur Gonsales da Silva
Arthur Gonsales da Silva
Roger Pinho de Oliveira
Caio de Oliveira Bastos
Caio de Oliveira Bastos
Elena Almeida de Carvalho
Bruno Duarte Gomes
author_facet Arthur Gonsales da Silva
Arthur Gonsales da Silva
Roger Pinho de Oliveira
Caio de Oliveira Bastos
Caio de Oliveira Bastos
Elena Almeida de Carvalho
Bruno Duarte Gomes
author_sort Arthur Gonsales da Silva
collection DOAJ
description Image classification is a highly significant field in machine learning (ML), especially when applied to address longstanding and challenging issues in the biological sciences, such as specie recognition and biodiversity conservation. In this study, we present the development of a hybrid machine learning-based tool suitable for deployment on mobile devices. This tool is aimed at processing and classifying three-dimensional samples of endemic lizard species from the Amazon rainforest. The dataset used in our experiment was collected at the Museu Paraense Emílio Goeldi (MPEG), Belém-PA, Brazil, and comprises three species: (a) Anolis fuscoauratus; (b) Hoplocercus spinosus; and (c) Polychrus marmoratus. We compared the effectiveness of four artificial neural networks (ANN) for feature extraction: (a) MobileNet; (b) MobileNetV2; (c) MobileNetV3-Small; and (d) MobileNetV3-Large. Additionally, we evaluated five classical ML models for classifying the extracted patterns: (a) Support Vector Machine (SVM); (b) GaussianNB (GNB); (c) AdaBoost (ADB); (d) K-Nearest Neighbors (KNN); and (e) Random Forest (RF). The performance metrics of all classifiers were very close, we used the McNemar’s test on each model’s confusion matrix to evaluate and compare their statistical significance. Our best model was a combination of a 2.9 million parameters MobileNetV3-Small as the feature extractor, with a linear kernel-based SVM as the classifier, which achieved accuracy of 0.955, precision of 0.948, recall of 0.948, and f1-score of 0.948. The results indicated that the use of a small deep learning (DL) model, in combination with a classical ML algorithm, emerges as a viable technique for classifying three-dimensional representations of lizard species samples. Such an approach facilitates taxonomic identification work for professionals in the field and provides a tool adaptable for integration into mobile data recording equipment, such as smartphones, and benefiting from more morphological features extracted from three-dimensional samples instead of two-dimensional images.
format Article
id doaj-art-b1c7468df9bd4615b52b91fa2207b0e9
institution Kabale University
issn 2624-8212
language English
publishDate 2025-08-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Artificial Intelligence
spelling doaj-art-b1c7468df9bd4615b52b91fa2207b0e92025-08-20T03:41:05ZengFrontiers Media S.A.Frontiers in Artificial Intelligence2624-82122025-08-01810.3389/frai.2025.15243801524380A mobile hybrid deep learning approach for classifying 3D-like representations of Amazonian lizardsArthur Gonsales da Silva0Arthur Gonsales da Silva1Roger Pinho de Oliveira2Caio de Oliveira Bastos3Caio de Oliveira Bastos4Elena Almeida de Carvalho5Bruno Duarte Gomes6Departamento de Ciência de Dados, Instituto Tecnológico Vale, Belém, BrazilCentro de Ciências Biológicas e da Saúde, Universidade da Amazônia, Belém, BrazilCentro de Ciências Biológicas e da Saúde, Universidade da Amazônia, Belém, BrazilDepartamento de Ciência de Dados, Instituto Tecnológico Vale, Belém, BrazilInstituto de Ciências Biológicas, Universidade Federal do Pará, Belém, BrazilCentro de Ciências Biológicas e da Saúde, Universidade da Amazônia, Belém, BrazilInstituto de Ciências Biológicas, Universidade Federal do Pará, Belém, BrazilImage classification is a highly significant field in machine learning (ML), especially when applied to address longstanding and challenging issues in the biological sciences, such as specie recognition and biodiversity conservation. In this study, we present the development of a hybrid machine learning-based tool suitable for deployment on mobile devices. This tool is aimed at processing and classifying three-dimensional samples of endemic lizard species from the Amazon rainforest. The dataset used in our experiment was collected at the Museu Paraense Emílio Goeldi (MPEG), Belém-PA, Brazil, and comprises three species: (a) Anolis fuscoauratus; (b) Hoplocercus spinosus; and (c) Polychrus marmoratus. We compared the effectiveness of four artificial neural networks (ANN) for feature extraction: (a) MobileNet; (b) MobileNetV2; (c) MobileNetV3-Small; and (d) MobileNetV3-Large. Additionally, we evaluated five classical ML models for classifying the extracted patterns: (a) Support Vector Machine (SVM); (b) GaussianNB (GNB); (c) AdaBoost (ADB); (d) K-Nearest Neighbors (KNN); and (e) Random Forest (RF). The performance metrics of all classifiers were very close, we used the McNemar’s test on each model’s confusion matrix to evaluate and compare their statistical significance. Our best model was a combination of a 2.9 million parameters MobileNetV3-Small as the feature extractor, with a linear kernel-based SVM as the classifier, which achieved accuracy of 0.955, precision of 0.948, recall of 0.948, and f1-score of 0.948. The results indicated that the use of a small deep learning (DL) model, in combination with a classical ML algorithm, emerges as a viable technique for classifying three-dimensional representations of lizard species samples. Such an approach facilitates taxonomic identification work for professionals in the field and provides a tool adaptable for integration into mobile data recording equipment, such as smartphones, and benefiting from more morphological features extracted from three-dimensional samples instead of two-dimensional images.https://www.frontiersin.org/articles/10.3389/frai.2025.1524380/fullhybrid machine learning3D representationsAmazonian lizardsMobileNetspecies classification
spellingShingle Arthur Gonsales da Silva
Arthur Gonsales da Silva
Roger Pinho de Oliveira
Caio de Oliveira Bastos
Caio de Oliveira Bastos
Elena Almeida de Carvalho
Bruno Duarte Gomes
A mobile hybrid deep learning approach for classifying 3D-like representations of Amazonian lizards
Frontiers in Artificial Intelligence
hybrid machine learning
3D representations
Amazonian lizards
MobileNet
species classification
title A mobile hybrid deep learning approach for classifying 3D-like representations of Amazonian lizards
title_full A mobile hybrid deep learning approach for classifying 3D-like representations of Amazonian lizards
title_fullStr A mobile hybrid deep learning approach for classifying 3D-like representations of Amazonian lizards
title_full_unstemmed A mobile hybrid deep learning approach for classifying 3D-like representations of Amazonian lizards
title_short A mobile hybrid deep learning approach for classifying 3D-like representations of Amazonian lizards
title_sort mobile hybrid deep learning approach for classifying 3d like representations of amazonian lizards
topic hybrid machine learning
3D representations
Amazonian lizards
MobileNet
species classification
url https://www.frontiersin.org/articles/10.3389/frai.2025.1524380/full
work_keys_str_mv AT arthurgonsalesdasilva amobilehybriddeeplearningapproachforclassifying3dlikerepresentationsofamazonianlizards
AT arthurgonsalesdasilva amobilehybriddeeplearningapproachforclassifying3dlikerepresentationsofamazonianlizards
AT rogerpinhodeoliveira amobilehybriddeeplearningapproachforclassifying3dlikerepresentationsofamazonianlizards
AT caiodeoliveirabastos amobilehybriddeeplearningapproachforclassifying3dlikerepresentationsofamazonianlizards
AT caiodeoliveirabastos amobilehybriddeeplearningapproachforclassifying3dlikerepresentationsofamazonianlizards
AT elenaalmeidadecarvalho amobilehybriddeeplearningapproachforclassifying3dlikerepresentationsofamazonianlizards
AT brunoduartegomes amobilehybriddeeplearningapproachforclassifying3dlikerepresentationsofamazonianlizards
AT arthurgonsalesdasilva mobilehybriddeeplearningapproachforclassifying3dlikerepresentationsofamazonianlizards
AT arthurgonsalesdasilva mobilehybriddeeplearningapproachforclassifying3dlikerepresentationsofamazonianlizards
AT rogerpinhodeoliveira mobilehybriddeeplearningapproachforclassifying3dlikerepresentationsofamazonianlizards
AT caiodeoliveirabastos mobilehybriddeeplearningapproachforclassifying3dlikerepresentationsofamazonianlizards
AT caiodeoliveirabastos mobilehybriddeeplearningapproachforclassifying3dlikerepresentationsofamazonianlizards
AT elenaalmeidadecarvalho mobilehybriddeeplearningapproachforclassifying3dlikerepresentationsofamazonianlizards
AT brunoduartegomes mobilehybriddeeplearningapproachforclassifying3dlikerepresentationsofamazonianlizards