Dataset from the Snakes (Serpentes, Reptiles) collection of the Museu Paraense Emílio Goeldi, Pará, Brazil

Prudente, Ana Lúcia da Costa; Ramos, Lorran Alves da Cruz; Silva, Timóteo Monteiro da; Sarmento, João Fabrício de Melo; Dourado, Ângelo Cortez Moreira; Silva, Fernanda Magalhães; Almeida, Paula Carolina Rodrigues de; Santos, Cleverson Ranniéri Meira dos; Sousa, Marcos Paulo Alves de

doi:10.3897/bdj.7.e34013

Cited by 4 publications

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

LizardNet: A mobile hybrid deep learning tool for classification of 3D representations of Amazonian lizards

da Silva,

de Oliveira,

de Oliveira Bastos

et al. 2024

Preprint

View full text Add to dashboard Cite

Image classification is a highly significant field in machine learning (ML), especially when applied to address longstanding and challenging issues in the biological sciences. In this study, we present the development of a hybrid deep 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 Emilio Goeldi (MPEG), Belem-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) MobileNetV3Small; and d) MobileNetV3Large. 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). Our most effective model, MobileNetV3-Small + Linear SVM, achieved an accuracy of 0.948 and a f1-score of 0.955. Notably, it not only proved to be the least complex model among all combinations but also demonstrated the best performance after a statistical comparison. These results indicate that the combination of deep learning (DL) models with less complex classical ML algorithms, which have a lower error propensity, emerges as a viable and efficient technique for classifying three-dimensional 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.

show abstract

LizardNet: A mobile hybrid deep learning tool for classification of 3D representations of Amazonian lizards

da Silva,

de Oliveira,

de Oliveira Bastos

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

Atlas of Brazilian Snakes: Verified Point-Locality Maps to Mitigate the Wallacean Shortfall in a Megadiverse Snake Fauna

Nogueira

Argôlo

Arzamendia

et al. 2019

South American Journal of Herpetology

134

206

View full text Add to dashboard Cite

The State-of-the-Art of the Humoral Memory Response to Snakebites: Insights from the Yanomami Population

Jati,

dos Anjos Martins,

Rocha

et al. 2023

Toxins

View full text Add to dashboard Cite

Snakebite envenomation (SBE)-induced immunity refers to individuals who have been previously bitten by a snake and developed a protective immune response against subsequent envenomations. The notion stems from observations of individuals, including in the indigenous population, who present only mild signs and symptoms after surviving multiple SBEs. Indeed, these observations have engendered scientific interest and prompted inquiries into the potential development of a protective immunity from exposure to snake toxins. This review explores the evidence of a protective immune response developing following SBE. Studies suggest that natural exposure to snake toxins can trigger protection from the severity of SBEs, mediated by specific antibodies. However, the evaluation of the immune memory response in SBE patients remains challenging. Further research is needed to elucidate the immune response dynamics and identify potential targets for therapeutic interventions. Furthermore, the estimation of the effect of previous exposures on SBE epidemiology in hyperendemic areas, such as in the indigenous villages of the Amazon region (e.g., the Yanomami population) is a matter of debate.

show abstract

Dataset from the Snakes (Serpentes, Reptiles) collection of the Museu Paraense Emílio Goeldi, Pará, Brazil

Cited by 4 publications

References 10 publications

LizardNet: A mobile hybrid deep learning tool for classification of 3D representations of Amazonian lizards

LizardNet: A mobile hybrid deep learning tool for classification of 3D representations of Amazonian lizards

Atlas of Brazilian Snakes: Verified Point-Locality Maps to Mitigate the Wallacean Shortfall in a Megadiverse Snake Fauna

The State-of-the-Art of the Humoral Memory Response to Snakebites: Insights from the Yanomami Population

Contact Info

Product

Resources

About