Identification and Counting of Pirapitinga Piaractus brachypomus Fingerlings Fish Using Machine Learning

Identifying and counting fish are crucial for managing stocking, harvesting, and marketing of farmed fish. Researchers have used convolutional networks for these tasks and explored various approaches to enhance network learning. Batch normalization is one technique that improves network stability and accuracy. This study aimed to evaluate machine learning for identifying and counting pirapitinga <i>Piaractus brachypomus</i> fry with different batch sizes. The researchers used one thousand photographic images of Pirapitinga fingerlings, labeled with bounding boxes. They trained the adapted convolutional network model with batch normalization layers added at the end of each convolution block. They set the training to one hundred and fifty epochs and tested batch sizes of 5, 10, and 20. Furthermore, they measured network performance using precision, recall, and [email protected]. Models with smaller batch sizes performed less effectively. The training with a batch size of 20 achieved the best performance, with a precision of 96.74%, recall of 95.48%, [email protected] of 97.08%, and accuracy of 98%. This indicates that larger batch sizes improve accuracy in detecting and counting pirapitinga fry across different fish densities.

Authors

Institutions

Publication Details

Journal
Animals
Published
2024-10-17
DOI
https://doi.org/10.3390/ani14202999
Citations
3
Primary Topic
Water Quality Monitoring Technologies
Type
article
Field-Weighted Citation Impact
0.60

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Identification and Counting of Pirapitinga Piaractus brachypomus Fingerlings Fish Using Machine Learning

Rafael Vilhena Reis Neto, Heyde Francielle do Carmo França, Alene Santos Souza, Joel Jorge Nuvunga et al.
3 citations
Animals
Water Quality Monitoring Technologies
0.60
article

Identification and Counting of Pirapitinga Piaractus brachypomus Fingerlings Fish Using Machine Learning

Rafael Vilhena Reis Neto, Heyde Francielle do Carmo França, Alene Santos Souza, Joel Jorge Nuvunga, Lessandro do Carmo Lima, Liege Dauny Horn, Marília Parreira Fernandes, Pedro H. O. Viadanna, Adriano Carvalho Costa, Cibele Silva Minafra, Isabel Rodrigues de Rezende, Rilke Tadeu Fonseca de Freitas, Rodrigo Fortunato de Oliveira, Brenno Muller Vitorino, Vitória de Vasconcelos Kretschmer, Débora Ázara de Oliveira, Gidélia Araújo Ferreira de Melo
article en
3 citations

Abstract

Identifying and counting fish are crucial for managing stocking, harvesting, and marketing of farmed fish. Researchers have used convolutional networks for these tasks and explored various approaches to enhance network learning. Batch normalization is one technique that improves network stability and accuracy. This study aimed to evaluate machine learning for identifying and counting pirapitinga <i>Piaractus brachypomus</i> fry with different batch sizes. The researchers used one thousand photographic images of Pirapitinga fingerlings, labeled with bounding boxes. They trained the adapted convolutional network model with batch normalization layers added at the end of each convolution block. They set the training to one hundred and fifty epochs and tested batch sizes of 5, 10, and 20. Furthermore, they measured network performance using precision, recall, and [email protected]. Models with smaller batch sizes performed less effectively. The training with a batch size of 20 achieved the best performance, with a precision of 96.74%, recall of 95.48%, [email protected] of 97.08%, and accuracy of 98%. This indicates that larger batch sizes improve accuracy in detecting and counting pirapitinga fry across different fish densities.

AnimalsVol. 14(20)
Universidade Federal de Lavras (BR), Eduardo Mondlane University (MZ), Instituto Federal Goiano (BR), Washington State University (US), Universidade Estadual Paulista (Unesp) (BR)
Coordenação de Aperfeiçoamento de Pessoal de Nível Superior, Conselho Nacional de Desenvolvimento Científico e Tecnológico, Fundação de Amparo à Pesquisa do Estado de Goiás, Instituto Federal Goiás
Openalex Percentile: Top 33%
Water Quality Monitoring Technologies
0.60
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.