Similarity between Piaractus mesopotamicus, Colossoma macropomum and their interspecific hybrids

Costa, Alan Carlos; Serafini, Moacyr Antônio; Neto, Rafael Vilhena Reis; Santos, Priscilla Freitas; Marques, Letícia Ribeiro; Rezende, Isabel Rodrigues de; Mendonça, Maria Andréia Corrěa; Allaman, Ivan Bezerra; Freitas, Rilke Tadeu Fonseca de

doi:10.1016/j.aquaculture.2020.735397

Cited by 6 publications

(3 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, research studies that analyze normalization and batch size in the detection of commercial ngerling species are relevant. Fingerlings of the Serrasalmidae family, which includes farmed South American native sh species such as pacu, tambaqui, and pirapitinga, as well as their respective hybrids, are of economic importance in Latin America (Costa et al, 2017(Costa et al, , 2018(Costa et al, and 2020Ribeiro et al, 2019). Thus, the objective was to evaluate the batch normalization technique in the counting of pirapitinga Piaractus brachypomus ngerling sh using digital photographic images.…”

Section: Introductionmentioning

confidence: 99%

Identification and counting of pirapitinga Piaractus brachypomus fingerlings fish using Machine learning with batch normalization

Souza,

Costa,

França

et al. 2024

Preprint

Self Cite

View full text Add to dashboard Cite

The identification and counting of fish are relevant tools used for stocking, harvesting, and marketing management of farmed fish. The use of convolutional networks has been used for such purposes, and different approaches have been employed to improve network learning. Batch normalization is one of the techniques that aids in the enhancement and stability of the network, providing greater accuracy. Thus, the objective was to evaluate machine learning in the identification and counting of pirapitinga Piaractus brachypomus fingerlings fish with and without batch normalization. One thousand photographic images of pirapitinga fingerlings were used, labeled through bounding boxes. The training of the adapted convolutional network model was performed, with batch normalization layers inserted at the end of each convolution block. One hundred fifty epochs were established, and batch sizes for normalization were set to 1, 5, 10, and 20. The database training was also conducted without applying normalization for comparison. The evaluation metrics for network performance were precision, recall, and mAP@0.5. The results obtained with the model without the application of the technique were inferior to the models in which batch normalization was applied. The batch size equal to 20 was the model trained with the best performance, showing precision of 96.74%, recall of 95.48%, mAP@0.5 of 97.08%, and accuracy of 98%. It is concluded that batch normalization increases accuracy in the detection and counting of pirapitinga fingerlings in different densities of fish

show abstract

Section: Introductionmentioning

confidence: 99%

Identification and counting of pirapitinga Piaractus brachypomus fingerlings fish using Machine learning with batch normalization

Souza,

Costa,

França

et al. 2024

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…This species has physiological characteristics that allow it to increase production, including rapid growth, a propensity to accept exogenous food and tolerance to low levels of dissolved oxygen (Moraes et al, 2017). Furthermore, tambaqui demonstrates resistance to pathogens (Mourad et al, 2018), meat with nutritional and sensory properties that attract consumers (Costa et al, 2020), as well as significant cultural and economic importance (Guimarães & Martins, 2015).…”

Section: Introductionmentioning

confidence: 99%

Production of Tambaqui (Colossoma macropomum) in Brazil between 2017 to 2021

Araújo,

Mota,

Pires

et al. 2024

Braz. J. Anim. Environ. Res.

View full text Add to dashboard Cite

This article sought to evaluate the production of tambaqui in Brazil from 2017 to 2021. For the constitution of the work, secondary aquaculture data collected by the Brazilian Institute of Geography and Statistics, from 2017 to 2021, were used, considering the production by region, states, and municipalities. Data analysis was based on descriptive statistics. In this context, the North region was the largest producer of tambaqui, followed by the Northeast and Midwest, emphasizing the states of Rondônia, Maranhão, and Roraima. Despite standing out in the production of tambaqui, the North had a drop in the production of the species. Regarding municipalities, the highlight was Ariquemes, followed by Almas and Amajari. Although the species presents excellent zootechnical characteristics, which favor its production and commercialization, it is necessary to invest in public policies that help producers intensify production.

show abstract

“…Studies evaluating the effectiveness of CNNs in counting different quantities of fry are still scarce in the scientific literature, especially for round fish (Serrasalmidae; Characiformes), despite the importance of these species for aquaculture in Latin America [19,20]. Among the Serrasalmidae species, those of economic importance are pacu, pirapitinga, tambaqui, and their respective hybrids due to the nutritional and sensory characteristics of their meat, which appeal to consumers [21,22]. In view of the above, the aim of this research is to evaluate the effectiveness of counting different quantities of Serrasalmidae fry by means of images using CNNs.…”

Section: Introductionmentioning

confidence: 99%

Convolutional Neural Networks in the Inspection of Serrasalmids (Characiformes) Fingerlings

Fernandes,

Costa,

França

et al. 2024

Animals

Self Cite

View full text Add to dashboard Cite

Aquaculture produces more than 122 million tons of fish globally. Among the several economically important species are the Serrasalmidae, which are valued for their nutritional and sensory characteristics. To meet the growing demand, there is a need for automation and accuracy of processes, at a lower cost. Convolutional neural networks (CNNs) are a viable alternative for automation, reducing human intervention, work time, errors, and production costs. Therefore, the objective of this work is to evaluate the efficacy of convolutional neural networks (CNNs) in counting round fish fingerlings (Serrasalmidae) at different densities using 390 color photographs in an illuminated environment. The photographs were submitted to two convolutional neural networks for object detection: one model was adapted from a pre-trained CNN and the other was an online platform based on AutoML. The metrics used for performance evaluation were precision (P), recall (R), accuracy (A), and F1-Score. In conclusion, convolutional neural networks (CNNs) are effective tools for detecting and counting fish. The pre-trained CNN demonstrated outstanding performance in identifying fish fingerlings, achieving accuracy, precision, and recall rates of 99% or higher, regardless of fish density. On the other hand, the AutoML exhibited reduced accuracy and recall rates as the number of fish increased.

show abstract

Similarity between Piaractus mesopotamicus, Colossoma macropomum and their interspecific hybrids

Cited by 6 publications

References 6 publications

Identification and counting of pirapitinga Piaractus brachypomus fingerlings fish using Machine learning with batch normalization

Identification and counting of pirapitinga Piaractus brachypomus fingerlings fish using Machine learning with batch normalization

Production of Tambaqui (Colossoma macropomum) in Brazil between 2017 to 2021

Convolutional Neural Networks in the Inspection of Serrasalmids (Characiformes) Fingerlings

Contact Info

Product

Resources

About