RESUMEN
This study investigated the antimicrobial effects of lactic acid (LA) (3%) and peracetic acid (PA) (300 ppm) on tilapia fillets (Oreochromis niloticus) by fogging (15 min) or by immersion (2 s) in a pool of Escherichia coli (NEWP 0022, ATCC 25922, and a field-isolated strain), Staphylococcus aureus (ATCC 25923 and a field-isolated strain), and Salmonella Typhimurium (ATCC 13311 and ATCC 14028), as well as the effects on the physicochemical characteristics of the fillets. Fogging was effective and the best application method to control S. Typhimurium regardless of the acid used, promoting reductions of 1.66 and 1.23 log CFU/g with PA and LA, respectively. Regarding E. coli, there were significant reductions higher than 1 log CFU/g, regardless of the treatment or acid used. For S. aureus, only immersion in PA showed no significant difference (p < 0.05). For other treatments, significant reductions of 0.98, 1.51, and 1.17 log CFU/g were observed for nebulized PA, immersion, and LA fogging, respectively. Concerning the pH of the samples, neither of the acids used differed from the control. However, treatments with LA, and fogging with PA, reduced the pH compared to immersion in PA. As for color parameters, L* and a* values showed changes regardless of the acid or method used, resulting in an improved perception of fillet quality. These results indicate that fogging and immersion are alternatives for reducing S. Typhimurium, E. coli, and S. aureus in tilapia fillets.
RESUMEN
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.