Locomotor posture and swimming-intensity quantification in starvation-stress behavior detection of individual fish

Wu, Yao; Wang, Xiaochan; Zhang, Xiaolei; Shi, Yinyan; Liu, Weimin

doi:10.1016/j.compag.2022.107399

Cited by 7 publications

(2 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…After obtaining the images, deep learning (DL) is a preferable approach for recognizing fish behavior. The merit of the DL-based model includes automatic feature extraction, and it can learn semantic information from a given image [13]. Various researchers have reported several successful neural networks in the task of fish behavior recognition.…”

Section: Introductionmentioning

confidence: 99%

Identification of Fish Hunger Degree with Deformable Attention Transformer

Wu,

Xu,

et al. 2024

JMSE

View full text Add to dashboard Cite

Feeding is a critical process in aquaculture, as it has a direct impact on the quantity and quality of fish. With advances in convolutional neural network (CNN) and vision transformer (ViT), intelligent feeding has been widely adopted in aquaculture, as the real-time monitoring of fish behavior can lead to better feeding decisions. However, existing models still have the problem of insufficient accuracy in the fish behavior-recognition task. In this study, the largemouth bass (Micropterus salmoides) was selected as the research subject, and three categories (weakly, moderately, and strongly hungry) were defined. We applied the deformable attention to the vision transformer (DeformAtt-ViT) to identify the fish hunger degree. The deformable attention module was extremely powerful in feature extraction because it improved the fixed geometric structure of the receptive fields with data-dependent sparse attention, thereby guiding the model to focus on more important regions. In the experiment, the proposed DeformAtt-ViT was compared with the state-of-the-art transformers. Among them, DeformAtt-ViT achieved optimal performance in terms of accuracy, F1-score, recall, and precision at 95.50%, 94.13%, 95.87%, and 92.45%, respectively. Moreover, a comparative evaluation between DeformAtt-ViT and CNNs was conducted, and DeformAtt-ViT still dominated the others. We further visualized the important pixels that contributed the most to the classification result, enabling the interpretability of the model. As a prerequisite for determining the feed time, the proposed DeformAtt-ViT could identify the aggregation level of the fish and then trigger the feeding machine to be turned on. Also, the feeding machine will stop working when the aggregation disappears. Conclusively, this study was of great significance, as it explored the field of intelligent feeding in aquaculture, enabling precise feeding at a proper time.

show abstract

Section: Introductionmentioning

confidence: 99%

Identification of Fish Hunger Degree with Deformable Attention Transformer

Wu,

Xu,

et al. 2024

JMSE

View full text Add to dashboard Cite

show abstract

“…Food restriction is likely to occur in all animals due to numerous factors such as population competition, unequal spatial distribution of food, seasonal variations and ecological instability [ 1 , 2 ]. Unlike other vertebrates, many fish species have demonstrated the ability to withstand short- or long-term starvation [ 3 ].…”

Section: Introductionmentioning

confidence: 99%

Effects of Starvation and Refeeding on Growth, Digestion, Nonspecific Immunity and Lipid-Metabolism-Related Genes in Onychostoma macrolepis

Gou

Wang

Jin

et al. 2023

Animals

View full text Add to dashboard Cite

The present research was conducted to assess the influences of starvation and refeeding on growth, nonspecific immunity and lipid metabolic adaptation in Onychostoma macrolepis. To date, there have been no similar reports in O. macrolepis. The fish were randomly assigned into two groups: control group (continuous feeding for six weeks) and starved–refed group (starvation for three weeks and then refeeding for three weeks). After three weeks of starvation, the results showed that the body weight (BW, 1.44 g), condition factor (CF, 1.17%), visceral index (VSI, 3.96%), hepatopancreas index (HSI, 0.93%) and intraperitoneal fat index (IPFI, 0.70%) of fish were significantly lower compared to the control group (BW, 5.72 g; CF, 1.85%; VSI, 6.35%; HSI, 2.04%; IPFI, 1.92%) (p < 0.05). After starvation, the serum triglyceride (TG, 0.83 mmol/L), total cholesterol (T-GHOL, 1.15 mmol/L), high-density lipoprotein (HDL, 1.13 mmol/L) and low-density lipoprotein (LDL, 0.46 mmol/L) concentrations were significantly lower than those in the control group (TG, 1.69 mmol/L; T-GHOL, 1.86 mmol/L; HDL, 1.62 mmol/L; LDL, 0.63 mmol/L) (p < 0.05). The activities of intestinal digestive enzymes (amylase, lipase and protease) in the starved-refed group were significantly lower than those in the control group after three weeks of starvation (p < 0.05). The highest activities of immune enzymes such as lysozyme (LZM), acid phosphate (ACP), alkaline phosphate (ALP), superoxide dismutase (SOD), glutathione peroxidase (GSH-PX) and catalase (CAT) in the hepatopancreas were presented in the starved–refed group at second week, and significantly higher than those in the control group (p < 0.05). Meanwhile, starvation significantly improved intestinal immune enzymes activities (p < 0.05). the lowest TG contents and the highest expression levels of lipolysis genes including hormone-sensitive lipase (HSL) and carnitine palmitoyl transferase 1 isoform A (CPT-1A) appeared in the hepatopancreas, muscle and intraperitoneal fat after starvation, indicating the mobilization of fat reserves in these tissues (p < 0.05). After refeeding, the recovery of TG content might be mediated by the upregulation of the expression levels of lipogenesis genes such as sterol regulatory element binding protein 1 (SREBP1) and fatty acid synthase (FAS). Understanding the duration of physiological and metabolic changes in O. macrolepis and their reversibility or irreversibility to supplementary feeding response could provide valuable reference for the adaptability of O. macrolepis in large-scale culturing, proliferation and release.

show abstract

Dynamic and explainable fish mortality prediction under low-concentration ammonia nitrogen stress

Wang

Wang³

et al. 2023

Biosystems Engineering

View full text Add to dashboard Cite

Locomotor posture and swimming-intensity quantification in starvation-stress behavior detection of individual fish

Cited by 7 publications

References 31 publications

Identification of Fish Hunger Degree with Deformable Attention Transformer

Identification of Fish Hunger Degree with Deformable Attention Transformer

Effects of Starvation and Refeeding on Growth, Digestion, Nonspecific Immunity and Lipid-Metabolism-Related Genes in Onychostoma macrolepis

Dynamic and explainable fish mortality prediction under low-concentration ammonia nitrogen stress

Contact Info

Product

Resources

About