Abstract
The global aquaculture industry is experiencing a significant expansion, and it currently accounts for approximately 44% of the overall fish production worldwide. Despite encountering various obstacles in the aquaculture ecosystem, this surge in production has been achieved. In order to mitigate the negative effects of fish diseases, it is crucial to adopt scientifically proven and recommended methods for addressing health limitations. This paper aims to highlight some of the most effective techniques for identifying fish in an image using the ResNet50 model. Additionally, it intends to predict whether a fish is normal or abnormal based on its physical characteristics in aquaculture. To avoid spreading viral infections, fishermen must discard damaged or dead fish. Even for skilled fishermen, it might be challenging to spot odd fish since infected fish can be harder to identify than dead fish. As a result, it is desirable for anomalous fish to be detected automatically. Deep learning needs a lot of visual data, including both healthy and unhealthy fish, to detect abnormal fish from the image dataset. Aqua farmers are facing problems in assessing the health of the fish. Periodical observation of length is one of the parameters for assessing the health of the fish. But, farmers are failing to find the precise length of the fish. The length of the male sea bass fish is measured, and then length–weight relationship is applied for the derived length to achieve weight. Finally, we predicted whether the male sea bass fish is normal or abnormal with an accuracy of 92%.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bravata, N., Kelly, D., Eickholt, J., Bryan, J., Miehls, S., Zielinski, D.: Applications of deep convolutional neural networks to predict length, circumference, and weight from mostly dewatered images of fish. Ecol. Evol. 9313–9325 (2020)
Cheng, R., Zhang, C., Xu, Q., Liu, G., Song, Y., Yuan, X., Sun, J.: Underwater fish body length estimation based on binocular image processing. Information 11(10), 476 (2020)
Rekha, B.S., Srinivasan, G.N., Reddy, S.K., Kakwani, D., Bhattad, N.: Fish detection and classification using convolutional neural networks. In: Computational Vision and Bio-Inspired Computing: ICCVBIC 2019, pp. 1221–1231. Springer International Publishing (2020)
Ben Tamou, A., Benzinou, A., Nasreddine, K.: Live fish species classification in underwater images by using convolutional neural networks based on incremental learning with knowledge distillation loss. Mach. Learn. Knowl. Extract. 4(3), 753–767 (2022)
Bunonyo, K.W., Awomi, P.Z., Amadi, U.C.: Application of mathematical modeling to determine the growth in weight of a fish species. Central Asian J. Med. Nat. Sci. 3(3), 831–842 (2022)
Zhao, L., Montanari, F., Heberle, H., Schmidt, S.: Modeling bioconcentration factors in fish with explainable deep learning. Artif. Intell. Life Sci. 2, 100047 (2022)
Atmore, L.M., Ferrari, G., Martínez-García, L., van der Jagt, I., Blevis, R., Granado, J.: Ancient DNA sequence quality is independent of fish bone weight. J. Archaeol. Sci. 149, 105703 (2023)
Xia, C., Wang, X., Song, J., Dai, F., Zhang, Y., Yang, J., Liu, D.: Length and weight relationships of six freshwater fish species from the main channel of Yangtze River in China. Egypt. J. Aquatic Res. (2022)
Smoliński, S., Berg, F.: Varying relationships between fish length and scale size under changing environmental conditions—multidecadal perspective in Atlantic herring. Ecol. Ind. 134, 108494 (2022)
Oliveira, L.K., Wasielesky, W., Tesser, M.B.: Fish culture in biofloc technology (BFT): insights on stocking density carbon sources, C/N ratio, fish nutrition and health. Aquaculture Fisheries (2022)
Akila, M., Anbalagan, S., Lakshmisri, N.M., Janaki, V., Ramesh, T., Merlin, R.J., Kamala-Kannan, S.: Heavy metal accumulation in selected fish species from Pulicat Lake, India, and health risk assessment. Environ. Technol. Innov. 27, 102744 (2022)
Xue, Y., Bastiaansen, J.W., Khan, H.A., Komen, H.: An analytical framework to predict slaughter traits from images in fish. Aquaculture 566, 739175 (2023)
Wąsikowska, B., Linowska, A.A.: Application of the rough set theory to the analysis of food safety in fish processing. Procedia Comput. Sci. 192, 3342–3350 (2021)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Sreeja, V.S., Kumari, K.S., Reddy, D.B., Ujjwala, P. (2023). A Deep Learning-Based Prediction Model for Wellness of Male Sea Bass Fish. In: Bhateja, V., Carroll, F., Tavares, J.M.R.S., Sengar, S.S., Peer, P. (eds) Intelligent Data Engineering and Analytics. FICTA 2023. Smart Innovation, Systems and Technologies, vol 371. Springer, Singapore. https://doi.org/10.1007/978-981-99-6706-3_19
Download citation
DOI: https://doi.org/10.1007/978-981-99-6706-3_19
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-6705-6
Online ISBN: 978-981-99-6706-3
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)