40 SEPTEMBER • WORLD AQUACULTURE • WWW.WAS.ORG biology, which might result in catastrophe. Relying on AI models to predict and analyze data for us may reduce human intervention and handling stress in aquaculture, but there is no assurance that it can last forever, the machines need constant care, and the models need to be updated frequently. The constantly evolving and learning neural networks with optimizers such as Adam pose a threat as the model can perform badly in some unseen data, for instance, a model trained on zebrafish can only detect zebrafish. Even if there are plants and aerators, unless trained the model is going to assume everything is a zebrafish. Replacing humans with AI might be on the horizon, but as Fei-Fei said, as much as AI is showing how machines can think, it is also showing us how complex and amazing is the human brain that created such AI. Notes Madhav Karthikeyan,* Department of Biology, University of Crete, Heraklion, Greece 700 13. * Corresponding author: bio2p149@edu.biology.uoc.gr References Bishop, C.M., 1994. Neural networks and their applications. Review of scientific instruments, 65(6), pp.1803-1832. https://doi. org/10.1063/1.1144830 Fan, Y.L., Hsu, F.R., Wang, Y. and Liao, L.D., 2023. Unlocking the potential of zebrafish research with artificial intelligence: Advancements in tracking, processing, and visualization. Medical & Biological Engineering & Computing, 61(11), pp.2797-2814. doi: https://doi.org/10.1007/s11517-023-02903-1 Foley, J.A., Ramankutty, N., Brauman, K.A., Cassidy, E.S., Gerber, J.S., Johnston, M., Mueller, N.D., O’Connell, C., Ray, D.K., West, P.C. and Balzer, C., 2011. Solutions for a cultivated planet. Nature, 478(7369), pp.337-342. doi: https://doi.org/10.1038/nature10452 Lepetit, V., Moreno-Noguer, F. and Fua, P., 2009. EPnP: An accurate O(n) solution to the PnP problem. International Journal of Computer Vision, 81(2), pp.155-166. doi: https://doi.org/10.1007/ s11263-008-0152-6 Li, H., Liu, Y., Chen, Q., Jin, L. and Peng, R., 2023. Research progress of zebrafish model in aquatic ecotoxicology. Water, 15(9), p.1735. doi: https://doi.org/10.3390/w15091735 Liakos, K.G., Busato, P., Moshou, D., Pearson, S. and Bochtis, D., 2018. Machine learning in agriculture: A review. Sensors, 18(8), p.2674. doi: https://doi.org/10.3390/s18082674 Marr, B.,2021. Understanding the 4 Types of Artificial Intelligence. [online] Bernard Marr. Available at: https://bernardmarr.com/ understanding-the-4-types-of-artificial-intelligence Martínez-Vázquez, J M., D G. Valcarce, M F. Riesco, V. S. Marco, M.Matsuoka, and V. Robles. 2019. “Artificial Neural Network (ANN) as a Tool to Reduce Human-Animal Interaction Improves Senegalese Sole Production.” Biomolecules 9, no. 12: 778. doi: https://doi.org/10.3390/biom9120778 Nguyen, Thanh Khoa, Madeline Petrikas, Brooke E. Chambers, and Rebecca A. Wingert. “Principles of zebrafish nephron segment development.” Journal of Developmental Biology 11, no. 1 (2023): 14. doi: https://doi.org/10.3390/jdb11010014 Redmon, J., Divvala, S., Girshick, R. and Farhadi, A., 2016. You only look once: Unified, real-time object detection in Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 779-788). Available at: https:// www.cv-foundation.org/openaccess/content_cvpr_2016/html/ Redmon_You_Only_Look_CVPR_2016_paper.html?ref=https:// githubhelp.com Rejeb, A., Simske, S., Rejeb, K., Treiblmaier, H. and Zailani, S., 2022. The big picture of industry 4.0 in the food sector: A review. Future Internet, 14(4), p.99. doi: https://doi.org/10.3390/ su141912437 Russell, S. and Norvig, P., 2021. Artificial intelligence: A modern approach. 4th ed. Pearson. Available at: https://thuvienso.hoasen. edu.vn/handle/123456789/8967 Shamshiri, R.R., Weltzien, C., Hameed, I.A., Yule, I.J., Grift, T.E., Balasundram, S.K., Pitonakova, L., Ahmad, D. and Chowdhary, G., 2018. Research and development in agricultural robotics: A perspective of digital farming. International Journal of Agricultural and Biological Engineering, 11(4), pp.1-11. doi: https://doi.org/10.25165/j.ijabe.20181104.4278 Siki, Z. and Takács, B., 2021. Automatic Recognition of ArUco Codes in Land Surveying Tasks. Baltic Journal of Modern Computing, 9(1). doi: https://doi.org/10.22364/bjmc.2021.9.1.06 United Nations. Department of Economic and Social Affairs. Population Division (2019). World population prospects: Highlights, 2019 revision. New York: United Nations. Available at: https://www.un.org/es/desa/world-population-prospects-2019highlights Wang, R., Guo, H., Wang, X. and Han, L., 2023, November. The Effect of ArUco Marker Size, Number, and Distribution on the Localization Performance of Fixed-Point Targets. In 2023 6th International Conference on Robotics, Control and Automation Engineering (RCAE) (pp. 118-123). IEEE. doi: https://doi. org/10.1109/RCAE59706.2023.10398770. Zhang, Y., Wang, J. and Wang, J., 2020. Precision agriculture—a worldwide overview. Sensors, 20(10), p.2796. doi: https://doi. org/10.1016/S0168-1699(02)00096-0 Zhang, Z., 2000. A flexible new technique for camera calibration. IEEE Transactions on Pattern Analysis and Machine Intelligence, 22(11), pp.1330-1334. doi: https://doi. org/10.1109/34.888718. Future work should focus on refining length measurement accuracy and expanding the dataset for more robust results. Testing in diverse environments and integrating real-time monitoring will further enhance its utility in zebrafish research. The accuracy of the model and speed of analysis contradict each other; we can either sacrifice accuracy by a small margin for rapid detection or vice versa. Yet, implementing the latest models, which have lower parameters, can give an improved accuracy even under rapid detection.
RkJQdWJsaXNoZXIy MjExNDY=