Automated detection of aquatic animals using deep learning techniques
Main Article Content
Abstract
Deep learning-based approaches have arisen as promising devices for mechanizing the recognition and characterization of oceanic creatures, offering critical progressions in marine biology, fisheries the board, and natural checking. This paper gives a far-reaching survey of the difficulties and potential open doors related with executing profound learning techniques in sea-going science. Picture grouping undertakings have seen an ascent with the presentation of profound learning strategies. In this paper, we have proposed a crossover Deep learning system that is utilized for highlight extraction and profound learning strategy for characterization. Both the proposed structures are tried on various dataset. Our trial results show that our system gives improved results than the majority of the customary as well as existing profound learning procedures. The vital advances of DL calculations applied to the visual acknowledgment and location of oceanic creatures are summed up, including datasets, calculations and execution. Besides, the difficulties are summarized and characterized in the item acknowledgment and identification space for oceanic creatures.
Article Details
Section
How to Cite
References
Assegid, W. and Ketema, G., 2023. Assessing the effects of climate change on aquatic ecosystems. Aquatic Ecosystems and Environmental Frontiers, 1(1), pp. 6-10.
Bohara, K., Joshi, P., Acharya, K.P. and Ramena, G., 2024. Emerging technologies revolutionising disease diagnosis and monitoring in aquatic animal health. Reviews in Aquaculture, 16(2), pp. 836-854. [https://doi.org/10.1111/raq.12870](https://doi.org/10.1111/raq.12870)
Chen, Z., Du, M., Yang, X.D., Chen, W., Li, Y.S., Qian, C. and Yu, H.Q., 2023. Deep-learning-based automated tracking and counting of living plankton in natural aquatic environments. Environmental Science & Technology, 57(46), pp. 18048-18057. [https://doi.org/10.1021/acs.est.3c00253](https://doi.org/10.1021/acs.est.3c00253)
Dixon, D.A. (Ed.), 2003. Biology, Management, and Protection of Catadromous Eels: Proceedings of the First International Symposium on Biology, Management, and Protection of Catadromous Eels: Held at St. Louis, Missouri, USA: 21-22 August 2000 (Vol. 33). American Fisheries Society.
Hou, Z., Makarov, Y.V., Samaan, N.A. and Etingov, P.V., 2013. Standardized software for wind load forecast error predictions analyses based on Wavelet-ARIMA models—Applications at multiple geographically distributed wind farms. In 2013 46th Hawaii International Conference on System Sciences (pp. 5005-5011). IEEE.
Kandimalla, V., Richard, M., Smith, F., Quirion, J., Torgo, L. and Whidden, C., 2022. Automated detection, classification and counting of fish in fish passages with deep learning. Frontiers in Marine Science, 8, p. 823173. [https://doi.org/10.3389/fmars.2021.823173](https://doi.org/10.3389/fmars.2021.823173)
Li, D. and Du, L., 2022. Recent advances of deep learning algorithms for aquacultural machine vision systems with emphasis on fish. Artificial Intelligence Review, 55(5), pp. 4077-4116. [https://doi.org/10.1007/s10462-021-10102-3](https://doi.org/10.1007/s10462-021-10102-3)
Ozturk, T., Talo, M., Yildirim, E.A., Baloglu, U.B., Yildirim, O. and Acharya, U.R., 2020. Automated detection of COVID-19 cases using deep neural networks with X-ray images. Computers in Biology and Medicine, 121, p. 103792.
Yassir, A., Andaloussi, S.J., Ouchetto, O., Mamza, K. and Serghini, M., 2023. Acoustic fish species identification using deep learning and machine learning algorithms: A systematic review. Fisheries Research, 266, p. 106790. [https://doi.org/10.1016/j.fishres.2023.106790](https://doi.org/10.1016/j.fishres.2023.106790)