{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T20:35:01Z","timestamp":1777667701447,"version":"3.51.4"},"reference-count":25,"publisher":"MDPI AG","issue":"8","license":[{"start":{"date-parts":[[2024,7,27]],"date-time":"2024-07-27T00:00:00Z","timestamp":1722038400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"University of Malta SEA-EU Blue Economy Student Research Grant"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Information"],"abstract":"<jats:p>This study addresses the challenge of accurately identifying fish species by using machine learning and image classification techniques. The primary aim is to develop an innovative algorithm that can dynamically identify the most common (within Maltese coastal waters) invasive Mediterranean fish species based on available images. In particular, these include Fistularia commersonii, Lobotes surinamensis, Pomadasys incisus, Siganus luridus, and Stephanolepis diaspros, which have been adopted as this study\u2019s target species. Through the use of machine-learning models and transfer learning, the proposed solution seeks to enable precise, on-the-spot species recognition. The methodology involved collecting and organising images as well as training the models with consistent datasets to ensure comparable results. After trying a number of models, ResNet18 was found to be the most accurate and reliable, with YOLO v8 following closely behind. While the performance of YOLO was reasonably good, it exhibited less consistency in its results. These results underline the potential of the developed algorithm to significantly aid marine biology research, including citizen science initiatives, and promote environmental management efforts through accurate fish species identification.<\/jats:p>","DOI":"10.3390\/info15080437","type":"journal-article","created":{"date-parts":[[2024,7,29]],"date-time":"2024-07-29T09:50:05Z","timestamp":1722246605000},"page":"437","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["AquaVision: AI-Powered Marine Species Identification"],"prefix":"10.3390","volume":"15","author":[{"given":"Benjamin","family":"Mifsud Scicluna","sequence":"first","affiliation":[{"name":"Oceanography Malta Research Group, Department of Geosciences, University of Malta, MSD 2080 Msida, Malta"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8635-9230","authenticated-orcid":false,"given":"Adam","family":"Gauci","sequence":"additional","affiliation":[{"name":"Oceanography Malta Research Group, Department of Geosciences, University of Malta, MSD 2080 Msida, Malta"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6919-5374","authenticated-orcid":false,"given":"Alan","family":"Deidun","sequence":"additional","affiliation":[{"name":"Oceanography Malta Research Group, Department of Geosciences, University of Malta, MSD 2080 Msida, Malta"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2024,7,27]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"e4073","DOI":"10.1002\/aqc.4073","article-title":"Automated identification of invasive rabbitfishes in underwater images from the Mediterranean Sea","volume":"34","author":"Magneville","year":"2024","journal-title":"Aquat. Conserv."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"6268","DOI":"10.1111\/gcb.16362","article-title":"Spatio-temporal dynamics of exotic fish species in the Mediterranean Sea: Over a century of invasion reconstructed","volume":"28","author":"Azzurro","year":"2022","journal-title":"Glob. Change Biol."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"411","DOI":"10.5697\/oc.56-3.411","article-title":"Recent sea surface temperature trends and future scenarios for the Mediterranean Sea","volume":"56","author":"Shaltout","year":"2014","journal-title":"Oceanologia"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"105015","DOI":"10.1016\/j.marpol.2022.105015","article-title":"On the use of deep learning for fish species recognition and quantification on board fishing vessels","volume":"139","author":"Ovalle","year":"2022","journal-title":"Mar. Policy"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"225","DOI":"10.12681\/mms.1064","article-title":"Updated review of marine alien species and other \u201cnewcomers\u201d recorded from the Maltese Islands (Central Mediterranean)","volume":"16","author":"Evans","year":"2015","journal-title":"Mediterr. Mar. Sci."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"1826","DOI":"10.1109\/18.857794","article-title":"Multiresolution image classification by hierarchical modeling with two-dimensional hidden Markov models","volume":"46","author":"Li","year":"2000","journal-title":"IEEE Trans. Inf. Theory"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"198","DOI":"10.1111\/j.1467-9388.2009.00641.x","article-title":"Preventing Transboundary Harm From Invasive Alien Species","volume":"18","author":"Riley","year":"2009","journal-title":"Rev. Eur. Community Int. Environ. Law"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"199","DOI":"10.1080\/19475721003743876","article-title":"Marine alien species as an aspect of global change","volume":"1","author":"Galil","year":"2010","journal-title":"Adv. Oceanogr. Limnol."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"314","DOI":"10.1016\/j.marpolbul.2006.11.008","article-title":"Loss or gain? Invasive aliens and biodiversity in the Mediterranean Sea","volume":"55","author":"Galil","year":"2007","journal-title":"Mar. Pollut. Bull."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"107","DOI":"10.12681\/mms.15940","article-title":"Assessing the socio-economic impacts of priority marine invasive fishes in the Mediterranean with the newly proposed SEICAT methodology","volume":"19","author":"Galanidi","year":"2018","journal-title":"Mediterr. Mar. Sci."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"977","DOI":"10.1007\/s10530-012-0344-4","article-title":"Fistularia commersonii in the Mediterranean Sea: Invasion history and distribution modelling based on presence-only records","volume":"15","author":"Azzurro","year":"2012","journal-title":"Biol. Invasions"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"S113","DOI":"10.3391\/ai.2010.5.S1.023","article-title":"New records of Lobotes surinamensis (Bloch, 1790) in Maltese coastal waters","volume":"5","author":"Deidun","year":"2010","journal-title":"Aquat. Invasions"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Pe\u0161i\u0107, A., Markovi\u0107, O., Joksimovi\u0107, A., \u0106etkovi\u0107, I., and Jevremovi\u0107, A. (2020). Invasive Marine Species in Montenegro Sea Waters. The Handbook of Environmental Chemistry, Springer.","DOI":"10.1007\/698_2020_700"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Xu, L., Bennamoun, M., An, S., Sohel, F., and Boussaid, F. (2019). Deep Learning for Marine Species Recognition. Smart Innovation, Systems and Technologies, Springer.","DOI":"10.1007\/978-3-030-11479-4_7"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"238","DOI":"10.1016\/j.ecoinf.2018.09.007","article-title":"A Deep learning method for accurate and fast identification of coral reef fishes in underwater images","volume":"48","author":"Villon","year":"2018","journal-title":"Ecol. Inform."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Catal\u00e1n, I.A., \u00c1lvarez-Ellacur\u00eda, A., Lisani, J.-L., S\u00e1nchez, J., Vizoso, G., Heinrichs-Maquil\u00f3n, A.E., Hinz, H., Al\u00f3s, J., Signarioli, M., and Aguzzi, J. (2023). Automatic detection and classification of coastal Mediterranean fish from underwater images: Good practices for robust training. Front. Mar. Sci., 10.","DOI":"10.3389\/fmars.2023.1151758"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Gauci, A., Deidun, A., and Abela, J. (2020). Automating Jellyfish Species Recognition through Faster Region-Based Convolution Neural Networks. Appl. Sci., 10.","DOI":"10.3390\/app10228257"},{"key":"ref_18","first-page":"102","article-title":"FishDeTec: A Fish Identification Application using Image Recognition Approach","volume":"12","author":"Rum","year":"2021","journal-title":"Int. J. Adv. Comput. Sci. Appl."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Barbedo, J.G.A. (2022). A Review on the Use of Computer Vision and Artificial Intelligence for Fish Recognition, Monitoring, and Management. Fishes, 7.","DOI":"10.3390\/fishes7060335"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"39","DOI":"10.22401\/ANJS.25.2.08","article-title":"Fish Species Identification Techniques: A Review","volume":"25","author":"Hassoon","year":"2022","journal-title":"Al-Nahrain J. Sci."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Ma, Y.-X., Zhang, P., and Tang, Y. (2018, January 28\u201330). Research on Fish Image Classification Based on Transfer Learning and Convolutional Neural Network Model. Proceedings of the 2018 14th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD), Huangshan, China.","DOI":"10.1109\/FSKD.2018.8686892"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"2216","DOI":"10.1111\/2041-210X.13075","article-title":"Machine learning for image based species identification","volume":"9","year":"2018","journal-title":"Methods Ecol. Evol."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Fawzi, A., Samulowitz, H., Turaga, D., and Frossard, P. (2016, January 25\u201328). Adaptive data augmentation for image classification. Proceedings of the 2016 IEEE International Conference on Image Processing (ICIP), Phoenix, AZ, USA.","DOI":"10.1109\/ICIP.2016.7533048"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Marom, N.D., Rokach, L., and Shmilovici, A. (2010, January 17\u201320). Using the confusion matrix for improving ensemble classifiers. Proceedings of the 2010 IEEE 26th Convention of Electrical and Electronics Engineers in Israel, Eilat, Israel.","DOI":"10.1109\/EEEI.2010.5662159"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"101320","DOI":"10.1016\/j.ecoinf.2021.101320","article-title":"Automatic underwater fish species classification with limited data using few-shot learning","volume":"63","author":"Villon","year":"2021","journal-title":"Ecol. Inform."}],"container-title":["Information"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2078-2489\/15\/8\/437\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T15:25:05Z","timestamp":1760109905000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2078-2489\/15\/8\/437"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,27]]},"references-count":25,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2024,8]]}},"alternative-id":["info15080437"],"URL":"https:\/\/doi.org\/10.3390\/info15080437","relation":{},"ISSN":["2078-2489"],"issn-type":[{"value":"2078-2489","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,7,27]]}}}