{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T12:29:20Z","timestamp":1777465760610,"version":"3.51.4"},"reference-count":31,"publisher":"Oxford University Press (OUP)","issue":"6","license":[{"start":{"date-parts":[[2024,3,22]],"date-time":"2024-03-22T00:00:00Z","timestamp":1711065600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/pages\/standard-publication-reuse-rights"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,11,25]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Ship-type identification in a maritime context can be critical to the authorities to control the activities being carried out. Although Automatic Identification Systems has been mandatory for certain vessels, if a vessel does not have them voluntarily or not, it can lead to a whole set of problems, which is why the use of tracking alternatives such as radar is fully complementary for a vessel monitoring systems. However, radars provide positions, but not what they are detecting. Having systems capable of adding categorical information to radar detections of vessels makes it possible to increase control of the activities being carried out, improve safety in maritime traffic, and optimize on-site inspection resources on the part of the authorities. This paper addresses the binary classification problem (fishing ships versus all other vessels) using unbalanced data from real vessel trajectories. It is performed from a deep learning approach comparing two of the main trends, Convolutional Neural Networks and Long Short-Term Memory. In this paper, it is proposed the weighted cross-entropy methodology and compared with classical data balancing strategies. Both networks show high performance when applying weighted cross-entropy compared with the classical machine learning approaches and classical balancing techniques. This work is shown to be a novel approach to the international problem of identifying fishing ships without context.<\/jats:p>","DOI":"10.1093\/jigpal\/jzae027","type":"journal-article","created":{"date-parts":[[2024,3,26]],"date-time":"2024-03-26T06:47:43Z","timestamp":1711435663000},"page":"942-954","source":"Crossref","is-referenced-by-count":4,"title":["LSTM vs CNN in real ship trajectory classification"],"prefix":"10.1093","volume":"32","author":[{"given":"Juan Pedro","family":"Llerena","sequence":"first","affiliation":[{"name":"Universidad Carlos III de Madrid GIAA Group, , Madrid 28270, , jllerena@inf.uc3m.es","place":["Spain"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jes\u00fas","family":"Garc\u00eda","sequence":"additional","affiliation":[{"name":"Universidad Carlos III de Madrid GIAA Group, , Madrid 28270, , jgherrer@inf.uc3m.es","place":["Spain"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jos\u00e9 Manuel","family":"Molina","sequence":"additional","affiliation":[{"name":"Universidad Carlos III de Madrid GIAA Group, , Madrid 28270, , molina@ia.uc3m.es","place":["Spain"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2024,3,22]]},"reference":[{"key":"2025011705415607500_ref1","article-title":"Stopping the high seas robbers: coming to grips with illegal, unreported and unregulated fisheries on the high seas","author":"Upton","year":"2003","journal-title":"Round Table on Sustainable Development OECD, Paris"},{"key":"2025011705415607500_ref2","doi-asserted-by":"crossref","first-page":"6013","DOI":"10.3390\/su12156013","article-title":"International soft laws against IUU fishing for sustainable marine resources: adoption of the voluntary guidelines for flag state performance and challenges for Taiwan","volume":"12","author":"Tai","year":"2020","journal-title":"Sustainability"},{"key":"2025011705415607500_ref3","article-title":"International fisheries relations | Fact Sheets on the European Union | European Parliament","author":"E. Commission"},{"key":"2025011705415607500_ref4","article-title":"The fight to save our oceans | FAO Stories | Food and Agriculture Organization of the United Nations","author":"Food and Agriculture Organization of the United Nations"},{"key":"2025011705415607500_ref5","first-page":"1","article-title":"Illicit trade in marine fish catch and its effects on ecosystems and people worldwide","volume-title":"Sci Adv","author":"Sumaila","year":"2020"},{"key":"2025011705415607500_ref6","first-page":"1","article-title":"Architecture for trajectory-based fishing ship classification with AIS data","volume":"20","author":"S\u00e1nchez","year":"2020","journal-title":"Sensors (Switzerland)"},{"key":"2025011705415607500_ref7","volume-title":"AIS Data","author":"Danish Maritime Authority: AIS data sets"},{"key":"2025011705415607500_ref8","doi-asserted-by":"crossref","first-page":"978","DOI":"10.1007\/978-3-319-98074-4","volume-title":"Learning from Imbalanced Data Sets","author":"Fern\u00e1ndez","year":"2018"},{"key":"2025011705415607500_ref9","first-page":"321","article-title":"SMOTE: synthetic minority over-sampling technique","volume":"16","author":"Chawla","year":"2002","journal-title":"Ecological Applications"},{"key":"2025011705415607500_ref10","first-page":"1","article-title":"Ship classification based on trajectory data with machine-learning methods","volume":"2018","author":"Kraus","year":"2018","journal-title":"Proceedings of the International Radar Symposium"},{"key":"2025011705415607500_ref11","first-page":"153","article-title":"Classification of vessel activity in streaming data","author":"Kontopoulos","journal-title":"DEBS 2020, Proceedings of the 14th ACM International Conference Distributed Event-Based Systems"},{"key":"2025011705415607500_ref12","doi-asserted-by":"crossref","first-page":"2158","DOI":"10.23919\/ICIF.2018.8455776","article-title":"Using deep learning for classifying ship trajectories","author":"Ljunggren","year":"2018","journal-title":"The 21st International Conference on Information Fusion, FUSION 2018"},{"key":"2025011705415607500_ref13","doi-asserted-by":"crossref","first-page":"4010","DOI":"10.3390\/app10114010","article-title":"Convolutional neural network-based gear type identification from automatic identification system trajectory data","volume":"10","author":"ilKim","year":"2020","journal-title":"Applied Sciences"},{"key":"2025011705415607500_ref14","doi-asserted-by":"crossref","first-page":"17351780","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short term memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Computation"},{"key":"2025011705415607500_ref15","first-page":"627","article-title":"A recurrent neural network model for detecting fishing gear patterns","volume":"15","author":"Srisukkham","year":"2021","journal-title":"ICIC Express Letters"},{"key":"2025011705415607500_ref16","first-page":"1","article-title":"Using deep learning to forecast maritime vessel flows","volume":"20","author":"Zhou","year":"2020","journal-title":"Sensors (Basel)"},{"key":"2025011705415607500_ref17","article-title":"Neural machine translation by jointly learning to align and translate","author":"Bahdanau","year":"2014","journal-title":"The 3rd International Conference on Learning Representations, ICLR 2015, Conference Track Proceedings"},{"key":"2025011705415607500_ref18","first-page":"268","article-title":"Sequence-to-sequence learning for human pose correction in videos","author":"Swetha","year":"2018","journal-title":"Proceedings of the 4th Asian Conference on Pattern Recognition, ACPR 2017"},{"key":"2025011705415607500_ref19","doi-asserted-by":"crossref","first-page":"4806","DOI":"10.1109\/ACCESS.2019.2962617","article-title":"The real-world-weight cross-entropy loss function: modeling the costs of mislabeling","volume":"8","author":"Ho","year":"2020","journal-title":"IEEE Access"},{"key":"2025011705415607500_ref20","doi-asserted-by":"crossref","first-page":"1937","DOI":"10.1007\/s11063-018-09977-1","article-title":"Learning from imbalanced data sets with weighted cross-entropy function","volume":"50","author":"Aurelio","year":"2019","journal-title":"Neural Processing Letters"},{"key":"2025011705415607500_ref21","first-page":"333","article-title":"Addressing imbalance in multi-label classification using weighted cross entropy loss function","volume":"2020","author":"Rezaei-Dastjerdehei","year":"2020","journal-title":"The 27th National and 5th International Iranian Conference on Biomedical Engineering, ICBME 2020"},{"key":"2025011705415607500_ref22","doi-asserted-by":"crossref","first-page":"230","DOI":"10.1109\/AIAM48774.2019.00053","article-title":"Dynamic weighted cross entropy for semantic segmentation with extremely imbalanced data","author":"Lu","year":"2019","journal-title":"Proceedings of the2019 International Conference on Artificial Intelligence and Advanced Manufacturing, AIAM 2019"},{"key":"2025011705415607500_ref23","doi-asserted-by":"crossref","first-page":"483","DOI":"10.1016\/j.jcp.2019.06.056","article-title":"Deep learning of dynamics and signal-noise decomposition with time-stepping constraints","volume":"396","author":"Rudy","year":"2019","journal-title":"Journal of Computational Physics"},{"key":"2025011705415607500_ref24","first-page":"1","article-title":"Forecasting nonlinear systems with LSTM: analysis and comparison with EKF","volume":"21","author":"Llerena","year":"2021","journal-title":"Sensors"},{"key":"2025011705415607500_ref25","first-page":"588","article-title":"On the dangers of cross-validation: an experimental evaluation","volume":"2","author":"Rao","year":"2008","journal-title":"Society for Industrial and Applied Mathematics - 8th SIAM International Conference on Data Mining 2008, Proceedings in Applied Mathematics, 130"},{"key":"2025011705415607500_ref26","author":"Statistics and Machine Learning Toolbox - MATLAB"},{"key":"2025011705415607500_ref27","first-page":"1","author":"Breiman","year":"2017","journal-title":"Classification and Regression Trees"},{"key":"2025011705415607500_ref28","volume-title":"Neural Network Toolbox\u2122 User\u2019s Guide R2013b","author":"Beale","year":"2013"},{"key":"2025011705415607500_ref29","doi-asserted-by":"crossref","first-page":"84","DOI":"10.1145\/3065386","article-title":"ImageNet classification with deep convolutional neural networks","volume":"60","author":"Krizhevsky","year":"2017","journal-title":"Communications of the ACM"},{"key":"2025011705415607500_ref30","article-title":"Adam: a method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"2025011705415607500_ref31","doi-asserted-by":"crossref","first-page":"106682","DOI":"10.1016\/j.petrol.2019.106682","article-title":"Time-series well performance prediction based on Long Short-Term Memory (LSTM) neural network model","volume":"186","author":"Song","year":"2019","journal-title":"Journal of Petroleum Science and Engineering"}],"container-title":["Logic Journal of the IGPL"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/jigpal\/article-pdf\/32\/6\/942\/60929232\/jzae027.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jigpal\/article-pdf\/32\/6\/942\/60929232\/jzae027.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,17]],"date-time":"2025-01-17T05:42:10Z","timestamp":1737092530000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jigpal\/article\/32\/6\/942\/7633928"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3,22]]},"references-count":31,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2024,11,25]]}},"URL":"https:\/\/doi.org\/10.1093\/jigpal\/jzae027","relation":{},"ISSN":["1367-0751","1368-9894"],"issn-type":[{"value":"1367-0751","type":"print"},{"value":"1368-9894","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2024,12]]},"published":{"date-parts":[[2024,3,22]]}}}