{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T06:42:20Z","timestamp":1772088140259,"version":"3.50.1"},"reference-count":33,"publisher":"MDPI AG","issue":"2","license":[{"start":{"date-parts":[[2026,2,23]],"date-time":"2026-02-23T00:00:00Z","timestamp":1771804800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Zhejiang Provincial Soft Science Research Program Project","award":["2026C25007"],"award-info":[{"award-number":["2026C25007"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Systems"],"abstract":"<jats:p>Accurate perception of tugboat operational status is essential for optimising port scheduling efficiency and ensuring operational safety. However, existing AIS-based methods often struggle to capture the fine-grained and asymmetric manoeuvring characteristics of tugboats, particularly in distinguishing assisted berthing from unberthing operations. To address these limitations, this study proposes a hybrid recognition framework integrating multidimensional feature engineering with spatiotemporal dynamics. First, a speed-threshold-based sliding window algorithm segments trajectories into sailing and berthing states. Second, a 15-dimensional feature vector\u2014comprising statistical and descriptive features from speed, heading, and trajectory morphology\u2014is constructed to characterise tugboat behaviour. Notably, morpho-logical descriptors such as the \u2018Overlap Ratio\u2019 serve as implicit spatial proxies, capturing geographical constraints without reliance on Electronic Navigational Charts. A three-layer fully connected neural network (FCNN) is then developed to classify segments into \u201cCruising\u201d and \u201cAssisting in Berthing\/Unberthing.\u201d Finally, a speed-dynamics rule further distinguishes berthing from unberthing based on opposing temporal evolution patterns. Experiments on real AIS data from Ningbo\u2013Zhoushan Port demonstrate that the model achieves an F1-score of 0.90 and a recall of 0.93 for assistance-related operations. Permutation importance analysis confirms that integrating kinematic and morphological features enables interpretable and precise intent inference. This study offers a high-precision, low-dependency solution for tugboat operation identification, supporting intelligent port surveillance and sustainable maritime management.<\/jats:p>","DOI":"10.3390\/systems14020225","type":"journal-article","created":{"date-parts":[[2026,2,23]],"date-time":"2026-02-23T10:00:52Z","timestamp":1771840852000},"page":"225","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Spatiotemporal Feature-Driven Deep Learning Framework for Fine-Grained Tugboat Operation Recognition"],"prefix":"10.3390","volume":"14","author":[{"given":"Xiang","family":"Jia","sequence":"first","affiliation":[{"name":"Faculty of Maritime and Transportation, Ningbo University, Ningbo 315211, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3898-2180","authenticated-orcid":false,"given":"Hongxiang","family":"Feng","sequence":"additional","affiliation":[{"name":"Faculty of Maritime and Transportation, Ningbo University, Ningbo 315211, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4260-6732","authenticated-orcid":false,"given":"Manel","family":"Grifoll","sequence":"additional","affiliation":[{"name":"Barcelona Innovation in Transport (BIT), Department of Civil and Environmental Engineering, Universitat Polit\u00e8cnica de Catalunya\u2014BarcelonaTech, 08003 Barcelona, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qin","family":"Lin","sequence":"additional","affiliation":[{"name":"College of International Economics & Trade, Ningbo University of Finance & Economics, Ningbo 315000, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2026,2,23]]},"reference":[{"key":"ref_1","unstructured":"ITF (2015). The Impact of Mega-Ships, International Transport Forum Policy Papers."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Su, S.-F., and Wang, N. (2022). Review on the Research of Ship Automatic Berthing Control. Proceedings of the Offshore Robotics, Springer.","DOI":"10.1007\/978-981-16-2078-2"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Mentjes, J., Wiards, H., and Feuerstack, S. (2022). Berthing Assistant System Using Reference Points. J. Mar. Sci. Eng., 10.","DOI":"10.3390\/jmse10030385"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"120709","DOI":"10.1016\/j.oceaneng.2025.120709","article-title":"Study on Automatic Berthing of Large Under-Actuated Vessel with Multi-Tug Collaboration","volume":"325","author":"Chen","year":"2025","journal-title":"Ocean Eng."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Paulauskas, V., and Paulauskas, D. (2025). Ship Mooring Methodology Designed for Ship Berthing in Extremely Limited Conditions. J. Mar. Sci. Eng., 13.","DOI":"10.3390\/jmse13030575"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Park, J.-S., Nguyen, T.-N., Dinh, C.-T., Huynh, T., and Kim, Y.-B. (2025). Modeling and Control of Tugboat-Assisted Operation for Marine Vessels. J. Mar. Sci. Eng., 13.","DOI":"10.20944\/preprints202504.1026.v1"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"2521907","DOI":"10.1080\/18824889.2025.2521907","article-title":"Hierarchical Control of Multiple Tugboats with Constraint-Driven Model-Following Control","volume":"18","author":"Otsuki","year":"2025","journal-title":"SICE J. Control Meas. Syst. Integr."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Li, X., Xiao, Y., Su, F., Wu, W., and Zhou, L. (2021). AIS and VBD Data Fusion for Marine Fishing Intensity Mapping and Analysis in the Northern Part of the South China Sea. ISPRS Int. J. Geo-Inf., 10.","DOI":"10.3390\/ijgi10050277"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"103409","DOI":"10.1016\/j.trd.2022.103409","article-title":"A Bi-Objective Green Tugboat Scheduling Problem with the Tidal Port Time Windows","volume":"110","author":"Zhong","year":"2022","journal-title":"Transp. Res. Part D Transp. Environ."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"110829","DOI":"10.1016\/j.engappai.2025.110829","article-title":"Big-Data-Driven Vessel Destination Prediction for Smart Port Management","volume":"154","author":"Chen","year":"2025","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Ortega-Piris, A., Diaz-Ruiz-Navamuel, E., Martinez, A.H., Gutierrez, M.A., and Lopez-Diaz, A.-I. (2022). Analysis of the Concentration of Emissions from the Spanish Fleet of Tugboats. Atmosphere, 13.","DOI":"10.3390\/atmos13122109"},{"key":"ref_12","first-page":"1995","article-title":"Emission Characteristics of Port Tugboat Based on Working Conditions","volume":"41","author":"Tang","year":"2021","journal-title":"Zhongguo Huanjing Kexue\/China Environ. Sci."},{"key":"ref_13","first-page":"103989","article-title":"The Impacts of Pilotage Planning on Green Maritime Logistics","volume":"81","author":"Feng","year":"2025","journal-title":"Reg. Stud. Mar. Sci."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Li, B., Chen, Q., Lau, Y., and Dulebenets, M.A. (2023). Tugboat Scheduling with Multiple Berthing Bases under Uncertainty. J. Mar. Sci. Eng., 11.","DOI":"10.3390\/jmse11112180"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"102741","DOI":"10.1016\/j.jtrangeo.2020.102741","article-title":"Time Efficiency Assessment of Ship Movements in Maritime Ports: A Case Study of Two Ports Based on AIS Data","volume":"86","author":"Feng","year":"2020","journal-title":"J. Transp. Geogr."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1080\/20464177.2026.2618907","article-title":"A Constant Parameter Time-Domain Simulator for a Tugboat with Forward-Speed Dependent Hydrodynamics and Speed Control","volume":"25","author":"Chen","year":"2026","journal-title":"J. Mar. Eng. Technol."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"498","DOI":"10.1177\/0361198120916734","article-title":"Analysis of Tugboat Activities Using AIS Data for the Tianjin Port","volume":"2674","author":"Chen","year":"2020","journal-title":"Transp. Res. Rec."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Wu, L., Xu, Y., and Wang, F. (2020). Identifying Port Calls of Ships by Uncertain Reasoning with Trajectory Data. ISPRS Int. J. Geo-Inf., 9.","DOI":"10.3390\/ijgi9120756"},{"key":"ref_19","first-page":"104579","article-title":"Inland Vessel Behavior Identification and Trajectory Reconstruction Based on Multi-Feature Fusion","volume":"92","author":"Liu","year":"2025","journal-title":"Reg. Stud. Mar. Sci."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"118677","DOI":"10.1016\/j.oceaneng.2024.118677","article-title":"A Novel Vessel Trajectory Feature Engineering for Fishing Vessel Behavior Identification","volume":"310","author":"Yang","year":"2024","journal-title":"Ocean Eng."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"114787","DOI":"10.1016\/j.jenvman.2022.114787","article-title":"COVID-19 Impact on Maritime Traffic and Corresponding Pollutant Emissions. The Case of the Port of Barcelona","volume":"310","author":"Guarasa","year":"2022","journal-title":"J. Environ. Manag."},{"key":"ref_22","first-page":"132","article-title":"Scheduling Optimization of Port Tugboat Operation Considering Multi-Anchorage","volume":"48","author":"Xu","year":"2014","journal-title":"Shanghai Jiaotong Daxue Xuebao\/J. Shanghai Jiaotong Univ."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"102075","DOI":"10.1016\/j.apor.2020.102075","article-title":"Numerical Analysis of Escort Tug Manoeuvrability Characteristics","volume":"97","author":"Piaggio","year":"2020","journal-title":"Appl. Ocean Res."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"119737","DOI":"10.1016\/j.oceaneng.2024.119737","article-title":"FDBR: Ultra-Fast and Data-Efficient Behavior Recognition of Port Vessels Using a Statistical Framework","volume":"315","author":"Qiang","year":"2025","journal-title":"Ocean Eng."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"110105","DOI":"10.1016\/j.ress.2024.110105","article-title":"A Framework for Ship Abnormal Behaviour Detection and Classification Using AIS Data","volume":"247","author":"Rong","year":"2024","journal-title":"Reliab. Eng. Syst. Saf."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"111185","DOI":"10.1016\/j.engappai.2025.111185","article-title":"Anomaly Detection in Ship Trajectories Using Machine Learning and Dynamic Time Warping","volume":"157","author":"Tourneret","year":"2025","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_27","first-page":"104493","article-title":"HAMSCNN: A Hybrid Attention Multi-Scale CNN for Accurate Ship Detection in Maritime Surveillance","volume":"91","author":"Mehta","year":"2025","journal-title":"Reg. Stud. Mar. Sci."},{"key":"ref_28","first-page":"104332","article-title":"Incorporating Knowledge Graph and Multi-Model Stacking Ensemble Learning for Prediction of Fines for Illegal Fishing","volume":"89","author":"Yu","year":"2025","journal-title":"Reg. Stud. Mar. Sci."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"1571","DOI":"10.1109\/TKDE.2025.3531770","article-title":"AISFuser: Encoding Maritime Graphical Representations With Temporal Attribute Modeling for Vessel Trajectory Prediction","volume":"37","author":"Zhang","year":"2025","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"542","DOI":"10.1038\/s41597-024-03391-0","article-title":"Maritime Freight Carbon Emission in the U.S. Using AIS Data from 2018 to 2022","volume":"11","author":"Cheng","year":"2024","journal-title":"Sci. Data"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"111852","DOI":"10.1016\/j.oceaneng.2022.111852","article-title":"Loitering Behavior Detection and Classification of Vessel Movements Based on Trajectory Shape and Convolutional Neural Networks","volume":"258","author":"Zhang","year":"2022","journal-title":"Ocean Eng."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"108061","DOI":"10.1016\/j.ress.2021.108061","article-title":"Maritime Traffic Probabilistic Prediction Based on Ship Motion Pattern Extraction","volume":"217","author":"Rong","year":"2022","journal-title":"Reliab. Eng. Syst. Saf."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1007\/s00773-014-0293-y","article-title":"Introduction of MMG Standard Method for Ship Maneuvering Predictions","volume":"20","author":"Yasukawa","year":"2015","journal-title":"J. Mar. Sci. Technol."}],"container-title":["Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2079-8954\/14\/2\/225\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T05:38:08Z","timestamp":1772084288000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2079-8954\/14\/2\/225"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,23]]},"references-count":33,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2026,2]]}},"alternative-id":["systems14020225"],"URL":"https:\/\/doi.org\/10.3390\/systems14020225","relation":{},"ISSN":["2079-8954"],"issn-type":[{"value":"2079-8954","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,23]]}}}