隨著國內海域遊憩風氣日漸盛行，親海、近海及用海行為已成為全民休閒與觀光發展的重要活動型態。然而，面對瞬息萬變的海洋環境與高密度的遊憩行為，傳統以人力巡守為主的管理模式已難以全面因應各項潛在風險。因此，為解決海域遊憩區域遊客數量持續增長所帶來的管理挑戰，本研究提出一個以人工智慧技術為核心的海域遊憩安全維護系統框架―智慧海灘(Smart Beach)。
在該框架下，本研究首先將機器學習方法應用於海岸災害預測上，透過分析實際監測的海氣象資料來建立預測模型，並藉由多組實驗探討此類機器學習模型的特性。研究結果顯示模型表現優異，即便在海岸瘋狗浪發生機制尚未完全明確的情況下，仍能產出高準確性的預報結果，為海岸災害預警機制提供有效支持。
其次，本研究應用深度學習方法在海域動態目標辨識上，提出一套建立海域遊憩動態目標辨識模型的框架與原則，並透過真實場域數據與多項實驗結果驗證其有效性。研究結果顯示模型能有效辨識超過十種類別的海域遊憩活動與溺水姿態，尤其在關鍵的溺水事件偵測中，能準確區分正常活動與溺水事件，展現極低的誤報率。研究結果同時也強調了影像擴增、模型架構與超參數率定對提升模型訓練成效的重要性。
此外，本研究進一步引入了先進的訓練方法與最佳化策略，包含較新式的深度學習方法、訓練超參數率定方法，以及基於生成式人工智慧(Generative AI)的影像擴增技術。結果顯示，較新一代的模型通常較容易獲得優異的辨識準確性與訓練穩定性；然而，較早期的模型在經過適當的訓練配置最佳化後，仍可達到與新模型相近的辨識表現。未來可進一步利用生成式人工智慧技術直接生成海洋動態目標特徵，以擴增溺水事件及其他較難蒐集之影像資料，進而提升模型在海域動態目標辨識的泛化能力。
最後，本研究進一步將核心成果延伸至不同實務應用中，包含整合多目標追蹤演算法以即時掌握海域遊憩民眾動向，特別針對越界或溺水個體進行追蹤；運用海域動態目標辨識模型於海岸災害潛在發生區域的即時警示；將相同的深度學習模型框架延伸應用於海洋垃圾的偵測與分類任務。
綜以上所述，上述人工智慧技術的成功應用與優異成效，充分證實了將此類技術導入海域遊憩安全預警與監控的可行性與潛力，期能為未來的海域安全智慧化管理提供重要參考與實質幫助。

To address escalating public safety threats and the operational challenges of managing crowds in marine recreational areas, this study proposes Smart Beach, an advanced AI-integrated framework for marine recreational safety.
Within the framework of the Smart Beach, this research first applies machine learning to predict Coastal Freak Waves using observational data and subsequently discuss the model's characteristic through various experiments. Remarkably, even with complex and unresolved physical mechanisms, the models deliver highly reliable predictive performance, providing robust support for early warning systems.
Subsequently, this research discusses comprehensive deep learning methodologies developed to recognize marine dynamic targets, optimizing the identification of over ten categories of recreational activities and drowning postures. The model demonstrates excellent performance in detecting drowning individuals, while effectively preventing false alarms from normal ongoing activities. Real-world validation further confirmed its robustness, emphasizing that data augmentation, model structure, and hyperparameter tuning during training are all crucial.
Furthermore, this study integrates advanced training and optimization strategies, including newer deep learning architectures, novel hyperparameter tuning methods, and Generative AI-based data augmentation. The results show that new models generally achieve great accuracy and training stability easily. The old models, although they can attain comparable performance, can only do so through an optimal training configuration. Future work may leverage Generative AI to generate marine dynamic target features, augmenting datasets of drowning events and other rare marine datasets.
The findings of this study were extended to various field applications, including integrating Multiple Target Tracking algorithm for individuals tracking, utilizing the deep learning model to capture the occurrence of coastal hazards, and marine debris classification model for rapid environmental pollution assessment. In conclusion, the successful deployment and remarkable performance of these integrated AI technologies for marine recreational safety early warning and surveillance, highlighting their substantial potential to transform contemporary marine safety management.

[1] Afzal, M. S., Kumar, L., Chugh, V., Kumar, Y., & Zuhair, M., 2023. Prediction of significant wave height using machine learning and its application to extreme wave analysis. J. Earth Syst. Sci., 132, 51. https://doi.org/10.1007/s12040-023-02058-5
[2] Ajgaonkar, K., Khanolkar, S., Rodrigues, J., Shilker, E., Borkar, P., & Braz, E., 2020. Development of a lifeguard assist drone for coastal search and rescue. In Global Oceans 2020: Singapore–US Gulf Coast, pp. 1-10. IEEE. https://doi.org/10.1109/IEEECONF38699.2020.9389382
[3] Al Najar, M., Wilson, D. G., & Almar, R., 2026. Interpretable machine learning for shoreline forecasting. Sci. Rep., 16, 11457. https://doi.org/10.1038/s41598-026-37403-3
[4] Ankiewicz, A., Bokaeeyan, M., & Akhmediev, N., 2019. Shallow-water rogue waves: An approach based on complex solutions of the Korteweg–de Vries equation. Phys. Rev. E, 99, 050201. https://doi.org/10.1103/PhysRevE.99.050201
[5] Australia, S. L. S., 2025. National coastal safety report 2024. Sydney: Surf Life Saving Australia.
[6] Barbelian, M. A., Dinu, C., & Peitreanu, C. V., 2021. Deep learning approach on shark attack risk assessment using real-time autonomous surveillance systems. U.P.B. Sci. Bull., 83(4).
[7] Bewley, A., Ge, Z., Ott, L., Ramos, F., & Upcroft, B., 2016. Simple online and realtime tracking. In 2016 IEEE International Conference on Image Processing (ICIP), pp. 3464-3468. IEEE.
[8] Bhavya Sree, B., Yashwanth Bharadwaj, V., & Neelima, N., 2021. An Inter-Comparative Survey on State-of-the-Art Detectors—R-CNN, YOLO, and SSD. In Intelligent Manufacturing and Energy Sustainability: Proceedings of ICIMES 2020, pp. 475-483. Springer Singapore. https://doi.org/10.1007/978-981-33-4443-3_46
[9] Bishop, C. M. (1995). Neural networks for pattern recognition. Oxford university press. https://doi.org/10.1093/oso/9780198538493.001.0001
[10] Bochkovskiy, A., Wang, C. Y., & Liao, H. Y. M., 2020. Yolov4: Optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934. https://doi.org/10.48550/arXiv.2004.10934
[11] Breiman, L., 2001. Random Forests. Mach. Learn., 45, 5–32. https://doi.org/10.1023/A:1010933404324
[12] Breiman, L., 1984. Classification and Regression Trees. New York, Routledge. https://doi.org/10.1201/9781315139470
[13] Callens, A., Morichon, D., Abadie, S., Delpey, M., & Liquet, B., 2020. Using Random forest and Gradient boosting trees to improve wave forecast at a specific location. Appl. Ocean Res., 104, 102339. https://doi.org/10.1016/j.apor.2020.102339
[14] Cavaleri, L., Bertotti, L., Torrisi, L., Bitner-Gregersen, E., Serio, M., & Onorato, M., 2012. Rogue waves in crossing seas: The Louis Majesty accident. J. Geophys. Res. Oceans, 117, C00J10. https://doi.org/10.1029/2012JC007923
[15] Chang, Y. L., Anagaw, A., Chang, L., Wang, Y. C., Hsiao, C. Y., & Lee, W. H., 2019. Ship detection based on YOLOv2 for SAR imagery. Remote Sens., 11(7), 786. https://doi.org/10.3390/rs11070786
[16] Chang, M., Xing, Y. Y., Zhang, Q. Y., Han, S. J., & Kim, M., 2020. A CNN image classification analysis for ‘clean-coast detector’ as tourism service distribution. J. Distrib. Sci., 18(1), 15-26. https://doi.org/10.15722/jds.18.01.20201.15
[17] Chen, S. T., 2019. Probabilistic forecasting of coastal wave height during typhoon warning period using machine learning methods. J. Hydroinform., 21, 343–358. https://doi.org/10.2166/hydro.2019.115
[18] Chien, H. W. A., Kao, C. C., & Chuang, L. Z., 2002. On the characteristics of observed coastal freak waves. Coast. Eng. J., 44, 301–319. https://doi.org/10.1142/S0578563402000561
[19] Claesson, A., Svensson, L., Nordberg, P., Ringh, M., Rosenqvist, M., Djarv, T., & Hollenberg, J., 2017. Drones may be used to save lives in out of hospital cardiac arrest due to drowning. Resuscitation, 114, 152-156. https://doi.org/10.1016/j.resuscitation.2017.01.003
[20] Cortes, C., & Vapnik, V., 1995. Support-vector networks. Mach. Learn., 20, 273–297. https://doi.org/10.1023/A:1022627411411
[21] De Laurentiis, L., Jones, C. E., Holt, B., Schiavon, G., & Del Frate, F., 2021. Deep Learning for Mineral and Biogenic Oil Slick Classification With Airborne Synthetic Aperture Radar Data. IEEE Trans. Geosci. Remote Sens., 59(10), 8455-8469. https://doi.org/10.1109/TGRS.2020.3034722
[22] Didenkulova, I., & Rodin, A., 2012. Statistics of shallow water rogue waves in Baltic Sea conditions: The case of Tallinn Bay. In Proceedings of the 2012 IEEE/OES Baltic International Symposium (BALTIC), pp. 1–6. https://doi.org/10.1109/BALTIC.2012.6249221
[23] Didenkulova, E., Didenkulova, I., & Medvedev, I., 2023. Freak wave events in 2005–2021: Statistics and analysis of favourable wave and wind conditions. Nat. Hazards Earth Syst. Sci., 23, 1653–1663. https://doi.org/10.5194/nhess-23-1653-2023
[24] Dietterich, T. G., 1998. Approximate statistical tests for comparing supervised classification learning algorithms. Neural Comput., 10, 1895–1923.
[25] Divinsky, B. V., Levin, B. V., Lopatukhin, L. I., Pelinovsky, E. N., & Slyunyaev, A. V., 2004. A freak wave in the Black Sea: Observations and simulation. Dokl. Earth Sci., 395, 438–443.
[26] Doong, D. J., Peng, J. P., & Chen, Y. C., 2018. Development of a warning model for coastal freak wave occurrences using an artificial neural network. Ocean Eng., 169, 270–280. https://doi.org/10.1016/j.oceaneng.2018.09.029
[27] Doong, D. J., Chen, S. T., Chen, Y. C., & Tsai, C. H., 2020. Operational probabilistic forecasting of coastal freak waves by using an artificial neural network. J. Mar. Sci. Eng., 8(3), 165. https://doi.org/10.3390/jmse8030165
[28] Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., & Houlsby, N., 2020. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929.
[29] Dusek, G., Churma, M., Im, J., Etienne, R., Pang, A., de Silva, A., & Mori, I., 2020. From Lifeguards to AI: Advancing Rip Current Forecasting Through New Detection Methods. Ocean Sciences Meeting, Computer Vision and Pattern Recognition.
[30] Everingham, M., Van Gool, L., Williams, C. K., Winn, J., & Zisserman, A., 2010. The pascal visual object classes (voc) challenge. Int. J. Comput. Vis., 88, 303-338. https://doi.org/10.1007/s11263-009-0275-4
[31] Fallati, L., Polidori, A., Salvatore, C., Saponari, L., Savini, A., & Galli, P., 2019. Anthropogenic Marine Debris assessment with Unmanned Aerial Vehicle imagery and deep learning: A case study along the beaches of the Republic of Maldives. Sci. Total Environ., 693, 133581. https://doi.org/10.1016/j.scitotenv.2019.133581
[32] Girshick, R., Donahue, J., Darrell, T., & Malik, J., 2014. Rich feature hierarchies for accurate object detection and semantic segmentation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 580-587.
[33] Girshick, R., 2015. Fast r-cnn. In Proceedings of the IEEE International Conference on Computer Vision, pp. 1440-1448.
[34] Goldberg, D. E. (1989). Genetic Algorithms in Search, Optimization, and Machine Learning. Addison-Wesley Publishing Company.
[35] Gonçalves, G., Andriolo, U., Pinto, L., & Bessa, F., 2020. Mapping marine litter using UAS on a beach-dune system: a multidisciplinary approach. Sci. Total Environ., 706, 135742. https://doi.org/10.1016/j.scitotenv.2019.135742
[36] Gonçalves, L., & Damas, B., 2022. Automatic detection of rescue targets in marine search and rescue missions using UAVs. In 2022 International Conference on Unmanned Aircraft Systems (ICUAS), pp. 1638-1643. IEEE. https://doi.org/10.1109/ICUAS54217.2022.9836137
[37] Gramstad, O., & Bitner-Gregersen, E., 2019. Predicting extreme waves from wave spectral properties using machine learning. Int. Conf. Offshore Mech. Arct. Eng., 58783, V003T02A005. https://doi.org/10.1115/OMAE2019-96061
[38] Holland, J. H. (1975). Adaptation in Natural and Artificial Systems. University of Michigan Press.
[39] Hu, S. Y., Feng, A., Shi, J. H., Li, J. J., Khan, F., Zhu, H. W., Chen, J., & Chen, G. M., 2022. Underwater gas leak detection using an autonomous underwater vehicle (robotic fish). Process Saf. Environ. Prot., 167, 89-96. https://doi.org/10.1016/j.psep.2022.09.002
[40] Huang, B., Chen, G., Zhang, H., Hou, G., & Radenkovic, M., 2023. Instant deep sea debris detection for maneuverable underwater machines to build sustainable ocean using deep neural network. Sci. Total Environ., 878, 162826. https://doi.org/10.1016/j.scitotenv.2023.162826
[41] Isa, I. S., Rosli, M. S. A., Yusof, U. K., Maruzuki, M. I. F., & Sulaiman, S. N., 2022. Optimizing the hyperparameter tuning of YOLOv5 for underwater detection. IEEE Access, 10, 52818-52831. https://doi.org/10.1109/ACCESS.2022.3174583
[42] James, S. C., Zhang, Y., & O’Donncha, F., 2018. A machine learning framework to forecast wave conditions. Coast. Eng., 137, 1–10. https://doi.org/10.1016/j.coastaleng.2018.03.004
[43] Janssen, P. A. E. M., 2003. Nonlinear Four-Wave Interactions and Freak Waves. J. Phys. Oceanogr., 33, 863–884. https://doi.org/10.1175/1520-0485(2003)33<863:NFIAFW>2.0.CO;2
[44] Jocher, G., Chaurasia, A., Stoken, A., Borovec, J., Kwon, Y., Michael, K., & Mammana, L., 2022. ultralytics/yolov5: v6.2-yolov5 classification models, apple m1, reproducibility, clearml and deci.ai integrations. Zenodo.
[45] Kerguillec, R., Audère, M., Baltzer, A., Debaine, F., Fattal, P., Juigner, M., & Rollo, N., 2019. Monitoring and management of coastal hazards: Creation of a regional observatory of coastal erosion and storm surges in the pays de la Loire region (Atlantic coast, France). Ocean Coastal Manage., 181, 104904. https://doi.org/10.1016/j.ocecoaman.2019.104904
[46] Khanam, R., & Hussain, M., 2024. YOLOv11: An overview of the key architectural enhancements. arXiv preprint arXiv:2410.17725. https://doi.org/10.48550/arXiv.2410.17725
[47] Kharif, C., & Pelinovsky, E., 2003. Physical mechanisms of the rogue wave phenomenon. Eur. J. Mech. B-Fluids, 22, 603–634. https://doi.org/10.1016/j.euromechflu.2003.09.00
[48] Kim, T., & Lee, W.-D., 2024. Prediction of wave runup on beaches using interpretable machine learning. Ocean Eng., 297, 116918. https://doi.org/10.1016/j.oceaneng.2024.116918
[49] Krizhevsky, A., Sutskever, I., & Hinton, G. E., 2012. Imagenet classification with deep convolutional neural networks. Adv. Neural Inf. Process. Syst., 25.
[50] Lavrenov, I., 1998. The wave energy concentration at the Agulhas current off South Africa. Nat. Hazards, 17, 117–127.
[51] Lavrenov, I., & Porubov, A., 2006. Three reasons for freak wave generation in the non-uniform current. Eur. J. Mech. B-Fluids, 25, 574–585. https://doi.org/10.1016/j.euromechflu.2006.02.009
[52] LeCun, Y., Bottou, L., Bengio, Y., & Haffner, P., 1998. Gradient-based learning applied to document recognition. Proc. IEEE, 86(11), 2278-2324. https://doi.org/10.1109/5.726791
[53] Lee, J. W., Irish, J. L., Bensi, M. T., & Marcy, D. C., 2021. Rapid prediction of peak storm surge from tropical cyclone track time series using machine learning. Coast. Eng., 170, 104024. https://doi.org/10.1016/j.coastaleng.2021.104024
[54] Li, Y., Guo, J. H., Guo, X. M., Liu, K. Z., Zhao, W. T., Luo, Y. T., & Wang, Z. Y., 2020. A Novel Target Detection Method of the Unmanned Surface Vehicle under All-Weather Conditions with an Improved YOLOV3. Sensors, 20(17). https://doi.org/10.3390/s20174885
[55] Li, C., Li, L., Jiang, H., Weng, K., Geng, Y., Li, L., Ke, Z., Li, Q., Cheng, M., Nie, W., Li, Y., Zhang, B., Liang, Y., Zhou, L., Xu, X., Chu, X., Wei, X., & Wei, X., 2022. YOLOv6: A Single Stage Object Detection Framework for Industrial Applications. arXiv preprint arXiv:2209.02976. https://doi.org/10.48550/arXiv.2209.02976
[56] Lin, S., Ying, K., Chen, S., & Lee, Z., 2008. Particle swarm optimization for parameter determination and feature selection of support vector machines. Expert Syst. Appl., 35, 1817–1824. https://doi.org/10.1016/j.eswa.2007.08.088
[57] Lin, T. Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., & Zitnick, C. L., 2014. Microsoft coco: Common objects in context. In Computer Vision–ECCV 2014: 13th European Conference, pp. 740-755. Springer International Publishing. https://doi.org/10.1007/978-3-319-10602-1_48
[58] Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C. Y., & Berg, A. C., 2016. Ssd: Single shot multibox detector. In Computer Vision–ECCV 2016: 14th European Conference, pp. 21-37. Springer International Publishing. https://doi.org/10.1007/978-3-319-46448-0_2
[59] Liu, W., 2021. Beach sports image detection based on heterogeneous multiprocessor and convolutional neural network. Microprocess. Microsyst., 82, 103910. https://doi.org/10.1016/j.micpro.2021.103910
[60] Luo, W., Xing, J., Milan, A., Zhang, X., Liu, W., & Kim, T. K., 2021. Multiple object tracking: A literature review. Artif. Intell., 293, 103448.
[61] McCulloch, W. S., & Pitts, W., 1943. A logical calculus of the ideas immanent in nervous activity. Bull. Math. Biophys., 5, 115–133. https://doi.org/10.1007/BF02478259
[62] Melet, A., Teatini, P., Lee Cozannet, G., Jamet, C., Conversi, A., Benveniste, J., & Almar, R., 2020. Earth observations for monitoring marine coastal hazards and their drivers. Surv. Geophys., 41, 1489-1534. https://doi.org/10.1007/s10712-020-09594-5
[63] Mendelman, H., Massas, T., & Moshe, Y., 2023. Analysis of waves and human interaction using beach webcams. In OCEANS 2023-Limerick, pp. 1-4. IEEE. https://doi.org/10.1016/10.1109/OCEANSLimerick52467.2023.10244424
[64] Mori, N., Liu, P. C., & Yasuda, T., 2002. Analysis of freak wave measurements in the Sea of Japan. Ocean Eng., 29, 1399–1414. https://doi.org/10.1016/S0029-8018(01)00073-7
[65] Mostakov, N. A., Bakaev, V. S., Kulagin, K. A., Migachev, A. N., & Grafenkov, A. V., 2022. UAV-based drowning rescue system. In 2022 International Conference on Information, Control, and Communication Technologies (ICCT), pp. 1-4. IEEE. https://doi.org/10.1109/ICCT56057.2022.9976801
[66] Pelinovsky, E., Talipova, T., & Kharif, C., 2000. Nonlinear-dispersive mechanism of the freak wave formation in shallow water. Phys. D, 147, 83–94. https://doi.org/10.1016/S0167-2789(00)00149-4
[67] Platt, J., 1999. Probabilistic outputs for support vector machines and comparisons to regularized likelihood methods. Adv. Large Margin Classif., 10, 61–74.
[68] Redmon, J., Divvala, S., Girshick, R., & 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.
[69] Redmon, J., & Farhadi, A., 2017. YOLO9000: better, faster, stronger. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7263-7271.
[70] Redmon, J., & Farhadi, A., 2018. Yolov3: An incremental improvement. arXiv preprint arXiv:1804.02767.
[71] Ren, S., He, K., Girshick, R., & Sun, J., 2015. Faster r-cnn: Towards real-time object detection with region proposal networks. Adv. Neural Inf. Process. Syst., 28.
[72] Rombach, R., Blattmann, A., Lorenz, D., Esser, P., & Ommer, B. (2022). High-resolution image synthesis with latent diffusion models. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (pp. 10684-10695). https://doi.org/10.1109/CVPR52688.2022.01042
[73] Roy, M., Gautam, A., & Sugandhi, A., 2021. A deep learning framework for enhancing marine coastal security. In 2021 2nd International Conference for Emerging Technology (INCET), pp. 1-6. IEEE. https://doi.org/10.1109/INCET51464.2021.9456235
[74] Ruder, S., 2019. Neural transfer learning for natural language processing (Doctoral dissertation, NUI Galway).
[75] Rumelhart, D., Hinton, G., & Williams, R., 1986. Learning representations by back-propagating errors. Nature, 323, 533–536. https://doi.org/10.1038/323533a0
[76] Sathish, T., Maheswari, S. U., Balaji, V., Nirupama, P., Panchal, H., Li, Z., & Tlili, I., 2023. Coastal pollution analysis for environmental health and ecological safety using deep learning technique. Adv. Eng. Softw., 179, 103441. https://doi.org/10.1016/j.advengsoft.2023.103441
[77] Singh, A., & Nene, M., 2023. Optimization of YOLOV7's hyper parameters for simultaneous object detection in satellite imagery. Authorea Preprints.
[78] Sinha, A., & Abernathey, R., 2021. Estimating ocean surface currents with machine learning. Front. Mar. Sci., 8, 672477. https://doi.org/10.3389/fmars.2021.672477
[79] Soomere, T., & Engelbrecht, J., 2006. Weakly two-dimensional interaction of solitons in shallow water. Eur. J. Mech. B-Fluids, 25, 636–648. https://doi.org/10.1016/j.euromechflu.2006.02.008
[80] Sutskever, I., Vinyals, O., & Le, Q. V., 2014. Sequence to sequence learning with neural networks. Adv. Neural Inf. Process. Syst., 27.
[81] Tamura, H., Waseda, T., & Miyazawa, Y., 2009. Freakish sea state and swell-windsea coupling: Numerical study of the Suwa-Maru incident. Geophys. Res. Lett., 36, L01607. https://doi.org/10.1029/2008GL036280
[82] Teng, C., Kylili, K., & Hadjistassou, C., 2022. Deploying deep learning to estimate the abundance of marine debris from video footage. Mar. Pollut. Bull., 183, 114049. https://doi.org/10.1016/j.marpolbul.2022.114049
[83] Terven, J., Córdova-Esparza, D. M., & Romero-González, J. A., 2023. A comprehensive review of yolo architectures in computer vision: From yolov1 to yolov8 and yolo-nas. Mach. Learn. Knowl. Extr., 5(4), 1680-1716. https://doi.org/10.3390/make5040083
[84] Tian, Y., Ye, Q., & Doermann, D., 2025. YOLOv12: Attention-centric real-time object detectors. arXiv preprint arXiv:2502.12524.
[85] Toffoli, A., Waseda, T., Houtani, H., Cavaleri, L., Greaves, D., & Onorato, M., 2015. Rogue waves in opposing currents: An experimental study on deterministic and stochastic wave trains. J. Fluid Mech., 769, 277–297. http://doi.org/10.1017/jfm.2015.132
[86] Toguchi, H., Shimada, R., Ishikawa, T., & Komine, T., 2022. Study of determining risk level regarding swimming condition on bathing beach using AI. Coastal Eng. Proc., (37), 8-8. https://doi.org/10.9753/icce.v37.papers.8
[87] Tsai, C., Su, M., & Huang, S., 2004. Observations and conditions for occurrence of dangerous coastal waves. Ocean Eng., 31, 745–760. https://doi.org/10.1016/S0029-8018(03)00113-6
[88] Vadivel, M., Sundar, A. S., Murthy, P. V. R. K., Soundararajan, M., Rajan, D., & Priya, V., 2025. Dynamic coastal vulnerability index: A machine learning approach to predict future impacts of climate change and human activity on coastal environments. J. S. Am. Earth Sci., 165, 105692. https://doi.org/10.1016/j.jsames.2025.105692
[89] Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., & Polosukhin, I., 2017. Attention is all you need. Adv. Neural Inf. Process. Syst., 30.
[90] Viñes, M., Sánchez-Arcilla Jr., A., Epelde, I., Mösso, C., Franco, J., Sospedra, J., Gracia, V., & Sánchez-Arcilla, A., 2025. Morphodynamic predictions based on Machine Learning. Performance and limits for pocket beaches near the Bilbao port. Front. Environ. Sci., 13, 1600473. https://doi.org/10.3389/fenvs.2025.1600473
[91] Wang, C. Y., Bochkovskiy, A., & Liao, H. Y. M., 2023. YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 7464-7475.
[92] Wang, C. Y., Yeh, I. H., & Mark Liao, H. Y., 2024. Yolov9: Learning what you want to learn using programmable gradient information. In European Conference on Computer Vision, pp. 1-21. Springer Nature Switzerland. https://doi.org/10.1007/978-3-031-72751-1_1
[93] Wang, A., Chen, H., Liu, L., Chen, K., Lin, Z., Han, J., & Ding, G., 2024. YOLOv10: Real-time end-to-end object detection. arXiv preprint arXiv:2405.14458. https://doi.org/10.52202/079017-3429
[94] Waseda, T., Kinoshita, T., & Tamura, H., 2009. Evolution of a Random Directional Wave and Freak Wave Occurrence. J. Phys. Oceanogr., 39, 621–639. https://doi.org/10.1175/2008JPO4031.1
[95] Waseda, T., Tamura, H., & Kinoshita, T., 2012. Freakish sea state and sea states during ship accidents. J. Mar. Sci. Technol., 17, 305–314. https://doi.org/10.1007/s00773-012-0171-4
[96] Wojke, N., Bewley, A., & Paulus, D., 2017. Simple online and realtime tracking with a deep association metric. In 2017 IEEE International Conference on Image Processing (ICIP), pp. 3645-3649. IEEE.
[97] World Health Organization, 2024. Global status report on drowning prevention 2024. World Health Organization.
[98] Xu, G., Cheng, C., Yang, W., Xie, W., Kong, L., Hang, R., Ma, F., Dong, C., & Yang, J., 2021. Oceanic Eddy Identification Using an AI Scheme. Remote Sens., 11, 1349. https://doi.org/10.3390/rs11111349
[99] Zakharov, V., Dyachenko, A., & Prokofiev, A., 2006. Freak waves as nonlinear stage of Stokes wave modulation instability. Eur. J. Mech. B-Fluids, 25, 677–692. https://doi.org/10.1016/j.euromechflu.2006.03.004
[100] Zhang, D., O'Conner, N. E., Simpson, A. J., Cao, C., Little, S., & Wu, B., 2022. Coastal fisheries resource monitoring through A deep learning-based underwater video analysis. Estuar. Coast. Shelf Sci., 269, 107815. https://doi.org/10.1016/j.ecss.2022.107815
[101] Zhang, J., Zhao, X., Jin, S., & Greaves, D., 2022. Phase-resolved real-time ocean wave prediction with quantified uncertainty based on variational Bayesian machine learning. Appl. Energy, 324, 119711. https://doi.org/10.1016/j.apenergy.2022.119711