Abstract
The classification of ships using remotely sensed data is increasingly vital for maritime security, environmental monitoring, and commercial applications. Advances in satellite imagery and remote sensing technologies have heightened the need for effective ship classification algorithms. A key challenge lies in the variability of ship appearances due to size, shape, orientation, and environmental factors. Ensemble learning, which combines multiple classifiers for improved accuracy, has shown promise in this area. However, this method faces issues like increased memory and time complexity, and the influence of lower-quality models, highlighting the need for model pruning. This study presents a new approach to maritime management through the introduction of an ensemble learning system. The MAGNAT (Maritime mAnaGement eNsemble leArning sysTem) proposal and novel contribution in this paper represent an intelligent ensemble solution that significantly enhances ship classification in the maritime domain through the adoption of ensemble learning techniques. Incorporating various Convolutional Neural Network (CNN) models into the training process, a novel aggregation strategy is devised to eliminate redundant models, retaining only those that actively enhance the learning process. Extensive experiments utilizing a renowned ship dataset were conducted to validate the effectiveness of the framework, ultimately demonstrating its superiority over conventional ensemble solutions.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Hsu, Y.-C.: Assessment of criteria of ship classification societies. Marit. Policy Manag. 50(7), 980–1004 (2023)
Wang, Y., Liu, J., Liu, R.W., Liu, Y., Yuan, Z.: Data-driven methods for detectionof abnormal ship behavior: progress and trends. Ocean Eng. 271, 113673 (2023)
Anta˜o, P., Sun, S., Teixeira, A., Soares, C.G.: Quantitative assessment of ship collision risk influencing factors from worldwide accident and fleet data. Reliab. Eng. Syst. Saf. 234, 109166 (2023)
Yasir, M., et al.: Ship detection based on deep learning using sar imagery: a systematic literature review. Soft. Comput. 27(1), 63–84 (2023)
Li, J., Chen, J., Cheng, P., Yu, Z., Yu, L., Chi, C.: A survey on deep-learning-basedreal-time sar ship detection. IEEE J. Sel. Top. Appl. Earth Observations Remote Sens. 16, 3218–3247 (2023)
Yang, Y., Lv, H., Chen, N.: A survey on ensemble learning under the era of deeplearning. Artif. Intell. Rev. 56(6), 5545–5589 (2023)
Campagner, A., Ciucci, D., Cabitza, F.: Aggregation models in ensemble learning: a large-scale comparison. Inf. Fusion 90, 241–252 (2023)
Ganaie, M.A., Hu, M., Malik, A., Tanveer, M., Suganthan, P.: Ensemble deep learning: a review. Eng. Appl. Artif. Intell. 115, 105151 (2022)
Yan, Z., Song, X., Yang, L., Wang, Y.: Ship classification in synthetic aperture radarimages based on multiple classifiers ensemble learning and automatic identification system data transfer learning. Remote Sens. 14(21), 5288 (2022)
Wang, Y., Yang, L., Song, X., Chen, Q., Yan, Z.: A multi-feature ensemble learning classification method for ship classification with space-based ais data. Appl. Sci. 11(21), 10336 (2021)
Salem, M.H., Li, Y., Liu, Z., AbdelTawab, A.M.: A transfer learning and optimizedcnn based maritime vessel classification system. Appl. Sci. 13(3), 1912 (2023)
Zheng, H., Hu, Z., Liu, J., Huang, Y., Zheng, M.: Metaboost: a novel heterogeneousdcnns ensemble network with two-stage filtration for sar ship classification. IEEE Geosci. Remote Sens. Lett. 19, 1–5 (2022)
Gao, J., Chi, M., Zhihui, H.: Energy consumption optimization of Inland sea ships based on operation data and ensemble learning. Math. Problems Eng. 2022, 1–13 (2022). https://doi.org/10.1155/2022/9231782
Wei, Y., Chen, Z., Zhao, C., Chen, X., He, J., Zhang, C.: A time-varying ensemblemodel for ship motion prediction based on feature selection and clustering methods. Ocean Eng. 270, 113659 (2023)
Liu, Y., Zhang, R., Deng, R., Zhao, J.: Ship detection and classification based oncascaded detection of hull and wake from optical satellite remote sensing imagery. GIScience Remote Sens. 60(1), 2196159 (2023)
Liu, Y., et al.: A survey of visual transformers. IEEE Trans. Neural Networks Learn. Syst. 1–21 (2023)https://doi.org/10.1109/TNNLS.2022.3227717
Chen, S., et al.: Adaptformer: adapting vision transformers for scalable visual recognition. Adv. Neural. Inf. Process. Syst. 35, 16664–16678 (2022)
Zhao, H., Zhang, H., Zhao, Y.: Yolov7-sea: object detection of maritime uav imagesbased on improved yolov7. In: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pp. 233–238 (2023)
Chen, X., Wu, X., Prasad, D.K., Wu, B., Postolache, O., Yang, Y.: Pixel-wise shipidentification from maritime images via a semantic segmentation model. IEEE Sens. J. 22(18), 18180–18191 (2022)
Acknowledgement
This work is co-funded by EU Horizon Europe under the project entitled “Smart Maritime and Underwater Guardian (SMAUG)” with grant number 101121129.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Mesgaribarzi, N. (2024). MAGNAT: Maritime Management Ensemble Learning System. In: Rocha, Á., Adeli, H., Dzemyda, G., Moreira, F., Poniszewska-Marańda, A. (eds) Good Practices and New Perspectives in Information Systems and Technologies. WorldCIST 2024. Lecture Notes in Networks and Systems, vol 986. Springer, Cham. https://doi.org/10.1007/978-3-031-60218-4_1
Download citation
DOI: https://doi.org/10.1007/978-3-031-60218-4_1
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-60217-7
Online ISBN: 978-3-031-60218-4
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)