journal article·2024-05-22Open access

Study on Classification of Fishing Vessel Operation Types Based on Dilated CNN-IndRNN

Jiachen Yu, Shunlong Fu, Xiongguan Bao

Applied Sciences· Volume 14· Issue 11

Abstract

At present, fishery resources are becoming increasingly depleted, and a reliable assessment of fishing activity is a key step in protecting marine resources. Correctly identifying the type of fishing operation can help identify illegal fishing vessels, strengthen fishing regulations, and prevent overfishing. Aiming to address these problems, this study first collects and preprocesses fishing vessel AIS data. Improvements are proposed on the basis of the convolutional neural network (CNN), long short-term memory (LSTM), and other models, changing the CNN to dilated CNN and LSTM to independently recurrent neural network (IndRNN). The results of the experiment show that the accuracy, precision, recall, and F-1 score of the model are finally obtained as 93.12%, 93.10%, 93.14%, and 93.10%, respectively. Overall, the new model proposed in this study offers a significant improvement in performance compared to the models of other scholars in the past.
Source: crossref · Quality: baseline

Research context

OpenAlex topics: Marine and Coastal Research

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

Affiliations

Faculty of Maritime and Transportation, Ningbo University, Ningbo 315000, China

References (28)

Show source-provided references
1. Rebuilding global fisheries10.1126/science.1173146 ↗
2. Rebuilding marine life10.1038/s41586-020-2146-7 ↗
3. Income diversification and risk for fishermen10.1073/pnas.1212278110 ↗
4. Macfadyen, G., Huntington, T., and Cappell, R. (2009). Abandoned, Lost or Otherwise Discarded Fishing Gear, FAO. FAO Fisheries and Aquaculture Technical Paper No. 523.
5. Winners and losers in a world where the high seas is closed to fishing
6. Anomaly Detection of Fishing Vessels Based on AIS Data
7. Detecting suspicious fishing vessel behaviors from AIS data using deep learning
8. Detecting Illegal Fishing Vessels Using Automatic Identification System Data Based on Machine Learning Algorithms
9. Use of a Vessel Monitoring System (VMS) to improve spatial management measures for a data-poor deep-water fishery
10. Validation of GPS loggers and vessel monitoring systems for use on fishing vessels
11. A systematic approach to identify fishing areas based on VMS data: Application to the Brazilian pair trawl fishery targeting Argentine hake
12. Evaluation of trawling, gillnetting and longlining fishing gear efficiency and sustainability in the Red Sea
13. Fishing gear classification based on fish behaviour to assist fisheries management
14. The impact of trawl fishery on the ecosystem in the south-eastern Black Sea
15. Tracking the global footprint of fisheries10.1126/science.aao5646 ↗
16. Kim, K.L., and Lee, K.M. (2020). Convolutional neural network based geartype ide-ntification from automatic identification system trajectory data. Appl. Sci., 10.10.3390/app10114010 ↗
17. VA-TRAC: Geospatial Trajectory Analysis for Monitoring, Identification, and Verification in Fishing Vessel Operations10.1111/cgf.13966 ↗
18. Automatic identifica-tion system based fishing trajectory data preprocessing method using map reduce
19. De Souza, E.N., Boerder, K., Matwin, S., and Worm, B. (2017). Improving Fishing Pattern Detection from Satellite AIS Using Data Mining and Machine Learning. PLoS ONE, 11.10.1371/journal.pone.0163760 ↗
20. Challenges and opportunities in using vessel monitoring systems and automatic identification systems (VMS/AIS) to support the ecosystem approach to fisheries
21. A hybrid method for nonlinear equations
22. Ship detection in optical remote sensing images based on deep convolutional neural networks10.1117/1.JRS.11.042611 ↗
23. A deep learning approach for fault detection and RUL estimation in bearings
24. Deep learning10.1038/nature14539 ↗
25. Goodfellow, I., Bengio, Y., and Courville, A. (2016). Deep Learning, MIT Press.
26. Convolutional neural networks for super-resolution of raw time-of-flight depth images
27. Li, S., Li, W., and Cook, C. (2018, January 18–22). Independently Recurrent Neural Network (IndRNN): Building A Longer and Deeper RNN. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.10.1109/CVPR.2018.00572 ↗
28. IndRNN for Time Series Forecasting: A Case Study of Debris Flow Forecasting