Abstract
Ship abnormal behavior detection is an essential part of maritime supervision. It can assist maritime departments to conduct real-time supervision on a certain sea area, avoid ship risks, and improve the efficiency of sea area supervision. Given the problems of complex detection methods, poor detection effectiveness, and low detection accuracy, a Gated Recurrent Unit (GRU) was proposed for ship abnormal behavior detection. Under the premise of introducing the attention mechanism into a GRU, the optimal GRU structure parameters were obtained through the intelligent algorithm to perform deeper feature extraction and train the ship abnormal behavior based on the optimized GRU neural network, so as to realize the detection and recognition of the trajectory data to be measured. Finally, based on the public data set and the trajectory data of the inward and outward ports of ships issued by Nanjing Section, Jiangsu Maritime Bureau, the TensorFlow frame was used to establish an abnormal behavior detection model. The simulation results demonstrated that the abnormal behavior detection model shortened the abnormal detection time. The abnormal behavior detection model used in the detection of ship abnormal behavior enhanced the accuracy and stability of the abnormal behavior identification and verified the validity and superiority of this method.
Highlights
With the long-term development of the marine and shipbuilding industry, people’s maritime activities have penetrated into all aspects of marine production
The results showed that the recognition accuracy of the Bi-long short-term memory (LSTM) model was higher, and the ship abnormal behavior could be found in time
This model uses an intelligent algorithm to optimize the structural parameters and convergence speed of the Gated Recurrent Unit (GRU) network, and constructs a ship abnormal behavior detection model based on the optimized GRU network
Summary
With the long-term development of the marine and shipbuilding industry, people’s maritime activities have penetrated into all aspects of marine production. To realize the effective monitoring of the ship’s navigation state, the relevant government departments have established a ship traffic service monitoring system in marine environments This monitoring system does not have the ability to identify abnormal behaviors, and the processing of ship trajectory information is manually completed. References [21,22,23] use the characteristics of deep learning and time series to propose a ship trajectory prediction method based on recurrent neural networks—the long–short-term memory (RNN-LSTM) model. Based on the existing methods, this paper proposes a GRU network model with an attention mechanism This model uses an intelligent algorithm to optimize the structural parameters and convergence speed of the GRU network, and constructs a ship abnormal behavior detection model based on the optimized GRU network. Eng. 2022, 10, 249 the problems of low detection accuracy and long detection time caused by the complex detection methods in the existing methods
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
