Abstract
This paper proposes a data preparation process for managing real-world kinematic data and detecting fishing vessels. The solution is a binary classification that classifies ship trajectories into either fishing or non-fishing ships. The data used are characterized by the typical problems found in classic data mining applications using real-world data, such as noise and inconsistencies. The two classes are also clearly unbalanced in the data, a problem which is addressed using algorithms that resample the instances. For classification, a series of features are extracted from spatiotemporal data that represent the trajectories of the ships, available from sequences of Automatic Identification System (AIS) reports. These features are proposed for the modelling of ship behavior but, because they do not contain context-related information, the classification can be applied in other scenarios. Experimentation shows that the proposed data preparation process is useful for the presented classification problem. In addition, positive results are obtained using minimal information.
Highlights
Maritime vigilance is essential to ensure safety and security at sea
These sensors can be categorized into two major groups: those relying on the collaboration of the object using information that is provided by the located ship (e.g., Automatic Identification System, AIS), and those that only use the information generated by the sensor
To address track noise generated by kinematic AIS data over time, so-called state estimation algorithms exist in the field of data fusion
Summary
Maritime vigilance is essential to ensure safety and security at sea. Illegal, unreported and unregulated (IUU) fishing [1] poses a risk to food safety and maritime biodiversity. This paper proposes ship type identification using only the kinematic information that can be extracted from any sensor. Sensors 2020, 20, 3782 identification, e.g., it is highly likely that a ship detected in a fishing area is a fishing ship This improvement in recognition capability specializes the system to the environment of the particular context information. As a result of these issues, the approach proposed in this paper does not consider context information and detects fishing ships using only sensor-extracted kinematics. Movements made by different objects (e.g., ships) may differ greatly in terms of both distance and duration, which implies that they are not comparable to each other To solve these problems, the proposed process takes the following steps: First, data cleaning is undertaken to eliminate information that is inconsistent or incorrect, or otherwise cannot be used in the subsequent classification process.
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.
