Blog
About

0
views
0
recommends
+1 Recommend
1 collections
    0
    shares
      • Record: found
      • Abstract: found
      • Article: found

      FVID: Fishing Vessel Type Identification Based on VMS Trajectories

      Read this article at

      ScienceOpenPublisher
      Bookmark
          There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

          Abstract

          Vessel Monitoring System (VMS) provides a new opportunity for quantified fishing research. Many approaches have been proposed to recognize fishing activities with VMS trajectories based on the types of fishing vessels. However, one research problem is still calling for solutions, how to identify the fishing vessel type based on only VMS trajectories. This problem is important because it requires the fishing vessel type as a preliminary to recognize fishing activities from VMS trajectories. This paper proposes fishing vessel type identification scheme (FVID) based only on VMS trajectories. FVID exploits feature engineering and machine learning schemes of XGBoost as its two key blocks and classifies fishing vessels into nine types. The dataset contains all the fishing vessel trajectories in the East China Sea in March 2017, including 10031 pre-registered fishing vessels and 1350 unregistered vessels of unknown types. In order to verify type identification accuracy, we first conduct a 4-fold cross-validation on the trajectories of registered fishing vessels. The classification accuracy is 95.42%. We then apply FVID to the unregistered fishing vessels to identify their types. After classifying the unregistered fishing vessel types, their fishing activities are further recognized based upon their types. At last, we calculate and compare the fishing density distribution in the East China Sea before and after applying the unregistered fishing vessels, confirming the importance of type identification of unregistered fishing vessels.

          Related collections

          Author and article information

          Journal
          JOUC
          Journal of Ocean University of China
          Science Press and Springer (China )
          1672-5182
          07 May 2019
          01 April 2019
          : 18
          : 2
          : 403-412
          Affiliations
          1 College of Information Science and Engineering, Ocean University of China, Qingdao 266100, China
          2 Wenzhou Ocean and Fishery Vessel Safety Rescue Information Center, Wenzhou 325000, China
          Author notes
          *Corresponding author: HONG Feng
          Article
          s11802-019-3717-9
          10.1007/s11802-019-3717-9
          Copyright © Ocean University of China, Science Press and Springer-Verlag GmbH Germany 2019.

          The copyright to this article, including any graphic elements therein (e.g. illustrations, charts, moving images), is hereby assigned for good and valuable consideration to the editorial office of Journal of Ocean University of China, Science Press and Springer effective if and when the article is accepted for publication and to the extent assignable if assignability is restricted for by applicable law or regulations (e.g. for U.S. government or crown employees).

          Product
          Self URI (journal-page): https://www.springer.com/journal/11802

          Comments

          Comment on this article