Automatic ship route design between two ports: A data-driven method. (March 2020)

• Record Type: Journal Article
• Authors: Wen, Yuanqiao; Sui, Zhongyi; Zhou, Chunhui; Xiao, Changshi; Chen, Qianqian; Han, Dong; Zhang, Yimeng
• Is Part Of: Applied ocean research. Volume 96(2020)
• Publication Date: 2020-03
• Subjects: Ship route design -- Data-driven -- Ship dimensions -- DBSCAN algorithm -- ANN; Ocean engineering -- Periodicals; 620.416205
• DOI: 10.1016/j.apor.2019.102049
• Languages: English
• ISSNs: 0141-1187

Abstract

Abstract: With the forced installation of the ship's automatic identification system (AIS), a large amount of ship trajectory data in the world is generated. These data provide information on latitude, longitude, speed and course, and plenty of materials for maritime pattern extraction and vessel behavior prediction. And how to dig into these AIS data deeply to discover the ship behavior pattern is an important job. There are two key points on the automatic ship route design research: the turning area generation and the turning area linkage. In this paper, we integrate DBSCAN and Artificial Neural Network capable of automatic ship route design based on massive AIS data between certain ports. The main purpose of this study is to recognize the key regions by applying DBSCAN algorithm and then connect these regions automatically by cluster similarity measuring. Then artificial neural network has been used to learn the relationship of turning regions and generate a reasonable route with different ship dimensions. The main achievement of this study have twofold. First, a research framework for automatic generation of ship route is proposed. We can process big AIS data and use them to generate ship route. Second, generation of different routes according to ships of different dimension under the research framework. The method is capable of generating ship route automatically according to different ship dimensions, which has been evaluated on two real routes around the world.