文章基本信息

标题：Automatic Identification System (AIS) Data Supported Ship Trajectory Prediction and Analysis via a Deep Learning Model
本地全文：下载
作者：Chen, Xinqiang ; Wei, Chenxin ; Zhou, Guiliang 等
期刊名称：Journal of Marine Science and Engineering
电子版ISSN：2077-1312
出版年度：2022
卷号：10
期号：9
页码：1-12
DOI：10.3390/jmse10091314
语种：English
出版社：MDPI AG
摘要：Automatic Identification System (AIS) data-supported ship trajectory analysis consistently helps maritime regulations and practitioners make reasonable traffic controlling and management decisions. Significant attentions are paid to obtain an accurate ship trajectory by learning data feature patterns in a feedforward manner. A ship may change her moving status to avoid potential traffic accident in inland waterways, and thus, the ship trajectory variation pattern may differ from previous data samples. The study proposes a novel ship trajectory exploitation and prediction framework with the help of the bidirectional long short-term memory (LSTM) (Bi-LSTM) model, which extracts intrinsic ship trajectory features with feedforward and backward manners. We have evaluated the proposed ship trajectory performance with single and multiple ship scenarios. The indicators of mean absolute error (MAE), mean absolute percentage error (MAPE) and mean square error (MSE) suggest that the proposed Bi-LSTM model can obtained satisfied ship trajectory prediction performance.
关键词：maritime traffic flow; Bi-LSTM model; prediction; maritime traffic management; traffic safety