Ship trajectory classification method based on feature selection and hyper-parameter optimization

Abstract

The invention discloses a ship trajectory classification method based on feature selection and hyper-parameter optimization. For the problem of unbalanced original data in ship trajectory classification, firstly, data cleaning and preprocessing are performed on multiple pieces of trajectory data of an automatic ship identification system, then all trajectories are drawn by matplotlib, unavailable trajectories are deleted, then features are calculated to obtain additional features, dimensionality reduction processing is performed on speed, course and trajectory coordinates, backward feature selection is carried out on all features after dimension reduction processing through a random forest (RF), finally hyper-parameter optimization is carried out through the random forest, and classification prediction is carried out on the features through model training and performance evaluation without depending on an external information source. The ship trajectory classification method has high performance and is stable, and can be effectively applied to actual ship trajectory classification.

Description

technical field [0001] The invention relates to trajectory classification technology, in particular to a ship trajectory classification method based on feature selection and hyperparameter optimization. Background technique [0002] With the rapid development of maritime satellite navigation and positioning technology, the safety and efficiency of maritime transportation has become very important. The number of ships in global ocean transportation has reached an unprecedented level, and it is showing a trend of high-speed, large-scale and intelligent development. In 2021 The unexpected congestion and closure of the Suez Canal in March, rising tensions in the freight market, and the associated economic impacts are beginning to emerge show the value of trajectory classification. The automatic identification system (Automatic Identification System, AIS) is a new generation of maritime communication and navigation system working in the VHF band. The AIS message provides a wealth...

AI Technical Summary

Problems solved by technology

However, these studies only classify the trajectories of ships into specific ship operations, and do not classify the trajectories of various ships, nor combine dynamic features such as trajectories with static features, and do not calculate features to obtain additional features to classify trajectories, and it does not solve the problem of imbalance in the AIS dataset

Images