Method for predicting trajectory of marine floating objects based on adaptive Gaussian mixture model

Abstract

The present invention relates to the field of machine learning, and proposes an ocean trajectory clustering and predicting method. In order to accurately predict future trajectory points, trajectory clustering is required first. According to the trajectory clustering method disclosed by the present invention, similarity measurement is carried out on the trajectory points of complex variability andstrong volatility at sea, and the potential data information is mined; and the method combines the Gaussian mixture model GP with the Dirichlet process DP, and the non-parametric Bayesian framework of the DP is used to determine the number of clusters to improve cluster adaptability. The algorithm uses the process of adding Chinese restaurants based on the DP, and uses the collapsed Gibbs sampling method to solve the model, so that the unsupervised classification from the finite mixed model to the infinite mixed model is implemented, the number of clusters can be automatically obtained, and future trajectory points are predicted for the clustered trajectories by using the Gaussian process regression prediction method. According to the technical scheme of the present invention, the disadvantages of manually specifying the number of clusters and local maximization in parameter estimation are avoided, and the accuracy of prediction is improved under the premise of ensuring adaptive clustering.

Description

Technical field: [0001] The invention relates to the field of machine learning and ocean trajectory, in particular, a method for clustering and predicting the trajectory points of floating objects acquired in real time by buoys. Background technique: [0002] With the rapid development of the ocean transportation industry, trajectory analysis is the most commonly used method for moving objects at sea, but the complex and volatile trajectory at sea brings great challenges to data mining. Because the information between each other is not known before the trajectory data is analyzed, the trajectory clustering method is very suitable for mining the trajectory data of moving objects. Clustering is to analyze the structural characteristics of trajectories with similar motion patterns to determine the degree of similarity between trajectories, and then classify trajectories with high similarity into one category. Traditional clustering algorithms need to determine the number of cl...

AI Technical Summary

Problems solved by technology

[0003] In order to solve the arbitrariness of the number of artificially designated clusters, the purpose of this invention is to make up for the shortcomings faced by the traditional Gaussian mixture model, and propose a trajectory prediction method for floating objects in the sea based on the adaptive Gaussian mixture model

Images