A convolutional neural network-based moving object destination prediction method

Abstract

The invention discloses a convolutional neural network-based moving object destination prediction method, which comprises the following steps of: introducing a parameterized minimum description length(PMDL) strategy to carry out optimal segmented representation on an original trajectory, weakening the difference degree between similar trajectories, and enhancing respective important characteristics of the different trajectories; proposing a trajectory pixelated representation method (PRT), and converting the one-dimensional trajectory sequence into a two-dimensional pixel image; and intercepting important feature parts from the track image and inputting the important feature parts into a convolutional neural network (CNN) model, and performing feature extraction and destination prediction. The method has the advantages that a one-dimensional track sequence is converted into a two-dimensional pixel image, and destination coordinates are determined by mining spatial features of the track image; the invention provides an effective solution for the data sparsity problem which is common in destination prediction but cannot be solved in many traditional methods, and high-accuracy destination prediction is realized.

Description

technical field [0001] The invention provides a method for predicting the destination of a moving object, which predicts its possible destination coordinates under the condition of a known query track, and belongs to the cross field of engineering application and information science. Background technique [0002] With the ubiquity of mobile sensors, the use of smartphones and in-car navigation systems becoming part of our lives, we are also increasingly benefiting from various location-based services. The location sensor equipped with the mobile device uses the global positioning system to accurately provide the user's location, and the location with different time stamps forms the user's daily activity track. This trajectory data is highly temporally and spatially regular, providing the data source for the emergence and improvement of many location-based applications. A large number of new location-based applications need to predict destinations and future routes, such as ...

AI Technical Summary

Problems solved by technology

This method solves the "data sparse problem" that the traditional model does not pay attention to, and fully considers the impact on the accuracy of destination prediction due to the limited number of historical trajectories.

Images