Track similarity calculation method based on sorting learning

Abstract

The invention relates to a track similarity calculation method based on sorting learning. The method comprises the following steps: 1) expanding an Euclidean space; 2) calculating similar attributes of the track sequence; 3) normalizing the track sequence; 4) constructing a label of an experiment track by adopting a self-similarity method; 5) constructing a training set, and training the SVM learner; and 6) dividing the test set into an input document set and a label document set, and outputting the rank of the real label of each input document by applying the trained SVM sorting model. The beneficial effects of the invention are that the method irons out the limitations of a conventional track similarity calculation method based on a point matching algorithm, the low accuracy of track matching, the weak resistance to a noise non-uniform sampling rate, and the efficiency problem of a track matching algorithm based on deep learning; according to the method, the time complexity of similarity calculation is greatly reduced, and compared with the prior art, the accuracy of trajectory similarity calculation is improved.

Description

technical field [0001] The invention relates to the field of track similarity calculation, in particular to a track similarity calculation method based on ranking learning. Background technique [0002] Trajectory similarity calculation has been highly valued by research institutions at home and abroad because of its wide application prospects. So far, many research results have been achieved, in many fields such as vehicle route search, travel route query, animal migration route positioning, and even stock trends. There are quite good application prospects. Due to the development of the Internet of Things, embedded devices with global positioning systems are also widely used, making trajectory data easier to collect and greatly promoting the development of trajectory similarity research. However, the accuracy of trajectory similarity calculation is limited due to the inherent positioning bias of positioning systems such as GPS and the reality of uneven sampling rates. Mos...

AI Technical Summary

Problems solved by technology

However, due to the inherent positioning bias of GPS and other positioning systems and the reality of uneven sampling rates, the accuracy of trajectory similarity calculations is limited.

Most of the traditional trajectory similarity calculation methods are based on the idea of ​​point matching, which is highly interpretable and easy to operate, but the accuracy rate is not high in many application scenarios, and the resistance to noisy data is weak

The deep learning method that has emerged in recent years is applied to the trajectory similarity calculation. Although the accuracy rate has been improved, it requires a large amount of data sets and a long training time, which undoubtedly increases a lot of computing costs. It is not suitable for mobile devices with limited resources.

Images