Traffic mode discrimination method of semi-supervised SVM based on mobile phone signaling data

Abstract

The invention relates to a computer identification technology, and specifically relates to a traffic mode discrimination method of semi-supervised SVM based on mobile phone signaling data. The methodcomprises: (1) preparing and preprocessing data; (2) designing label types; (3) extracting travel characteristics; (4) establishing an improved traffic mode manual identification process; (5) trainingan initial classifier; (6) judging the traffic mode of an unmarked sample; (7) judging whether the classifier meets a termination condition or not; (8) updating a high confidence coefficient sample data set; (9) optimizing a semi-supervised SVM classifier based on a Tri-training; (10) judging the traffic mode of an unmarked sample; (11) judging whether the classifier meets a termination condition; (12) updating a data set of a low-confidence sample; and (13) optimizing the shell vector-based semi-supervised SVM classifier. The information acquisition cost is reduced, the data utilization rateis improved, judgment is flexible and comprehensive, the precision is high, and the application scene is wider.

Description

technical field [0001] The invention relates to computer identification technology, in particular to a traffic mode discrimination method based on semi-supervised SVM of mobile phone signaling data. Background technique [0002] Travel mode information plays an important role and value in traffic planning, traffic control management and other aspects. At present, the methods of obtaining traffic information include two categories: traditional survey and data mining. Traditional survey methods such as questionnaire surveys and telephone inquiries are difficult to implement at high frequency and on a large scale, and cannot accurately reflect the actual transportation mode information; data mining methods are mainly based on mobile phone data to establish certain rules to mine transportation mode information. , the method of data mining can not only solve the shortcomings of difficult survey organization, low sampling rate, and single dimension of information display, but als...

AI Technical Summary

Problems solved by technology

Cell phone signaling data is unlabeled data. If the method of supervised learning is used, a large amount of cell phone signaling data needs to be manually marked, which is a large workload and the data utilization rate is low; But the output class is difficult to identify and the accuracy is low

Images