Mobile phone user travel mode recognition method based on C4.5 decision tree

Abstract

The invention discloses a mobile phone user travel mode recognition method based on a C4.5 decision tree. The mobile phone user travel pattern recognition method comprises: collecting mobile phone signaling data of a volunteer, and processing the mobile phone signaling data into a travel track sequence with reference to time information and position information of the data; excavating a relationship of a travel characteristic attribute and a corresponding travel traffic mode from the travel track data of the volunteer; dividing the collected mobile phone signaling data of the volunteer into two parts according to a supervised machine learning method, which are respectively a training data set and a test data set; extracting a variety of characteristic attributes of travel behaviors from mobile phone data corresponding to the travel process of the volunteer according to the communication principle and the traffic theory; training a travel mode recognition model in combination with a real travel mode condition fed back by the volunteer via an artificial intelligence algorithm, C4.5 algorithm with supervision and learning ability to obtain a high-precision mobile phone user travel mode recognition model based on the mobile phone signaling data.

Description

technical field [0001] The invention relates to the technical field of traffic planning and management methods, in particular to a method for identifying travel modes of mobile phone users based on a C4.5 decision tree. Background technique [0002] The travel ratio of various modes of transportation and the sharing rate of public transportation have always been important data concerned by transportation planning and traffic management departments. In traffic analysis, commonly used traffic information collection methods include coils, microwaves, and videos. Different information collection methods have their advantages and scope of application. [0003] Due to the limited use of traffic collection methods such as coils, microwaves, and videos, it is impossible to continuously and effectively track people's travel behavior, and it is even more difficult to obtain OD information of people's travel. The cost of these traffic information collection devices is generally high,...

AI Technical Summary

Problems solved by technology

This is because although mobile phone signals can cover a wide range, the accuracy of base station positioning is low, which belongs to fuzzy positioning, because it is impossible to judge the user's travel mode through the speed value of the travel process like analyzing GPS data.

However, the proportion of GPS users is far lower than that of mobile phone users, and GPS data can only illustrate the travel characteristics of specific groups of people, and cannot truly reflect the travel status of the general public