Urban travel mode comprehensive identification method based on mobile phone signaling data

Abstract

The invention discloses an urban travel mode comprehensive identification method based on mobile phone signaling data. The method aims at mobile phone signaling data generated by a target city all daylong and identifies a parking point and an all-day travel OD of each person, and the method includes: firstly, accurately identifying all underground rail transit travel modes through a subway special base station, then, comparing the underground rail transit travel modes with the real navigation data of the Advanced GPS on the basis of extracting mobile phone data characteristic parameters, andidentifying the traffic mode of resident travel by utilizing an unsupervised machine learning algorithm. In order to improve the recognition accuracy, three correction modes are adopted to correct therecognition result (road network correction, user personal attribute correction and road network and user personal attribute combined correction), an optimization algorithm is provided, the three correction modes are compared, and the optimal correction result is obtained.

Description

technical field [0001] The invention relates to the field of traffic planning, in particular to the field of traffic demand prediction. Background technique [0002] Traffic demand forecasting is the basis of urban traffic planning, and it is of great significance to accurately predict urban traffic demand for rational management and control of urban traffic system. Existing traffic demand forecasting methods (such as traffic allocation models) are highly dependent on the travel demand estimates under different travel modes. However, due to its highly complex nature, it is difficult to accurately predict the needs of different approaches. This is due to the fact that the temporal / spatial fluctuations in the operation of the transportation system and the traffic flow are undetectable, thus, the effective identification of traffic modes is the key to the current technology. [0003] In the past, there were many defects in the method of obtaining traffic information such as t...

AI Technical Summary

Problems solved by technology

This method requires the survey object to cooperate with the collection of acceleration detection equipment data. This process is affected by multiple factors such as manpower and material resources. It is unreasonable to apply the algorithm model obtained from the collected data training to all future travel data.

Images