Method for cleaning traffic flow data on basis of time-space analysis

Abstract

The invention discloses a method for cleaning traffic flow data on the basis of time-space analysis. The method is implemented by a dirty data storage module, a clean data storage module and an computation module, wherein the dirty data storage module stores traffic flow information according to a fixed format without changing the fixed format, and the traffic flow information is received in real time; the computation module extracts the latest data from the dirty data storage module at fixed intervals, and simultaneously extracts data from a clean database to perform computation, and the data from the clean database has time and space matching relations with the latest data; and the clean data storage module stores data according to the fixed format, and the data are computed by the computation module. The method has the advantages that a procedure for cleaning the traffic flow data is simplified, a time-space parallel analysis process is adopted, accordingly, operation for cleaning the traffic flow data is carried out conveniently, quickly and accurately, and the method has actual engineering application value in aspects of simplifying procedures for cleaning traffic flow data and improving the cleaning quality of the traffic flow data.

Description

technical field [0001] The invention belongs to the field of data processing, and in particular relates to a traffic flow data cleaning system and method based on spatio-temporal analysis. Background technique [0002] With the continuous rise of urban traffic pressure, intelligent transportation systems are playing an increasingly important role in urban traffic management and control systems. The correctness, integrity and reliability of the traffic flow basic database are the basic guarantee for the efficient operation of the entire intelligent transportation system. However, the existing traffic collection system and information transmission system have many problems in data collection, transmission and storage operations, and dirty data is prone to be generated, such as detection device failure, data transmission failure and so on. These dirty data may lead to failure or even wrong decision-making of intelligent transportation system. Therefore, dirty data must be eff...

AI Technical Summary

Problems solved by technology

However, the former method includes Kalman filter model, parameter regression model, time series model, etc., only considers the use of historical factors for data processing, and is not suitable for time-varying complex systems, and has low precision; the latter method includes state phase space Reconstruction model, wavelet decomposition model, neural network, support vector machine, etc. The methods are too complicated and not suitable for practical application

Images