A Method of Urban Traffic Flow Prediction Based on Tensor Filling

Abstract

The present invention relates to an urban traffic flow prediction method based on tensor filling. The method comprises the following steps: the step S1: collecting traffic flow state data adjacent toa prediction point; the step S2: performing initial filling according to the collected traffic data; the step S3: design a traffic data tensor; and the step S4: performing dynamic filling prediction based on tensor decomposition dynamic filling according to the designed traffic flow data tensor. The urban traffic flow prediction method based on tensor filling overcomes defects that prediction precision is not good in the condition that a traffic flow data source has deficiencies in the prior art; and moreover, a mode of tensor window division dynamic filling is employed while a traffic flow tensor model is constructed, so that prediction precision is improved in the condition that the traffic flow data source has deficiencies.

Description

technical field [0001] The invention relates to an urban traffic flow prediction method based on tensor filling. Background technique [0002] With the rapid development of the economy, traffic congestion has become one of the primary considerations for travelers. The waste of travel time and costs caused by traffic congestion has also indirectly brought about varying degrees of economic losses and a decline in urban operating efficiency. , how to alleviate the road pressure caused by traffic congestion, and plan daily travel is a problem that needs to be solved. Accurate prediction of urban traffic flow can save travel time for travelers, reduce road congestion rate, and improve urban operation efficiency. great commercial value. [0003] The traffic flow prediction methods that have been proposed at home and abroad mainly include time series method, Kalman filter, chaos theory, neural network and support vector machine (SVM) and so on. Traffic flow data has the character...

AI Technical Summary

Problems solved by technology

Traffic flow data has the characteristics of time correlation and space correlation. The traffic flow prediction is analyzed through the data collected by sensor devices and future traffic predictions are made. Sensor devices include mobile devices and fixed devices. Common mobile devices include mobile phones, Tablet PCs, etc. Common fixed devices include ground sensing coils, etc. The prediction of traffic status depends on a large amount of historical data collected by sensors, and the historical data is often incomplete when considering the sudden failure of some acquisition devices in actual use. The previous prediction The method does not overcome the defect of low accuracy in predicting traffic flow with incomplete historical data

Images