Traffic flow prediction method fusing spatial and temporal features

Abstract

The invention discloses a traffic flow prediction method fusing spatial and temporal features. The method comprises the following steps: step 1, preprocessing data; step 2, introducing an automatic encoder to obtain data characteristics; step 3, introducing an SAEs model and acquiring spatial feature ; step 4, introducing an LSTM model, and obtaining time features; step 5, synthesizing the SAEs model and the LSTM model to obtain an ideal hybrid model, and establishing a hybrid deep learning model SAES-LSTM to predict the traffic flow of an urban expressway. Time and space information is comprehensively utilized. The collected information of a database is analyzed and utilized more fully, and therefore a prediction result can be more accurate.

Description

technical field [0001] The invention belongs to the technical field of traffic forecasting, and in particular relates to a traffic flow forecasting method integrating spatio-temporal features. Background technique [0002] With the development of science and technology, accurate and reliable traffic forecasting has become a high expectation of tourists, transportation agencies and the public. However, because the disturbance factors in various situations are very complex, it is difficult to accurately predict the change of traffic flow. The successful prediction of traffic information firstly depends on the quality of traffic data acquired on site. Inductive Loop Detectors (ILDs) are the most common devices used to capture traffic flow information on highways, but a growing number of reports indicate that the data captured from current ILDs deviates from reality. Therefore, non-intrusive traffic detectors such as remote traffic microwave sensors (RTMS) and traffic video de...

AI Technical Summary

Problems solved by technology

However, since each data source has its own characteristics, it is not an easy task to fuse data from multiple sources

Images