Traffic jam prediction method based on deep learning and fuzzy clustering

Abstract

The invention discloses a traffic jam prediction method based on deep learning and fuzzy clustering. The method comprises the following steps: (1) obtaining three-parameter original data of road traffic flow detected by a detector; (2) removing abnormal data from the data by using a threshold method, replacing the abnormal data by using a moving average method, and complementing missing data to obtain complete traffic time series data; aggregating the data to obtain a proper time interval, and finally normalizing the aggregated data; (3) mining spatial-temporal correlation according to historical data, performing training by using a CNN and a GRU to extract traffic flow spatial-temporal features, and performing future moment parameter prediction by using the trained network; (4) performingfuzzy clustering by using the historical data in the step (2), and calculating a membership degree to obtain a clustering center; and (4) judging the traffic state of the prediction time period according to the membership degree of the traffic data predicted in the step (3), thereby achieving the purpose of predicting traffic congestion. According to the invention, the traffic jam can be predicted more accurately.

Description

technical field [0001] The invention relates to the field of intelligent transportation, in particular to a traffic jam prediction method based on deep learning and fuzzy clustering. [0002] technical background [0003] As urban traffic conditions become more and more complex, road congestion is becoming more and more serious. Accurate prediction and evaluation of traffic conditions that have occurred or will occur in the future can not only allow travelers to understand the traffic conditions but also Plan your own route, and for the traffic management department, you can also formulate corresponding control measures in advance to reduce the impact of traffic congestion. [0004] It is an effective traffic congestion prediction method by predicting traffic flow parameters and then dividing the predicted traffic flow parameters into different traffic states. The existing traffic flow parameter prediction usually extracts the temporal characteristics of the traffic time ser...

AI Technical Summary

Problems solved by technology

The existing traffic flow parameter prediction usually extracts the temporal characteristics of the traffic time series data of a single road segment for prediction, while ignoring the interaction and spatio-temporal correlation between multiple road segments, resulting in low accuracy when predicting traffic parameters of multiple road segments ; At the same time, when using traffic flow parameters to classify traffic states, due to the ambiguity and uncertainty of traffic states, the amount of traffic state information contained in different parameters is also different. Directly using parameter values ​​​​to classify will lead to poor classification results

Images