Lane-level traffic flow prediction method based on dynamic traffic flow big data

Lane-level traffic flow prediction method based on dynamic traffic flow big data

The invention belongs to the field of traffic flow prediction, and discloses a lane-level traffic flow prediction method based on dynamic traffic flow big data, and the method comprises the steps: S1, collecting the historical traffic flow information of a to-be-predicted road network; s2, construct...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: LUO ZHIWEI, CHEN MINJIE, TANG JIEXIA, LIU JUNJIE, WANG GUICHENG, LUO ZHENQUAN, LIU WEILIN, CHEN XUGAO, LIANG GUOXIONG, LIU HAIXIA, LI LINMAO, LI ZIJUN, YE KUNHAN, QIN WEN, CHEN ZHIPING, XIAO GUOMEI
Format: Patent
Sprache:chi ; eng
Schlagworte:
CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FORADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORYOR FORECASTING PURPOSES
PHYSICS
SIGNALLING
SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR
TRAFFIC CONTROL SYSTEMS
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:The invention belongs to the field of traffic flow prediction, and discloses a lane-level traffic flow prediction method based on dynamic traffic flow big data, and the method comprises the steps: S1, collecting the historical traffic flow information of a to-be-predicted road network; s2, constructing a road network historical traffic flow information matrix, and processing the road network historical traffic flow information matrix by using expansion convolution; constructing the traffic flow information of the same node in the road network at different historical times into vectors, and calculating a learnable matrix based on the vectors of all nodes; s3, constructing a spatial feature adjacency matrix based on data driving; and S4, a gating structure is designed to integrate the time features and the space features, and the gating structure is designed based on an attention mechanism and global pooling operation to obtain a final prediction result. According to the method, the time features are extracted