Traffic flow prediction method of attention-based deep residual space-time diagram convolutional network
The invention discloses a traffic flow prediction method of an attention-based deep residual space-time diagram convolutional network, which comprises the following steps of: on the basis of dividing traffic flow data into data components according to three different time granularities, introducing...
Saved in:
Main Authors | , , , |
---|---|
Format | Patent |
Language | Chinese English |
Published |
03.02.2023
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | The invention discloses a traffic flow prediction method of an attention-based deep residual space-time diagram convolutional network, which comprises the following steps of: on the basis of dividing traffic flow data into data components according to three different time granularities, introducing a deep residual network to model traffic network data while considering an attention mechanism and a dynamic space-time block; therefore, the accuracy of traffic flow data prediction can be improved.
本发明公开了一种基于注意力的深度残差时空图卷积网络的交通流预测方法,在将交通流量数据按照三不同时间粒度划分成数据分量基础上,在考虑注意力机制和动态时空块的同时,引入了深层残差网络对交通网络数据进行建模,来处理复杂的交通网络数据,这样可以提升交通流数据预测的准确性。 |
---|---|
Bibliography: | Application Number: CN202211331900 |