LSTM-CNN-based urban road network traffic state prediction method
A technology of traffic status and prediction method, applied in the field of intelligent transportation, which can solve problems such as only considering the time dimension
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0069] Such as figure 1 , figure 2 , image 3 As shown, a LSTM-CNN-based urban road network traffic state prediction method includes the following steps:
[0070] A LSTM-CNN-based traffic state prediction method for urban road network, the specific steps are as follows:
[0071] Step S1: Estimate and calculate the historical vehicle speed of the road network;
[0072] Step S2: Construct an adjacency matrix based on the obtained historical vehicle speed information;
[0073] Step S3: constructing the LSTM-CNN neural network;
[0074] Step S4: the adjacency matrix is used as input to train the LSTM-CNN neural network, and utilize the gradient descent method to update and optimize the parameters of the LSTM-CNN neural network;
[0075] Step S5: Step S5 is performed iteratively until the LSTM-CNN neural network converges;
[0076] Step S6: Input the adjacency matrix of real-time vehicle speed information to the LSTM-CNN neural network to predict the traffic status of the ...
Embodiment 2
[0122] Such as figure 1 , figure 2 , image 3 , Figure 4 As shown, in this embodiment, the step size of prior data and prediction results is set to 5min. In order to test the reliability of the prediction effect of the model under different prior conditions, this setting has prior information of four lengths: 15min, 30min, 45min and 60min, and the corresponding step size is H={3,6,9,12}, The prediction lengths are 5min, 15min and 30min, and the corresponding step lengths are P={1,3,6}.
[0123] This embodiment is built based on the Tensorflow deep learning framework. After screening, the model parameters are determined as follows: In the convolutional network, use 6 convolution kernels with a size of (3,3), and use an average pooling layer with a size of (2,2 ), the number of neurons in the fully connected layer is 400, in the long short-term memory neural network, a layer of LSTM network is used, the number of nodes is 256, the final output is through a layer of fully c...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com