Traffic Flow Prediction Method Based on Balanced Exponential Smoothing Method and Stacked Autoencoder
A technology of stacking self-encoding and balanced index, which is applied in the field of traffic flow prediction based on the balanced exponential smoothing method and the stacked self-encoder, can solve the problems of complex nonlinearity of traffic flow, solve complex nonlinear problems and improve prediction. The effect of precision
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0034] Refer to attached figure 1 , to further describe the specific steps of the present invention.
[0035] Step 1, generate training sequence and test sequence.
[0036] Nearly three months of historical traffic flow data was collected using highway sensors.
[0037] Count the missing data collected by each sensor on the highway for three months.
[0038] The data of the first two months of the sensor data with the least missing data constitute the training sequence, and the data of the last month constitute the test sequence.
[0039] Step 2, preprocess the training sequence and test sequence.
[0040] Computes the average of the first two non-missing data and the last two non-missing data for each missing data in the training sequence and test sequence.
[0041] Completing each missing value in the training sequence and test sequence with the average value to obtain a complete training and test traffic flow data sequence.
[0042] Step 3, use the balance exponential ...
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