A High-speed Ramp Travel Time Prediction Method Based on Multi-model Fusion

A technology of travel time and prediction method, applied in the field of machine learning, which can solve problems such as weak generalization ability, poor stability of prediction effect, and complex parameter setting of a single prediction model

Inactive Publication Date: 2021-09-10
CHANGSHA UNIVERSITY OF SCIENCE AND TECHNOLOGY
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Aiming at the problems of complex parameter setting of the existing single prediction model, poor prediction effect stability and weak generalization ability, the present invention provides a high-speed ramp travel time prediction method based on multi-model fusion

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A High-speed Ramp Travel Time Prediction Method Based on Multi-model Fusion
  • A High-speed Ramp Travel Time Prediction Method Based on Multi-model Fusion
  • A High-speed Ramp Travel Time Prediction Method Based on Multi-model Fusion

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0037] like figure 1 As shown, this embodiment provides a high-speed ramp travel time prediction method based on multi-model fusion, which specifically includes:

[0038] like figure 2 As shown, use the following steps to obtain multiple pre-trained weak learners:

[0039] B1. Using the self-service sampling method to obtain multiple sample sampling sets for the training sample set;

[0040] B2. Perform data processing for each sample sampling set to obtain training samples suitable for each learning model;

[0041] B3. Using the training samples to train a corresponding learning model and obtain multiple pre-trained weak learners.

[0042] For example, this embodiment selects XGBoost (hereinafter referred to as Xgb), LightGBM, SVM, linear regression (Linear regression) and KNN as multiple pre-trained weak learner models to include.

[0043] S1. Obtain historical driving time data, and directly map the historical driving time data to obtain the first prediction result SWL...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The present invention relates to a high-speed ramp travel time prediction method based on multi-model fusion; S1, obtain historical travel time data, and directly map the historical travel time data to obtain the first prediction result; S2, use multiple pre-trained weak learners to obtain A plurality of second prediction results; S3, using the first prediction result to filter a plurality of second pre-results to obtain a prediction set; S4, using the MAPE value in the prediction set to obtain a strong learner model and updating the prediction set and the strong learner model; S5 , repeat above step S4; until the strong learner model is no longer updated, use the last updated strong learner model as the prediction model of the high-speed ramp travel time; the method of the present invention can predict the travel time of the high-speed ramp, and the obtained The prediction accuracy of the strong learner model is higher than that of any single model, and the obtained strong learner model has better robustness and generalization ability.

Description

technical field [0001] The invention relates to the technical field of machine learning, in particular to a multi-model fusion-based high-speed ramp travel time prediction method. Background technique [0002] The travel time of a road segment can directly reflect the degree of road congestion. Ramp travel time is an important evaluation index for the advantages and disadvantages of ramp control strategies, and a reasonable prediction of it can provide scientific data support for ramp control. There are many kinds of travel time predictions. For example, the parameter models include artificial neural network models and Kalman filter models, and they all require a large number of calibration parameters. There are also non-parametric models, such as historical average methods, KNN algorithms, and non-parametric regression models. Such algorithms are widely used because their mechanisms are relatively simple and do not require a large number of parameters to be set. The trave...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Patents(China)
IPC IPC(8): G08G1/01G06N20/00
Inventor 陈曦何宇明李捷彭朔
Owner CHANGSHA UNIVERSITY OF SCIENCE AND TECHNOLOGY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap