Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Grid search support vector machine-based journey time prediction method

A support vector machine and travel time technology, applied in the field of intelligent transportation, can solve the problems of time prediction without in-depth research, and achieve the effect of improving prediction accuracy

Active Publication Date: 2017-11-03
BEIHANG UNIV
View PDF4 Cites 20 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, there is no in-depth research on the prediction of the travel time of inland ships, and this problem needs to be solved urgently.

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
  • Grid search support vector machine-based journey time prediction method
  • Grid search support vector machine-based journey time prediction method
  • Grid search support vector machine-based journey time prediction method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0058] A support vector machine travel time prediction method based on grid search, taking the AIS data of the Wuhan section of the Yangtze River as an example, the details are as follows:

[0059] Step 1. In the original data, the scope of the monitoring flight segment is within the third ring road of Wuhan City, with a total length of about 22km, such as figure 2 As shown in the label, the monitoring time is from 00:00:00 on August 11, 2014 to 13:59:59 on August 19, 2014, with a total monitoring time of 206 hours. Based on SQL Server 2008, after investigation, a total of 167,865 pieces of data were generated.

[0060] According to the different course angles of the ship's navigation to the ground, the above raw data can be imported, and the following can be obtained: image 3 The above-mentioned 167,865 pieces of data are divided into uplink ships and downlink ships.

[0061] like image 3 It is shown in the two black rectangular boxes numbered 1 and 2, where the black b...

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 invention discloses a grid search support vector machine-based journey time prediction method and belongs to the intelligent transportation field. The method comprises the following steps that: 1, on the basis of ship automatic identification system data, and data preprocessing is performed according to the investigation of missing data, the division of upstream and downstream ships and the removal of redundant data; 2, a historical period-based inland ship journey time prediction model is constructed, and a training data set is obtained according to the model; 3, the optimal parameters of the prediction model are searched on the basis of a support vector machine grid search method; 4, the prediction of inland ship journey time is realized on the basis of the optimal parameters; and 5, an evaluation result is predicted. With the method of the invention adopted, the ship automatic identification system data are mined and analyzed through using a data mining theory method, and the therefore, the prediction of inland ship journey time can be realized; the improvement of the management level of navigation affair management departments can be facilitated; and the rapid development of inland shipping can be promoted.

Description

technical field [0001] The invention relates to a grid search-based support vector machine travel time prediction method, which belongs to the field of intelligent transportation. This method can realize the prediction of the travel time of inland river ships based on the data of automatic identification system (Automatic Identification System, AIS), and provide theoretical and technical support for the navigation management department. Background technique [0002] Inland waterway shipping is one of the important modes of transportation in our country. It is an important participant in the comprehensive utilization of water resources and complex transportation system, and it connects inland areas and coastal areas, bringing huge economic profits to our country every year. However, my country's inland waterway shipping still has problems such as ship navigation safety, logistics optimization management, port planning and dispatching, etc., which directly affect the developme...

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
IPC IPC(8): G08G3/00G06Q10/04G06Q50/30G06K9/62
CPCG06Q10/04G08G3/00G06F18/2411G06Q50/40
Inventor 马晓磊杨洁
Owner BEIHANG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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