Unlock instant, AI-driven research and patent intelligence for your innovation.

Site site selection prediction method based on Weighted-Leader Rank and GMM clustering

A forecasting method and site technology, applied in forecasting, character and pattern recognition, instruments, etc., can solve the problems of deviation from the actual demand of site selection, less consideration of the travel characteristics of urban residents, etc.

Pending Publication Date: 2021-12-28
BEIJING UNIV OF TECH
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] In addition, the current site selection is mainly based on population density, regional land use characteristics and traffic conditions, and less consideration is given to the travel characteristics of urban residents, resulting in deviations between site selection and people's actual needs

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
  • Site site selection prediction method based on Weighted-Leader Rank and GMM clustering
  • Site site selection prediction method based on Weighted-Leader Rank and GMM clustering
  • Site site selection prediction method based on Weighted-Leader Rank and GMM clustering

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035] The present invention is explained and elaborated below in conjunction with relevant accompanying drawings:

[0036] The data set that the present invention adopts is the metro station check-in (AFC) data and the same period taxi GPS passenger travel trajectory data, based on the algorithm flow chart of Weighted-LeaderRank algorithm and mixed Gaussian model algorithm (GMM) as attached image 3 As shown, it is characterized in that it comprises the following steps.

[0037] Step 1: Collect the location coordinates of the completed subway stations, passenger AFC check-in data, and taxi GPS trajectory data. The GPS trajectory data includes the license plate numbers of 21,590 taxis, generation time, latitude and longitude, speed, vehicle status, etc., as shown in Table 1 shown.

[0038] Table 1 Taxi experiment data set

[0039]

[0040] Step 2: Set the default subway station coverage to 1km, and convert the subway AFC check-in data processing into a station-to-station ...

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 site selection prediction method based on Weighted-Leader Rank and GMM clustering. The method comprises the following steps: predicting a future metro line through metro station clock-in data and taxi OD data, selecting several metro stations with the most representativeness for the sorted stations, and predicting the site selection positions of the future peripheral stations. The method comprises the following steps of: converting a relation of passenger flow between established subway stations and stations into a weighted directed graph, and then calculating a Weighted-Leader Rank value of each node on the basis of the weighted directed graph; and taxi OD data outside the subway station coverage area are screened out, and GMM clustering is carried out on the data to obtain a clustering result, i.e., the predicted position of the overall newly-built subway station of the city in the future. A model evaluation method is provided, different parameters are set for the model, results are compared, and finally an optimal model is obtained and applied to prediction of the positions of newly-built stations around a representative subway station.

Description

technical field [0001] The invention belongs to the field of data mining, and relates to a site selection prediction method based on Weighted-LeaderRank and Gaussian Gaussian clustering (GMM). Background technique [0002] With the development of my country's cities and the continuous improvement of the transportation network, as of December 2019, Beijing's rail transit network has 23 operating lines and 405 stations, including 62 transfer stations. In addition, Beijing Metro currently has 15 lines under construction. By 2020, the Beijing Subway will form a rail transit network with 30 lines and a total length of 1,177 kilometers. Due to the late start of my country's overall subway construction, the existing subway lines do not meet all travel needs. People usually choose other travel methods in places outside the coverage of subway stations. [0003] The Weighted-LeaderRank algorithm is mainly used in the importance ranking of network nodes. The core idea of ​​the algori...

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): G06K9/62G06Q10/04G06Q50/30
CPCG06Q10/04G06F18/23G06Q50/40
Inventor 才智王佳炜郎琨李童苏醒郭黎敏
Owner BEIJING UNIV OF TECH