Bus passenger flow volume prediction modeling method based on XGBoost model

A modeling method and model prediction technology, applied in prediction, character and pattern recognition, instruments, etc., to achieve the effect of efficient data prediction

Inactive Publication Date: 2019-10-29
ZHEJIANG UNIV
View PDF3 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] At present, there are many studies on the modeling of bus passenger flow, but as far as the current progress is concerned, the most detailed model can only predict the passenger flow on a line in units of one hour

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
  • Bus passenger flow volume prediction modeling method based on XGBoost model
  • Bus passenger flow volume prediction modeling method based on XGBoost model
  • Bus passenger flow volume prediction modeling method based on XGBoost model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0050] The present invention will be further explained below in conjunction with the accompanying drawings and specific embodiments.

[0051] The bus passenger flow prediction modeling method based on the XGBoost model of the present invention utilizes IC cards and GPS data to study the number of passengers getting on the bus at each station in each period of the day, and considers weather factors to use the Xgboost model to predict the number of passengers getting on the bus in the future period The number of people on the bus, and a passenger flow prediction model for the alighting station is proposed.

[0052] Taking Shenzhen M414 line bus as an example below, adopt the modeling method of the present invention to predict its passenger flow.

[0053] 1 Study the number of passengers boarding at each station every half hour every day

[0054] (1) Data removal

[0055] The analysis of the data itself found that the following problems existed in the original data set:

[005...

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 bus passenger flow volume prediction modeling method based on an XGBoost model. According to the modeling method, the number of passengers getting on a bus at each station ineach time period every day is calculated by utilizing an IC card and GPS data, and the number of passengers getting on the bus at each station in the future time period of the bus is predicted by adopting an XGboost model in consideration of weather factors; the travel modes of the passengers are divided into regular travel passengers and random travel passengers, and the passenger flow distribution of get-off stations is predicted by utilizing the historical travel of the passengers and the get-on frequency of each station. A model is established based on bus card swiping data, and the method is suitable for a bus operation mode that card swiping records exist when a bus gets on the bus and card swiping is not conducted when the bus gets off the bus. The model is a mathematical and algorithm model for analyzing and predicting original data, can predict the getting-on passenger flow of all stations on a line by taking half an hour as a unit, and can obtain the distribution of the number of people getting off the bus at each station.

Description

technical field [0001] The invention belongs to the field of intelligent transportation, and in particular relates to an XGBoost model-based method for forecasting and modeling bus passenger flow. The invention establishes a model based on the card swiping data of the bus, and is suitable for the operation mode of the bus in which there is a record of swiping the card when getting on the bus but without swiping the card when getting off the bus. This model is a mathematical and algorithmic model that analyzes and predicts raw data. It can predict the flow of boarding people at all stations on a line in units of half an hour, and obtain the number of people getting off at each station. distributed. Background technique [0002] Urban public transport is a very important means of transportation in every city, and is the main body of urban traffic, known as the arteries of urban muscles. In recent years, with the increase of urban population, the operating pressure of urban t...

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 & AuthorityApplications(China)
IPC IPC(8): G06K9/62G06Q10/04G06Q50/26
CPCG06Q10/04G06Q50/26G06F18/2148G06F18/23213G06F18/24
Inventor朱雄卓张书悦
OwnerZHEJIANG UNIV