Airport terminal departure passenger traffic volume prediction method based on fuzzy decision-making tree

A fuzzy decision tree and flow forecasting technology, applied in forecasting, instrumentation, data processing applications, etc., can solve the problems of fuzzy terminal departure passenger flow, terminal congestion optimization speed, low promotion ability, etc. The speed of optimization is slow, the prediction process is simple, and the effect of low efficiency is solved

Active Publication Date: 2015-04-29
HARBIN INST OF TECH
View PDF4 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The purpose of the present invention is to solve the existing technology in solving the phenomenon of terminal building congestion caused by the continuous increase of traffic pressure in the civil aviation field. A fuzzy decision tree-based forecasting method for departure passenger flow in terminal

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
  • Airport terminal departure passenger traffic volume prediction method based on fuzzy decision-making tree
  • Airport terminal departure passenger traffic volume prediction method based on fuzzy decision-making tree
  • Airport terminal departure passenger traffic volume prediction method based on fuzzy decision-making tree

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0019] Specific implementation mode one: a kind of fuzzy decision tree-based method for predicting the flow of passengers departing from the terminal of the present implementation mode is specifically prepared according to the following steps:

[0020] Step 1. Fuzzy preprocessing is performed on the statistical data with attributes, that is, the specific values ​​of the number of flights, time points and dates are substituted into the membership degree function operation and then converted into membership degree data in the [0,1] interval; where the attributes include flights Quantity, time and date;

[0021] Step 2, calculate the fuzzy information entropy H(A) of the number of flights, time points and dates, and select the attribute with the smallest fuzzy information entropy as the root node of the fuzzy decision tree;

[0022] Step 3: Using 60% to 80% of the membership degree data obtained in step 1, use the decision tree algorithm and the root node to establish a fuzzy dec...

specific Embodiment approach 2

[0030] Specific embodiment two: the difference between this embodiment and specific embodiment one is: the number of flights in step one is x including M 1 , M 2 , M 3 and M 4 four states;

[0031] m 1 Indicates that the number of flights is small, and the number of flights is 0~4, M 2 Indicates that the number of flights is small, and the number of flights is 4 to 8. M 3 Indicates that the number of flights is large and the number of flights is 8-12 and M 4 Indicates that the number of flights is large and the number of flights is 12 to 16. Other steps and parameters are the same as those in Embodiment 1.

specific Embodiment approach 3

[0032] Specific implementation mode three: the difference between this implementation mode and specific implementation mode one or two is: in step one, the number of flights is x according to the calculation process of the degree of membership function:

[0033] M ( x ) = M 1 ( x ) = 1 x ≤ 4 8 - x ...

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 provides an airport terminal departure passenger traffic volume prediction method based on a fuzzy decision-making tree, and relates to an airport terminal departure passenger traffic volume prediction method. The airport terminal departure passenger traffic volume prediction method aims at solving the problems that in the prior art in solving the phenomenon that an airport terminal is crowded, optimizing speed is low, timeliness is poor, generalization ability is low, application is complex, efficiency is low and simple and accurate prediction requirements can not be met. The method comprises the steps of step 1, obtaining the membership degree; step 2, selecting an attribute with the smallest fuzzy information entropy to be served as a root node of the fuzzy decision-making tree; step 3, obtaining a joint confidence degree of a leaf node lambaba; step 4, if lambaba satisfies lambaba>lambaba0, ending continuation and setting the joint confidence degree of the leaf node lambaba as the passenger traffic volume level probability; step 5, if the joint confidence degree of the leaf node lambaba <= lambaba0, repeating step 3 until the leaf node satisfies lambaba>lambaba0 to obtain the fuzzy decision-making tree; step 6, ensuring the achievement of the steps such as obtaining the fuzzy decision-making tree.

Description

technical field [0001] The invention relates to the field of forecasting the outbound passenger flow of a terminal building, in particular to a method for predicting the outbound passenger flow of a terminal building based on a fuzzy decision tree. Background technique [0002] At present, the continuous increase of traffic pressure in the field of civil aviation has caused terminal congestion. Therefore, to achieve high-efficiency operation of the terminal, higher requirements are put forward for the forecast of passenger flow arriving at the terminal. Domestic research on the prediction of passenger arrival in a short period of time is still in its infancy. Due to the strong randomness and nonlinearity of passenger flow in a short period of time, it brings great difficulties to the prediction. At present, many methods have been used to predict passenger flow, including support vector regression model, BP neural network model, FIR neural network model, etc. These methods ha...

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 Applications(China)
IPC IPC(8): G06Q10/04G06Q50/30
CPCG06Q10/04G06Q50/30
Inventor 程绍武张亚平刘岩牟秋
Owner HARBIN INST OF TECH
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