Population prediction method based on LS-SVM-Leslie combination model
The invention provides a population prediction method based on an LS-SVM-Leslie combined model, and belongs to mathematics and computer science. The problem that a traditional population prediction model lacks a gender proportion, an age structure and a population data change rule is solved. Accordi...
Saved in:
Main Authors | , , , , , , |
---|---|
Format | Patent |
Language | Chinese English |
Published |
13.12.2022
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | The invention provides a population prediction method based on an LS-SVM-Leslie combined model, and belongs to mathematics and computer science. The problem that a traditional population prediction model lacks a gender proportion, an age structure and a population data change rule is solved. According to the technical scheme, the method comprises the following steps that S1, data are collected and preprocessed; s2, selecting a prediction index and estimating a birth ratio; s3, predicting a growth rate D1 of a specific age and a male/female death rate D2 by using an LS-SVM model; s4, inputting the D1 and the D2 into a Leslie model, and outputting specific initial age data D3; s5, taking D3 as an input parameter of Leslie in the next year, and iteratively outputting population data of each year; s6, establishing a time sequence prediction model and a gray system prediction model; and S7, combining the two models in the step S6 based on the weight, and outputting a prediction result. The population prediction me |
---|---|
Bibliography: | Application Number: CN202211205164 |