Combined prediction model of quantum genetic grey prediction model and support vector machine

The grey forecasting model has been successfully used in many fields. But it still has some defects. Research has found that the problems of the conventional grey prediction model in the background value and the boundary value have great influence on the accuracy of prediction result. To address thi...

Full description

Saved in:
Bibliographic Details
Published in2016 5th International Conference on Computer Science and Network Technology (ICCSNT) pp. 247 - 251
Main Authors Jiangyong Cao, Yilin Fang, Quan Liu, Aiming Liu
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.12.2016
Subjects
Biological cells
Data models
Genetic algorithms
Grey prediction model
Logic gates
Predictive models
Quantum genetic algorithm
Sociology
Support vector machine
Support vector machines
Online AccessGet full text
DOI10.1109/ICCSNT.2016.8070157

Cover

More Information
Summary:The grey forecasting model has been successfully used in many fields. But it still has some defects. Research has found that the problems of the conventional grey prediction model in the background value and the boundary value have great influence on the accuracy of prediction result. To address this problem, a combinatorial optimization method is proposed in this paper. Firstly, to overcome the shortcomings of the conventional grey prediction model, the quantum genetic algorithm is used to optimize the parameters of grey prediction model based on the least square calculation model parameters. Secondly, the support vector machine regression is used to predict the residual sequence to fix the prediction result yielded by the optimized prediction model talked above. Finally, examples are given to show that the combination prediction model proposed in this paper has higher prediction accuracy compared with the conventional grey prediction method.
DOI:10.1109/ICCSNT.2016.8070157