Properties of the GM(1,1) with fractional order accumulation

被引：108

作者：

Wu, Lifeng ^{[1
]}

Liu, Sifeng ^{[1
]}

Fang, Zhigeng ^{[1
]}

Xu, Haiyan ^{[1
]}

机构：

[1] Nanjing Univ Aeronaut & Astronaut, Coll Econ & Management, Nanjing 210016, Jiangsu, Peoples R China

来源：

APPLIED MATHEMATICS AND COMPUTATION | 2015年 / 252卷

基金：

中国国家自然科学基金;

关键词：

Grey system theory; The initial condition; The monotonicity and convexity; Fractional order accumulation; GREY FORECASTING-MODEL; BERNOULLI MODEL; OPTIMIZATION;

D O I：

10.1016/j.amc.2014.12.014

中图分类号：

O29 [应用数学];

学科分类号：

070104 ;

摘要：

For traditional grey model (GM(1,1)), it is proved theoretically that the initial condition is not utilized, and the simulative value is convex and increased or is the decreased and concave when the actual sequence is nonnegative increased. These shortcomings are the results of traditional first order accumulation on grey system model. However, for the GM(1,1) with fractional order accumulation, the initial condition is utilized, and the monotonicity and convexity of simulative value are uncertain when the actual value is nonnegative increased. The results of practical numerical examples demonstrate that the GM(1,1) with fractional order accumulation provides very remarkable predication performance compared with the traditional GM(1,1) model. (c) 2014 Elsevier Inc. All rights reserved.

引用

页码：287 / 293

页数：7

共 18 条

[1] Grey neural networks for river stage forecasting with uncertainty [J].