数学理论与应用 ›› 2017, Vol. 37 ›› Issue (1): 100-111.

• • 上一篇    下一篇

基于类高斯混合模型的水位规律研究

周琳1, 唐弋静1, 戴斌祥1, 刘晓群2   

  1. 1.中南大学数学与统计学院,湖南长沙,410083; 2.湖南省洞庭湖水利工程管理局,湖南长沙,410007

  • 出版日期:2017-03-30 发布日期:2020-09-25
  • 基金资助:

    国家自然科学基金资助项目(51479215);

    国家级本科生自由探索计划项目(201510533230)

Study on Water Level Regulation Based on Gauss-like Mixed Model

Zhou Lin1, Tang Yijing1, Dai Binxiang1, Liu Xiaoqun2   

  1. 1.School of Mathematics and Statistics,Central South University,Changsha 410083,China; 2.Dongting Lake Water Conservancy Engineering Management Bureau of Hunan Province,Changsha 410007,China

  • Online:2017-03-30 Published:2020-09-25

摘要: 函数拟合是一种重要的数据挖掘技术.在本文中,我们将一个改进的高斯混合模型应用于水位变化规律的研究中,以便更好的做出水位预报.以洞庭湖流域安乡站点为例,首先将其近十年来的水位数据进行数据预处理,得出每年的满足损失函数极小化的类高斯混合模型,再构造超定线性方程组并且利用最小二乘法求得各年对应的权重,从而得到一个加权模型,最后对此模型进行了合理性检验,并提出了改进结果.

关键词: 水位, 函数拟合, 高斯混合模型, 数据挖掘, 最小二乘法

Abstract:

Function fitting is an important data mining technique.In this paper,the modified Gauss type mixed model is applied to the study of the changing pattern of the water level in order to make accurate prediction of the water level.Firstly,we make a pretreatment of the ten years data of the water level and establish a Gauss-like mixed model which satisfies the smallest loss function via curve fit.Then,we construct an overdetermined linear equations and use the least square method to obtain the corresponding weight.Finally,we get a weighted model and examine the rationality of the model and make some improvements.

Key words:

"> Water level, Function fitting, Gauss mixed model, Date mining , Least square method