首页 | 本学科首页   官方微博 | 高级检索  
     

非线性动力系统R/S法的改进及小波预测
引用本文:毛军军,程蓉,吴涛. 非线性动力系统R/S法的改进及小波预测[J]. 计算机工程与应用, 2009, 45(29): 198-201. DOI: 10.3778/j.issn.1002-8331.2009.29.058
作者姓名:毛军军  程蓉  吴涛
作者单位:1.安徽大学 数学科学学院,合肥 230039 2.安徽大学 智能计算与信号处理教育部重点实验室,合肥 230039 3.南京大学 计算机软件新技术国家重点实验室,南京 210093
基金项目:国家自然科学基金,安徽省高校自然科学研究计划项目,中国博士后科学基金,安徽大学人才队伍建设经费资助 
摘    要:针对固定电话和移动电话用户人数的时间序列,将小波变换与R/S分析法,多重分形相结合,探讨了系统的动力学特性和演化规律,并从分形维数、非周期循环长度、奇异性指数等方面指出电话用户人数增长趋势存在强持续性和长期记忆性以及具有多重分形特征,随着配分阶数的增大,多重分形随之增强,并得出移动电话人数的多重分形特性更强。接着对原始数据和小波重构后的数据进行了回归拟合比较,结果证明小波重构后的数据拟合程度更高,并利用重构的数据预测了未来三个月的电话用户人数。

关 键 词:电话用户人数  R/S分析  非周期循环长度  多重分形分析  小波变换  预测  
收稿时间:2008-11-14
修稿时间:2009-2-3 

Improvement of R/S analysis in nonlinear system and wavelet forecast
MAO Jun-jun,CHENG Rong,WU Tao. Improvement of R/S analysis in nonlinear system and wavelet forecast[J]. Computer Engineering and Applications, 2009, 45(29): 198-201. DOI: 10.3778/j.issn.1002-8331.2009.29.058
Authors:MAO Jun-jun  CHENG Rong  WU Tao
Affiliation:1.Department of Mathematical Sciences,Anhui University,Hefei 230039,China 2.Key Laboratory of Intelligent Computing & Signal Processing of Ministry of Education,Anhui University,Hefei 230039,China 3.State Key Laboratory for Novel Software Technology,Nanjing University,Nanjing 210093,China
Abstract:By reconstructing the original data by wavelet transform based on R/S analysis and multifractal analysis,it analyses the nonlinear characteristics of the system of fixed-line phone users and mobile phone users and its evolutionary principle.According to fractal dimension,non-periodic cycle,holder index,it points out that the growth of phone users has strong stability,long-term memory and multifractal feature.With the order of paritition function increasing,the multifractal strength increases.Moreover,the multifractal strength of mobile phone users is greater.Compared to the original data,the reconstructed data fit better.The number of phone users of the next three months is forecasted by the reconstructed data.
Keywords:the number of phone users  Rescaled Range Analysis(R/S)  non-periodic cycle  multifractal analysis  wavelet transform  forecast
本文献已被 万方数据 等数据库收录!
点击此处可从《计算机工程与应用》浏览原始摘要信息
点击此处可从《计算机工程与应用》下载免费的PDF全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号