乙型、丙型流感病毒的长记忆ARFIMA模型

long-memory ARFIMA models for DNA sequences of influenza B,C virus

用时间序列模型来分析乙型、丙型这两种流感病毒,对乙流、丙流病毒DNA序列提供了一种新的时间序列模型,即CGR弧度序列。利用CGR坐标将乙流、丙流病毒DNA序列转换成CGR弧度序列,且引入长记忆ARFIMA模型去拟合这两类序列。发现随机找来的10条乙流序列,10条丙流序列都具有长相关性且拟合很好,并且还发现这两种病毒序列可以尝试用不同的ARFIMA模型ARFIMA(0,d,4)模型,ARFIMA(1,d,1)模型去识别。

In this paper,we make use of the time series model analyze the influenza B,C virus,and propose a new time series model for DNA sequence of influenza B,C virus,i.e.CGR radians series.The CGR coordinates are converted into a time series model,and a long-memory ARFIMA（p,d,q） model is introduced to simulate the time series model.We select randomly the 10 influenza B sequences and 10 influenza C sequences to analysis.we uncover in these data remarkably long-rang correlations and fit the model reasonably by ARFIMA（p,d,q） model,and also uncover that we can try to use different ARFIMA model（i.e.,ARFIMA（0,d,4）,ARFIMA（1,d,1）） to identify the two kinds of sequences.