摘要
数据挖掘技术已经应用到很多研究领域中,数据挖掘的类型也越来越复杂。其中一类数据本身是有顺序相关的,且是实值型数据,定义具有这样特征的数据为时间序列数据,使用常见的数据挖掘方法从时间序列数据中进行知识学习是不适用的。并且随着大数据理论的不断发展,能够增量式地处理数据以减小对时间和存储空间的需求。基于时间序列数据维度高、实值有序、数据间存在自相关性等特点,提出一种增量式决策树的时间序列分类算法。
Data mining technology has been attracting great interest in a vast array of research areas, and their types are more and more complex.The data is related and ordered set of real valued variables, and then such data with above characters is called time series. The following conclusion is that common method of data mining method can＇t be suit to time series data mining. And with the continuous development of the theory of big data, incremental method is essential in order to decrease temporal and space demand for implement of time series.Focuses on the research on time series classification according to time series features of high dimensionality, ordered real-valued vari-ables, auto-correlation and so on. And proposes incremental decision-tree algorithm for time series classification.
基金
北京市自然科学基金(No.4142042)
关键词
时间序列
增量式学习
决策树
算法研究
Time Series
Incremental Learning
Decision Tree
Algorithm Research
