The Data Mining Technique of Time-series Trending Structure Series

Author

Gao, Xiangjun ; Du, Qiliang ; Tian, Lianfang ; Mao, Zongyuan ; Wang, Yong

Author_Institution

Coll. of Autom. Sci. & Eng., South China Univ. of Technol., Guangzhou

Volume

2

fYear

0

fDate

0-0 0

Firstpage

6019

Lastpage

6023

Abstract

According to the inner characters of the time series, the conception of time-series trending structure series and the latest time sub-series was defined, and the time-series trending structure mining technique was presented. The technique first converted the time series waiting for mining into its trending structure series, then used the information underlying in the latest trending structure sub-series of the latest time sub-series as a guide to excavate the original time series. The model of RBF neural network was also presented to predict the trend of time series with real world data set. Experimental results reveal that the time-series trending structure mining technique is significant

Keywords

data mining; radial basis function networks; time series; RBF neural network; data mining; time subseries; time-series trending structure mining; trending structure series; Automation; Data mining; Educational institutions; Electronic mail; Information science; Intelligent control; Neural networks; Predictive models; RBF Neural Network; latest trending structure sub-series; time series; trending structure series;

fLanguage

English

Publisher

ieee

Conference_Titel

Intelligent Control and Automation, 2006. WCICA 2006. The Sixth World Congress on

Conference_Location

Dalian

Print_ISBN

1-4244-0332-4

Type

conf

DOI

10.1109/WCICA.2006.1714235

Filename

1714235