Your browser doesn't support javascript.
loading
Trend prediction of chaotic time series / 药物分析学报
Journal of Pharmaceutical Analysis ; (6): 38-41, 2007.
Article in Chinese | WPRIM | ID: wpr-621722
ABSTRACT
To predict the trend of chaotic time series in time series analysis and time series data mining fields, a novel predicting algorithm of chaotic time series trend is presented, and an on-line segmenting algorithm is proposed to convert a time series into a binary string according to ascending or descending trend of each subsequence. The on-line segmenting algorithm is independent of the prior knowledge about time series. The naive Bayesian algorithm is then employed to predict the trend of chaotic time series according to the binary string. The experimental results of three chaotic time series demonstrate that the proposed method predicts the ascending or descending trend of chaotic time series with few error.

Full text: Available Index: WPRIM (Western Pacific) Type of study: Prognostic study Language: Chinese Journal: Journal of Pharmaceutical Analysis Year: 2007 Type: Article

Similar

MEDLINE

...
LILACS

LIS

Full text: Available Index: WPRIM (Western Pacific) Type of study: Prognostic study Language: Chinese Journal: Journal of Pharmaceutical Analysis Year: 2007 Type: Article