Based On Knowledge Discovery In Time Series Data Mining Algorithm

KDD(Knowledge Discovery in Databases) is a new emerging area in the research of artificial intelligence and databases, in which DM (Data Mining) on the time-series data is one of the important subject. In this paper, the essential theory of KDD and DM and a few factors of mining time-series databases are analyzed, the method of sequence attribute discrete and DM algorithm of classification discovery, clustering discovery, association rules and sequence pattern, especially the DM method based on time-series data are studied, and the pattern matching and association rules algorithms based on time-series data are proposed for improving the performance of the algorithm, and the effect of interest measure and negative attribute in association rules mining are discussed. The theory researching in this paper is the base of time-series data prediction model KDD-based, and realization of the algorithms have highly practicality value of the prediction model construction.