SIMILARITY SEARCH BASED ON SHAPE REPRESENTATION IN TIME SERIES DATA SETS

Time\|series are important kinds of complex data. Recently a growing attention has been paid to mining time\|series knowledge,while similarity search in time\|series data sets is one of the important aspects in time series knowledge discovery. This paper proposes a new method of similarity search based on shape representation of time\|series. With the technique of piece\|wise linear representation, a complex time\|series curve is simplified as a group of straight lines. Combining the thought of symbol representation, the concept tree of shapes is constructed, and the method of shape description of time\|series—time\|series representation with cloud model, is presented. Finally, similarity search in time\|series data sets is realized with the enhanced dynamic programming algorithm.