Effective Subsequence Matching in Compressed Time Series

A novel algorithm for querying similar time series was proposed to satisfy the requirement of fitting and indexing time series. The approach first fits time series using two parameters of midline distance and turning points, which is benefit for fast retrieval of similar sequences. After finding similar segmented subsequence by segmented dynamic time warping distance, this method then search this subsequence point by point, by which the subsequence is matched accurately. Experiments show the effectiveness of this technique for fitting and indexing of oil data.