Selective Subsequence Time Series clustering

摘要

Subsequence Time Series (STS) Clustering is a time series mining task used to discover clusters of interesting subsequences in time series data. Many research works had used this algorithm as a subroutine in rule discovery, indexing, classification and anomaly detection. Unfortunately, recent work has demonstrated that almost all of the STS clustering algorithms give meaningless results, as their outputs are always produced in sine wave form, and do not associate with actual patterns of the input data. Consequently, algorithms that use the results from the STS clustering as their input will fail to produce its meaningful output. In this work, we propose a new STS clustering framework for time series data called Selective Subsequence Time Series (SSTS) clustering which provides meaningful results by using an idea of data encoding to cluster only essential subsequences. Furthermore, our algorithm also automatically determines an appropriate number of clusters without user’s intervention.