A GA-based approach for finding appropriate granularity levels of patterns from time series

Abstract

In our previous approach, we proposed an algorithm for finding segments and patterns simultaneously from a given time series. In that approach, because patterns were derived through clustering techniques, the number of clusters was hard to be setting. In other words, the granularity of derived patterns was not taken into consideration. Hence, an approach for deriving appropriate granularity levels of patterns is proposed in this paper. The cut points of a time series are first encoded into a chromosome. Each two adjacent cut points represents a segment. The segments in a chromosome are then divided into groups using the cluster affinity search technique with a similarity matrix and an affinity threshold. With the affinity threshold, patterns with the desired granularity level can be derived. Experiments on a real dataset are also conducted to demonstrate the effectiveness of the proposed approach.