Density and entanglement-based clustering of sequence data

Clustering is one of crucial tasks in data processing, and various techniques have been developed for some specific purposes. Sequence data consist of a sequence of data elements each of which has its own predecessor and successor. This paper addresses new clustering methods for sequence data which use the notion of data density and entanglement. The proposed clustering methods weigh the data points based on either their density or entanglement which later affects the location of cluster centroids. The clustering algorithms are extensions of k-means clustering and fuzzy k-means clustering algorithms. Some experiment results are presented to show the behavioral characteristics of the proposed algorithms.