Publication Date
Fall 2012
Degree Type
Master's Project
Degree Name
Master of Science (MS)
Department
Computer Science
Abstract
Over the past several decades, clustering algorithms have earned their place as a go-to solution for database mining. This paper introduces a new concept which is used to develop a new recursive version of DBSCAN that can successfully perform hierarchical clustering, called Level- Set Clustering (LSC). A level-set is a subset of points of a data-set whose densities are greater than some threshold, ‘t’. By graphing the size of each level-set against its respective ‘t,’ indents are produced in the line graph which correspond to clusters in the data-set, as the points in a cluster have very similar densities. This new algorithm is able to produce the clustering result with the same O(n log n) time complexity as DBSCAN and OPTICS, while catching clusters the others missed.
Recommended Citation
Indaco, Francesco, "HIERARCHICAL CLUSTERING USING LEVEL SETS" (2012). Master's Projects. 346.
DOI: https://doi.org/10.31979/etd.53ab-z6nq
https://scholarworks.sjsu.edu/etd_projects/346
