Fast and Accurate Spectral Clustering Based KNN-Similarity Graph Analysis

Apply

Fast and Accurate Spectral Clustering Based KNN-Similarity Graph Analysis

Journal Title: International Journal for Research in Applied Science and Engineering Technology (IJRASET) - Year 2016, Vol 4, Issue 1

Abstract

The recent years as an important analytical technique, both due to the prevalence of graph data, and the usefulness of graph structures for exploiting intrinsic data characteristics. However, as graph data grows in scale, it becomes increasingly more challenging to identify clusters. The propose an efficient clustering algorithm for large scale data using spectral methods. Finding clusters in data is a challenging task when the clusters differ widely in shapes, sizes, and densities. The proposed system present a novel spectral algorithm with a similarity measure based on modified nearest neighbor graph. The resulting affinity matrix reflexes the true structure of data. Its eigenvectors, that do not change their sign, are used for clustering data. The algorithm requires only one parameter a number of nearest neighbors, which can be quite easily established. Its performance on both synthetic and real data sets is competitive to other solutions.

Authors and Affiliations

S. Shanmugaprabha, R. Sekar

Keywords

Replacement of Synthetic Fiber with Eco Friendly Natural Fiber As Rein Forcement in Composite Materials and Compare Their Properties

Polymers are serving to a maximum extent, but they are also posing environmental problems due to their nonjudicious usage. The main problem with most of the polymers is their non- degradable nature which can pollute the...

EP ID EP21575
DOI -
Views 199
Downloads 3