Open AccessA Novel Spectral Clustering based on Local Distribution
Author(s) -
Jyotsna Kumar Mandal,
Parthajit Roy
Publication year - 2015
Publication title -
international journal of electrical and computer engineering
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.277
H-Index - 22
ISSN - 2088-8708
DOI - 10.11591/ijece.v5i2.pp361-370
Subject(s) - mahalanobis distance , cluster analysis , spectral clustering , computer science , outlier , data mining , benchmark (surveying) , metric (unit) , laplacian matrix , pattern recognition (psychology) , correlation clustering , artificial intelligence , exploit , graph , geography , theoretical computer science , cartography , engineering , operations management , computer security
This paper proposed a novel variation of spectral clustering model based on a novel affinitymetric that considers the distribution of the neighboring points to learn the underlayingstructures in the data set. Proposed affinity metric is calculated using Mahalanobis distancethat exploits the concept of outlier detection for identifying the neighborhoods of the datapoints. RandomWalk Laplacian of the representative graph and its spectra has been consideredfor the clustering purpose and the first k number of eigenvectors have been consideredin the second phase of clustering. The model has been tested with benchmark data and thequality of the output of the proposed model has been tested in various clustering indicesscales.