Parameter-lite clustering algorithm based on MST and fuzzy similarity merging

Authors:
Bhupathiraju V. S. Ramakrishnam Raju;Vatsavayi Valli Kumari
Affiliations:
SRKR Engineering College, Bhiamavaram AP, India;Andhra University, Visakhapatnam AP, India
Venue:
Proceedings of the International Conference on Advances in Computing, Communications and Informatics
Year:
2012

Citing 16
Cited 0

Algorithms for clustering data

Algorithms for clustering data
Unsupervised Optimal Fuzzy Clustering

IEEE Transactions on Pattern Analysis and Machine Intelligence
A Validity Measure for Fuzzy Clustering

IEEE Transactions on Pattern Analysis and Machine Intelligence
Data clustering: a review

ACM Computing Surveys (CSUR)
Pattern Recognition with Fuzzy Objective Function Algorithms

Pattern Recognition with Fuzzy Objective Function Algorithms
Approximation algorithms for classification problems with pairwise relationships: metric labeling and Markov random fields

Journal of the ACM (JACM)
Chameleon: Hierarchical Clustering Using Dynamic Modeling

Computer
A new fuzzy-clustering-based approach for two-way circuit partitioning

VLSID '95 Proceedings of the 8th International Conference on VLSI Design
Pattern Classification (2nd Edition)

Pattern Classification (2nd Edition)
Similarity-driven cluster merging method for unsupervised fuzzy clustering

UAI '04 Proceedings of the 20th conference on Uncertainty in artificial intelligence
Clustering with a minimum spanning tree of scale-free-like structure

Pattern Recognition Letters
Minimum Spanning Tree Based Clustering Algorithms

ICTAI '06 Proceedings of the 18th IEEE International Conference on Tools with Artificial Intelligence
Graph-Theoretical Methods for Detecting and Describing Gestalt Clusters

IEEE Transactions on Computers
Robust clustering methods: a unified view

IEEE Transactions on Fuzzy Systems
Fuzzy clustering with volume prototypes and adaptive cluster merging

IEEE Transactions on Fuzzy Systems
Survey: Graph clustering

Computer Science Review

Quantified Score

Hi-index	0.00

Visualization

Abstract

Clustering is an unsupervised process of classifying data items or objects into meaningful groups and each group is called a cluster. There are several algorithms for clustering based on different approaches (hierarchical, partitional, density-based, model-based, etc.). Most of these algorithms have some discrepancies, e.g. the number of the clusters should be a priori known. The present work introduces a novel Parameter-Lite clustering algorithm. The proposed algorithm employs the features of Minimum Spanning Tree (MST) and Fuzzy Similarity Merging to determine the number of clusters automatically. The aim of this combination is to decrease the number of the parameters defined heuristically and there by to decrease the manual intervention of the user on the clustering results. The proposed algorithm initially creates a minimum spanning tree for the given data set. The minimum spanning tree that is created is then divided into sub trees by eliminating the inconsistent edges. The resulting most similar clusters are then merged for optimal number of clusters. The proposed algorithm is tested for both synthetic and real data sets based on the ratio of intra-cluster and inter-cluster distances. The results discussed show that the proposed algorithm performs on par with the Standard K-Means clustering with minimal user intervention.