Molecular dynamics-like data clustering approach

Authors:
Li Junlin;Fu Hongguang
Affiliations:
School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China;School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China
Venue:
Pattern Recognition
Year:
2011

Citing 9
Cited 3

Algorithms for clustering data

Algorithms for clustering data
Characterization and detection of noise in clustering

Pattern Recognition Letters
Monte Carlo and Molecular Dynamics Simulations Polymer

Monte Carlo and Molecular Dynamics Simulations Polymer
Graph-based hierarchical conceptual clustering

The Journal of Machine Learning Research
Introduction to Data Mining, (First Edition)

Introduction to Data Mining, (First Edition)
A comparative analysis on the bisecting K-means and the PDDP clustering algorithms

Intelligent Data Analysis
Gravitational Fuzzy Clustering

MICAI '08 Proceedings of the 7th Mexican International Conference on Artificial Intelligence: Advances in Artificial Intelligence
Dynamic clustering based on universal gravitation model

MDAI'05 Proceedings of the Second international conference on Modeling Decisions for Artificial Intelligence
Clustering of symbolic objects using gravitational approach

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics

Integration of particle swarm optimization and genetic algorithm for dynamic clustering

Information Sciences: an International Journal
Point set morphological filtering and semantic spatial configuration modeling: Application to microscopic image and bio-structure analysis

Pattern Recognition
PHA: A fast potential-based hierarchical agglomerative clustering method

Pattern Recognition

Quantified Score

Hi-index	0.01

Visualization

Abstract

Based on the molecular kinetic theory, a molecular dynamics-like data clustering approach is proposed in this paper. Clusters are extracted after data points fuse in the iterating space by the dynamical mechanism that is similar to the interacting mechanism between molecules through molecular forces. This approach is to find possible natural clusters without pre-specifying the number of clusters. Compared with 3 other clustering methods (trimmed k-means, JP algorithm and another gravitational model based method), this approach found clusters better than the other 3 methods in the experiments.