Digital Signal Processing
An elastic net clustering algorithm for non-linearly separable data
ACIIDS'13 Proceedings of the 5th Asian conference on Intelligent Information and Database Systems - Volume Part I
| Hi-index | 0.00 |
This work proposes a new method for data clustering in an n-dimensional space using the Elastic Net Algorithm, which is a variant of the Kohonen topographic map-learning algorithm. The Elastic Net Algorithm is a mechanical metaphor in which an elastic ring is attracted by points in a bi-dimensional space while their internal elastic forces try to shun the elastic expansion. The different weights associated with these two kinds of forces lead the elastic to a gradual expansion in the direction of the bi-dimensional points. In this new method, the Elastic Net Algorithm is employed with the help of a heuristic framework that improves its performance for application in the n-dimensional space of cluster analysis. Tests were made with two types of data sets: (1) simulated data sets with up to 1000 points randomly generated in groups linearly separable with up to dimension 10 and (2) the Fisher Iris Plant database, a well-known database referred in the pattern recognition literature. The advantages of the method presented here are its simplicity, its fast and stable convergence, beyond efficiency in cluster analysis.