A cooperative biomimetic approach for high dimensional data mining

Authors:
Lydia Boudjeloud;Hanane Azzag
Affiliations:
Université Paul Verlaine, Metz, France;Institut Galilée, Villtaneuse, France
Venue:
Proceedings of the 13th annual conference companion on Genetic and evolutionary computation
Year:
2011

Citing 2
Cited 0

Graph drawing by force-directed placement

Software—Practice & Experience
Incremental Construction of Neighborhood Graphs Using the Ants Self-Assembly Behavior

ICTAI '07 Proceedings of the 19th IEEE International Conference on Tools with Artificial Intelligence - Volume 01

Quantified Score

Hi-index	0.00

Visualization

Abstract

We propose in this paper an original alternative to solve the problem of search space visualization to discover the complex structure of data, while respecting topology. Our cooperative approach provided a multi-dimensional visualization from the data. The first method is the subspace selection from whole data space. This selection is obtained by a genetic algorithm reducing the data dimension space by simply determining the most relevant dimensions evaluated by a distribution measure. Once a subspace selected we construct a neighborhood graph using artificial ants algorithm.