Fouille visuelle et classification de données par nuage d'insectes volants

RESUME. Nous presentons dans cet article un nouvel algorithme biomimetique permettant de creer des groupes au sein de donnees et de les visualiser dynamiquement. Cet algorithme s’inspire des insectes volants se deplacant en nuage en creant des mouvements complexes a partir de regles locales simples. Chaque insecte represente une donnee. Le deplacement des insectes vise a creer des groupes de donnees homogenes se deplacant ensemble dans un espace a deux dimensions. Les groupes crees et visualises en temps reel informent l’expert du domaine qui a fourni les donnees sur leur structuration en classe, par exemple, le nombre de classes plausible, le regroupement de donnees similaires, et les donnees isolees representant des cas « a part ». Nous presentons des extensions de l’algorithme comme la diminution du temps de calcul ou l’utilisation d’un affichage 3D. L’approche est etudiee sur des donnees artificielles et reelles. Un algorithme heuristique permet d’evaluer la pertinence des partitionnements trouves.

[1]  W ReynoldsCraig Flocks, herds and schools: A distributed behavioral model , 1987 .

[2]  N. Monmarche,et al.  Interactive mining of multimedia databases with virtual reality , 2003, International Conference On Virtual Reality and Its Applications in Industry.

[3]  Gregor von Laszewski,et al.  Intelligent Structural Operators for the k-way Graph Partitioning Problem , 1991, ICGA.

[4]  Rita Cucchiara,et al.  Analysis and Comparison of different Genetic Models for the Clustering problem in Image Analysis , 1993 .

[5]  J. Michael Davis The coordinated aerobatics of dunlin flocks , 1980, Animal Behaviour.

[6]  Nicolas Monmarché,et al.  On Improving Clustering in Numerical Databases with Artificial Ants , 1999, ECAL.

[7]  Anil K. Jain,et al.  Algorithms for Clustering Data , 1988 .

[8]  Peter L. Brooks,et al.  Visualizing data , 1997 .

[9]  J. M. Davis,et al.  Socially induced flight reactions in pigeons , 1975, Animal Behaviour.

[10]  Denyse Baillargeon,et al.  Bibliographie , 1929 .

[11]  Guy Theraulaz,et al.  Self-Organization in Biological Systems , 2001, Princeton studies in complexity.

[12]  Baldo Faieta,et al.  Diversity and adaptation in populations of clustering ants , 1994 .

[13]  Craig W. Reynolds,et al.  A Distributed Behavioral Model , 1987 .

[14]  I. Aoki Experimental and theoretical studies on schooling in fish. II. Internal dynamics of fish schools in relation to inter-fish distance. , 1984 .

[15]  Barbara Webb,et al.  Swarm Intelligence: From Natural to Artificial Systems , 2002, Connect. Sci..

[16]  Nicolas Monmarché,et al.  Algorithmes de fourmis artificielles : applications à la classification et à l'optimisation. (Artificial ant based algorithms applied to clustering and optimization problems) , 2000 .

[17]  Pak Chung Wong,et al.  30 Years of Multidimensional Multivariate Visualization , 1994, Scientific Visualization.

[18]  Hans-Peter Kriegel,et al.  Visualization Techniques for Mining Large Databases: A Comparison , 1996, IEEE Trans. Knowl. Data Eng..

[19]  Emanuel Falkenauer,et al.  A New Representation and Operators for Genetic Algorithms Applied to Grouping Problems , 1994, Evolutionary Computation.

[20]  Edward J. Wegman,et al.  Immersive Methods for Exploratory Analysis , 1998 .

[21]  William S. Cleveland,et al.  Visualizing Data , 1993 .

[22]  Marco Dorigo,et al.  Swarm intelligence: from natural to artificial systems , 1999 .

[23]  Chris Winter,et al.  Information Flocking: Data Visualisation in Virtual Worlds Using Emergent Behaviours , 1998, Virtual Worlds.

[24]  Lashon B. Booker,et al.  Proceedings of the fourth international conference on Genetic algorithms , 1991 .

[25]  Donald R. Jones,et al.  Solving Partitioning Problems with Genetic Algorithms , 1991, International Conference on Genetic Algorithms.