Dans ce travail de thèse, nous présentons une méthode originale s’inspirant des comportements des fourmis réelles pour la résolution de problème de classification non supervisée non hiérarchique. Cette approche créée dynamiquement des groupes de données. Elle est basée sur le concept des fourmis artificielles qui se déplacent en même temps de manière complexe avec les règles de localisation simples. Chaque fourmi représente une donnée dans l’algorithme. Les mouvements des fourmis visent à créer des groupes homogènes de données qui évoluent ensemble dans une structure de graphe. Nous proposons également une méthode de construction incrémentale de graphes de voisinage par des fourmis artificielles. Nous proposons deux méthodes qui se dérivent...
L'un des objectifs de la classification est d'expliciter les relations entre éléments et classes. Le...
International audienceWe present an incremental algorithm for building a neighborhood graph from a s...
In this paper is presented a new model for data clustering, which is inspired from the self-assembly...
Dans ce travail de thèse, nous présentons une méthode originale s’inspirant des comportements des fo...
In this work, we present a novel method based on behavior of real ants for solving unsupervised non-...
International audienceIn this paper we present a summary of our work which has proposed a new model ...
International audienceAs an important technique for data mining, clustering often consists in formin...
In this thesis, we present works inspired by real ants for the resolution of well known problems in ...
In this work we present a new clustering algrorithm for hierarchical clustering. It is inspired from...
Nous nous intéressons dans cette thèse à la résolution d'un problème de classification non supervisé...
In this paper we will present a new clustering algorithm for unsupervised learning. It is inspired f...
In this thesis, we develop a new clustering approach inspired from the chemical recognition system o...
The clustering algorithms have evolved over the last decade. With the continuous success of natural ...
International audienceIn this paper is presented a new model for data clustering, which is inspired ...
International audienceIn this paper we present a new incremental algorithm for building neighborhood...
L'un des objectifs de la classification est d'expliciter les relations entre éléments et classes. Le...
International audienceWe present an incremental algorithm for building a neighborhood graph from a s...
In this paper is presented a new model for data clustering, which is inspired from the self-assembly...
Dans ce travail de thèse, nous présentons une méthode originale s’inspirant des comportements des fo...
In this work, we present a novel method based on behavior of real ants for solving unsupervised non-...
International audienceIn this paper we present a summary of our work which has proposed a new model ...
International audienceAs an important technique for data mining, clustering often consists in formin...
In this thesis, we present works inspired by real ants for the resolution of well known problems in ...
In this work we present a new clustering algrorithm for hierarchical clustering. It is inspired from...
Nous nous intéressons dans cette thèse à la résolution d'un problème de classification non supervisé...
In this paper we will present a new clustering algorithm for unsupervised learning. It is inspired f...
In this thesis, we develop a new clustering approach inspired from the chemical recognition system o...
The clustering algorithms have evolved over the last decade. With the continuous success of natural ...
International audienceIn this paper is presented a new model for data clustering, which is inspired ...
International audienceIn this paper we present a new incremental algorithm for building neighborhood...
L'un des objectifs de la classification est d'expliciter les relations entre éléments et classes. Le...
International audienceWe present an incremental algorithm for building a neighborhood graph from a s...
In this paper is presented a new model for data clustering, which is inspired from the self-assembly...