Section: New Software and Platforms

MO-Mine

Scientific Description

MO-Mineclust is the first package of the platform and is dedicated to clustering (unsupervised classification). Indeed, it is well-known that clustering may be seen as a bi-objective optimization problem as the goal is both to minimize distances between data belonging to a same cluster, while maximizing distances between data belonging to different clusters. Several models (objective functions used,...) and engines (optimization algorithms) have been implemented. The framework searches, for a given dataset, the best association of model/engine/parameter without specifiing the number of clusters. MO-Mineclust shows very interesting behavior and shows that the choice of the model and the engine has a great importance in the performance of the method and depends on the dataset to analyze.

Functional Description

MO-Mine is a process of tests and evaluations of multi-objective optimisation algorithms for data mining. MO-Mine platform will provide data sets (literature + synthetics benchmarks), data mining (Features selection, Clustering, Classification and Association rules) algorithms based on multi-objective metaheuristics (Evolutionary algorithm), validation methods and tools to compare algorithms. MO-Mine is based on evolutionary algorithms implemented in ParadisEO and adapted to solve problem of data mining. MO-Mine proposed to users to compare their own methods with different approaches following protocols clearly identified and shared.

• Participants: B. Fisset, L. Jourdan and C. Dhaenens

• Contact: Laetitia Jourdan

• URL: http://mo-mine.gforge.inria.fr/doku.php