Clustering analysis of railway driving missions with niching

Amine Jaafar (1) , Bruno Sareni (1) , Xavier Roboam (1)

1 LAPLACE-GENESYS - Groupe ENergie Electrique et SYStémique

A wide number of applications requires classifying or grouping data into a set of categories or clusters. Most popular clustering techniques to achieve this objective are K-means clustering and hierarchical clustering. However, both of these methods necessitate the a priori setting of the cluster number. In this paper, a clustering method based on the use of a niching genetic algorithm is presented, with the aim of finding the best compromise between the inter-cluster distance maximization and the intra-cluster distance minimization. This method is applied to three clustering benchmarks and to the classification of driving missions for railway applications.

Mots clés: Clustering; K-means; Silhouette index; Niching genetic algorithms; Railway locomotive; Driving missions

Domaines: Energie électrique

Amine Jaafar, Bruno Sareni, Xavier Roboam. Clustering analysis of railway driving missions with niching. COMPEL: The International Journal for Computation and Mathematics in Electrical and Electronic Engineering, 2012, vol. 31, pp.920-931. ⟨10.1108/03321641211209807⟩. ⟨hal-00762266⟩