This paper presents the R package HDclassif which is devoted to the clustering and the discriminant analysis of high-dimensional data. The classification methods proposed in the package result from a new parametrization of the Gaussian mixture model which combines the idea of dimension reduction and model constraints on the covariance matrices. The supervised classification method using this parametrization is called high dimensional discriminant analysis (HDDA). In a similar manner, the associated clustering method is called high dimensional data clustering (HDDC) and uses the expectation-maximization algorithm for inference. In order to correctly fit the data, both methods estimate the specific subspace and the intrinsic dimension of the groups. Due to the constraints on the covariance matrices, the number of parameters to estimate is significantly lower than other model-based methods and this allows the methods to be stable and efficient in high dimensions. Two introductory examples illustrated with R codes allow the user to discover the hdda and hddc functions. Experiments on simulated and real datasets also compare HDDC and HDDA with existing classification methods on high-dimensional datasets. HDclassif is a free software and distributed under the general public license, as part of the R software project.

Le rôle de la proximité de réseau dans la géographie des collaborations scientifiques Résumé

This paper aims at introducing a novel measure of regional centrality in the context of R&D networks. We first demonstrate some substantial problems of SNA-based centrality measures to cope with regional R&D networks in a meaningful way. Then, we introduce a new measurement approach of regional network centrality based on the concept of interregional bridging paths (indirect connections at the regional level). We show that the formal definition of our regional bridging centrality measure can be expressed in terms of three simple components: the participation intensity of a region in interregional R&D collaborations, the relative outward orientation in terms of all established links and the diversification of R&D collaborations among partner regions. We illustrate the measure and its behaviour with respect to other conventional centrality measures by using the example of the European co-patent network at the NUTS2 level. * The authors thank the three anonymous referees for providing helpful comments. Laurent Bergé gratefully acknowledges the financial support of the French region of Aquitaine (Conseil Régional d'Aquitaine) for the research project REGNET (Grant #20101402006).