No abstract

Nous présentons dans ce travail un algorithme de coclustering pour données fonctionnelles. Cet algorithme repose sur le modèle des blocs latents utilisant une modélisation gaussienne des composantes principales fonctionnelles et un algorithme SEM-Gibbs pour l'inférence. Mots-clés. coclustering, données fonctionnelles, algorithme SEM-Gibbs Abstract. A model-based coclustering algorithm for functional data is presented. This algorithm relies on the latent block model using a Gaussian model for the functional principal components and a SEM-Gibbs algorithm for inference.

Cooperative intelligent transport systems (ITS) and connected vehicles are foreseen to change the way mobility is conceived today. Cooperative and connected vehicles will lead to improved road traffic safety and efficiency and will also trigger innovation in the infotainment area. These will foster the design of disruptive new business models for both the telco and automotive industries, triggering a profound impact in society and economy. However, before this can become a reality, many technical challenges still need to be solved. One important challenge relates to the provision of efficient and reliable vehicleto-anything (V2X) communications for the vehicles. The new emerging generation of mobile communications, the so-called 5G technology, is aimed at giving an answer to this challenge. Among other coordinated efforts, the European-funded 5GCAR project is looking into such V2X technology components and enablers. This paper aims at presenting and describing the technologies that are being considered in 5GCAR to make the vision of the cooperative and connected vehicle a reality.

In order to help the network maintainers with the daily diagnosis and optimization tasks, a supervised model for mobile anomalies prevention is proposed. The objective is to detect future malfunctions of a set of cells, by only observing key performance indicators that are considered as functional data. Thus, by alerting the engineers as well as self-organizing networks, mobile operators can be saved from a certain performance degradation. The model has proven its efficiency with an application on real data that aims to detect capacity degradation, accessibility and call drops anomalies for LTE networks.

No abstract