The main objective of the project is to propose a novel approach of distributed, scalable, dynamic and energy efficient algorithms for managing resources in a mobile network. This new approach relies on the design of an orchestration mechanism of a portfolio of algorithms. The ultimate goal of the proposed mechanism is to enhance the user experience, while at the same time to better utilize the operator resources. User mobility and new services are key elements to take into account if the operator wants to improve the user quality of experience. Future autonomous network management and control algorithms will thus have to deal with a real-time dynamicity due to user mobility and to traffic variations resulting from various usages. To achieve this goal, we focus on two central aspects of mobile networks and intend to design distributed learning mechanisms in non-stationary environments, as well as an orchestration mechanism that applies the best algorithms depending on the situation. The first main aspect to be addressed is the management of radio resources at the RAN (Radio Access Network) level. In current (LTE) and future (LTE-A) cellular systems, interference appears as a bottleneck for providing high data rates and seamless connectivity to the end-user. To reduce interference it is possible either to coordinate the transmissions of neighboring base stations (BS) so as to avoid simultaneous transmissions on the same radio resources or to allow BSs to cooperate: two or more BSs combine their transmissions towards a single user in order to increase its data rate. Both cases require distributed learning algorithms. The second aspect is the management of the popular contents users want to get access to. In a Content Delivery Network (CDN), popular content is disseminated and stored in cache servers as close as possible to the demand to avoid delay in access. How to place servers in the network and replicated contents in the servers are traditional issues in CDNs. In mobile CDNs, things are exacerbated because of the changing and unpredictable environment characterized by spatial and temporal changes in the traffic demand, user mobility and variable channel conditions. The way the project intends to tackle these problems is based on a “learn to learn approach”. If we think about BSs and cache servers as autonomous entities seeking to optimize a global objective function and able to take decisions based on incomplete information, the notion of distributed learning arises naturally. There are numerous approaches along these lines and each mechanism has its own characteristics in terms of needed information, type of achieved equilibrium, convergence speed, and stability. Each mechanism can also be tuned thanks via an array of parameters. The problem is exacerbated in non-stationary situations due to mobility, traffic demand or radio channel variations. The originality of the project thus lies in its objective of building a portfolio of distributed learning algorithms that are then to be orchestrated. To account for learning in the presence of non-stationary processes, we intend to use the theory of stochastic approximation in order to develop robust versions of existing learning schemes. Orchestrating a portfolio of learning algorithms is, in many regards, similar to the literature on “learning with expert advice”, so our goal will be to devise adaptive learning schemes that select dynamically between different learning schemes so that their long-term learning power exceeds the regret of any individual “expert”. Bringing together experts form both network and learning, NETLEARN ultimately intends to propose architecture and protocol adaptations for implementing our resource management algorithms.

The research interest for people faces identification, as part of judicial investigations, is well established and remains one of the key elements of success. However, the technologies used in uncontrolled conditions of shooting are still in their early stages of development and have yet to be improved and validated in real live test in order to make them fully operational. Given some recent progress, the recognition task is difficult because face images extracted from video-protection systems are poorly resolved, poorly lit and variably oriented. The PHYSIONOMIE project proposes to develop new tools of physiognomic recognition by: • improving the images of inquiry (pictures or video clips), • exploiting 3D face models to change the orientation of sought faces and then obtaining images with comparable exposures, • defining new similarity measures on partially comparable data (query and reference images are of different nature, presence of expression, occlusion, ...). The accuracy of biometric recognition algorithms depends on the quality of image acquisition and its overall performance depends greatly on the database size used. The creation of a 3D face images database of significant size would require a substantial time. Thus, PHYSIONOMIE will develop tools to build 3D face image models from anthropometric pictures. The validation of this approach will be done through 3D face models produced from low cost sensors such as stereoscopic smartphones, Kinect sensors, etc.., on face pictures acquired during the project. Physiognomic recognition tools will provide as a result a face list ranked in order of relevance, with the sought face that does not always appear at the first rank. Therefore, in PHYSIONOMIE, we propose to incorporate within the demonstrator intuitive and ergonomic capabilities of visual search to navigate through the results list. We will use the new similarity measures as well as soft biometrics (eye colour, presence of scars / tattoos ...) to navigate through the global database from one or more faces of the list returned. End-users, partners of the project, are willing to test and evaluate these tools. In this context, the project will measure the tool potential and will aim to evolve the similarity measure technologies for forensic identification. It will adapt the technology to operational needs, will specify the conditions of use and will measure the gain in efficiency. The possible deployment of a tool with PHYSIONOMIE features in operational services cannot be done without studying the societal acceptability of this technology and the project will conduct a qualitative and quantitative study in this area. Its findings will complement the technology and deployment roadmap, and will specify the contexts of use that are acceptable to society.