International audience

Despite the enormous data processing capacity available in big data frameworks, obtaining appropriate and private responses to large-scale queries without revealing sensitive information is still a challenging problem. In this paper, we address the problem of combining offline sampling techniques for space efficiency in multidimensional databases and Differential Privacy (DP) to protect sensitive data. We present our framework SLIM-View, which uses a novel sampling technique relying on a bi-objective optimization to decide the best sample size and the exponential mechanism to select the best sample while ensuring privacy. Our extensive experiments demonstrate that SLIM-View outperforms existing approaches by orders of magnitude in terms of utility and scalability while ensuring the same level of privacy.

Emergency is an essential mission of public hospitals, one of its main features is to meet requirements expected by the population, whatever their nature. This work proposes a fog-based architecture integrating intelligent algorithms; based on machine learning models, to improve the emergency department performance and the patient experience. The proposed architecture effectiveness is ensured via the fog infrastructure where interactions between the smart scheduling system; deployed on the cloud, and the doctors are maintained. To ensure the efficiency property, we adopt machine learning algorithms to assign and classify patients with regards to the urgency of their cases, their waiting time and physician's availability.