This paper focus on multiple CNN-based (Convolutional Neural Network) models for COVID-19 forecast developed by our research team during the first French lockdown. In an effort to understand and predict both the epidemic evolution and the impacts of this disease, we conceived models for multiple indicators: daily or cumulative confirmed cases, hospitalizations, hospitalizations with artificial ventilation, recoveries, and deaths. In spite of the limited data available when the lockdown was declared, we achieved good short-term performances at the national level with a classical CNN for hospitalizations, leading to its integration into a hospitalizations surveillance tool after the lockdown ended. Also, A Temporal Convolutional Network with quantile regression successfully predicted multiple COVID-19 indicators at the national level by using data available at different scales (worldwide, national, regional). The accuracy of the regional predictions was improved by using a hierarchical pre-training scheme, and an efficient parallel implementation allows for quick training of multiple regional models. The resulting set of models represent a powerful tool for short-term COVID-19 forecasting at different geographical scales, complementing the toolboxes used by health organizations in France.
International audiencePervasive Information System (PIS) provides a new vision of Information System available anytime and anywhere. The users of these systems must evolve in a space of services, in which several services are offered to him. However, PIS should enhance the transparency and efficiency of the system. We believe that a user-centric vision is needed to ensure a transparent access to the frequently changing space of services regardless of how to perform it. In this paper, we propose a new approach of PIS, both context-aware and intentional called IPIS. In this approach, services are proposed in order to satisfy user's intention in a given context. Then, we propose a context-aware intentional service discovery mechanism. Such mechanism is based on an extension of OWL-S taking into account the notion of context and intention. We present in this paper IPIS platform. Then, we detail the proposed service discovery mechanism and present experimental results that demonstrate the advantage of using our proposition
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.