• Visualisation de l'information adaptée au monitoring d'un processus industriel. Elodie Toufaili, Youssef Miloudi, Christophe Bortolaso
• Visualisation Node-RED des données sémantiques des capteurs de bâtiments. Ghislain Atemezing, Yann Gripay, Sylvie Servigne, Frédérique Laforest
• discussion

• WildCount : Inexpensive Edge sensor for recognizing and counting the presence of humans (anonymous) and animals into wild and protected areas. Didier Donsez
• Approches légères pour une solution de maison intelligente pour personnes âgées. Sara Kebir, Cécile Carra, Karim Tabia
• Gestion prédictive embarquée et frugale pour le bâtiment intelligent. Louis Closson
• Projet de Jumeau Numérique du bâtiment Espace Fauriel de Mines Saint-Etienne. Maxime Lefrançois
• discussion

• Détecter des situations médicales d’importance en utilisant le Stream Reasoning sur des données issues de l’IoT. Mathieu Bourgais, Franco Giustozzi, Laurent Vercouter
• Développement de nouvelles stratégies de monitoring grâce à une approche Massive IoT. Gwen Maudet, Mireille Batton-Hubert, Patrick Maille, Laurent Toutain
• discussion

• Un langage dédié au domaine du Web Sémantique des objets contraints. Fatma-Zohra Hannou
• LiRoT : un raisonneur incrémental léger pour le Web des Objets. Alexandre Bento, Lionel Médini, Kamal Singh, Frédérique Laforest
• Une plateforme d'apprentissage fédéré pour IoT : Application à l'industrie 4.0. Hamza Safri, Mohamed Mehdi Kandi, Youssef Miloudi, Christophe Bortolaso, Denis Trystram, Frédéric Desprez
• Détection d'intrusions fédérée et semi-supervisée pour l'IoT. Ons Aouedi, Kandaraj Piamrat, Guillaume Muller, Kamal Singh
• discussion

The on-going process of softwarization of IT networks promises to reduce the operational and management costs of network infrastructures by replacing hardware middleboxes with equivalent pieces of code executed on general-purpose servers. Alongside the benefits from the operator's perspective, new strategies to provide the network's resources to users are arising. Following the principle of "everything as a service", multiple tenants can access the required resources -- typically CPUs, NICs, or RAM -- according to a Service-Level Agreement. However, tenants' applications may require a complex and expensive measurement infrastructure to continuously monitor the network function's state. This may limit the feasibility of AI-enhanced systems. Although the application's specific behavior is unknown (and often opaque to the infrastructure owner), the software nature of (virtual) network functions (VNFs) may be the key to infer the behavior of the high-level functions by accessing low-level information, which is still under the control of the operating system and therefore of the infrastructure owner. As such, in the scenario of software VNFs executed on COTS servers, the underlying CPU's behavior can be used as the sole predictor for the high-level VNF state without explicit in-network measurements. This novel methodology can be applied to infer high-level characteristics such as throughput or packet loss using CPU data instead of network measurements. In this presentation, we show our experimental analysis of the behavior of a CPU that executes a VNF under different loads, how to correlate such data with the high-level application state, and use this knowledge to detect some network metrics.