We have three seminars on May 28, 2021, on Teams. More details below. If interested to join, please drop an email to seccis AT cnam DOT fr.
14h – 14h45 : Maria Isabella Viola
Titre : What is the relationship between cellular user mobility and COVID-19 spreading ?
Abstract: We present preliminary results on the impact that cellular user mobility has had on COVID-19 spreading. By analyzing spatially and temporally aggregated anonymized cellular mobility information, we could detect a correlation between human mobility (in normal conditions, in the first semester of 2019) and covid-19 spreading (at the beginning of the outbreak in 2020 and then in 2021, first semesters). Preliminary results show the correlation as well as the impact of the different government measures (lockdown, inter-region travel ban, 10km travel ban, curfew).
Bio : Maria Isabella Viola was born in Piacenza, Italy in 1996. She obtained a biomedical engineering bachelor at Politecnico di Milano in 2018, and then enrolled in a master of science in mathematical engineering at Politecnico di Milano, with a specialization in applied statistics, and an expected graduation in 2021. Her current thesis work at Cnam is about qualifying the correlation between COVID-19 spreading and human mobility under the advisory of Françoise Sailhan and Stefano Secci.
14h45 – 15h30 : Salah Bin-Ruba
Titre : A survey on Federated Learning (FL)
Federated Learning (FL) is a distributed ML paradigm where a number of devices are collectively participate in training global ML models locally under the orchestration of a central server. Each device’s data is stored locally and not exchanged or transferred, instead only model parameters are updated for aggregation.
Training in heterogeneous and potentially massive networks introduces novel challenges that must be addressed in a different fashion than those of standard machine learning approached. Such challenges are communication bottlenecks, statistical and systems heterogeneity, privacy and security preservations. A number of solutions and algorithmic are proposed in the state of the art to overcome such challenges.
In our presentation, we shall discuss what FL is and how is implemented, talking in more details about FL baseline algorithm called federated averaging (FedAvg). We will also look at the challenges facing FL and what solutions are provided to mitigate them.
Bio : Salah Bin-Ruba is a researcher at Conservatoire National des Arts et Métiers (CNAM), CEDRIC lab. He has a Master degree in Data Science and network intelligence from Telecom SudParis (France) and an MSc in Distributed Interactive Systems from Lancaster university (UK), where he also obtained a BSc in computer science. His research interests lie in the field of data-driven networks, with current focus on edge computing in beyond 5G Networks.
15h30 – 16h : Rahim Haiahem
Titre : LoRaWAN and air-quality surveillance
High accuracy air pollution monitoring in a smart city requires the deployment of a huge number of sensors in this city. One of the most appropriate wireless technologies expected to support high-density deployment is LoRaWAN which belongs to the Low Power Wide Area Network (LPWAN) family and offers a long communication range, multi-year battery lifetime, and low-cost end devices. It has been designed for End Devices (EDs) and applications that need to send small amounts of data a few times per hour. However, a high number of end devices breaks the orthogonality of LoRaWAN transmissions, which was one of the main advantages of LoRaWAN. Hence, network performances are strongly impacted. To solve this problem, we propose a set of solutions that ensure the orthogonality of LoRaWAN transmissions and provides accurate air pollution monitoring. We show how to organize EDs into clusters and sub-clusters, assign transmission times to EDs, configure and synchronize them, taking into account the specificities of LoRaWAN and the features of the air pollution monitoring application.
Bio : Rahim Haiahem is a PhD Student at the National School of Computer Science (ENSI), at The University of Manouba, in Tunisia. He received the Licence and Master degrees in Computer Science from the universities of 08 mai 1995 Guelma and UBMA Annaba, Algeria, respectively. His research interests include vehicular communications, wireless and mobile networks, smart city monitoring and Internet of Things.