6^th International Conference
on Networking and Advanced Systems
ICNAS'23

Prof. Sadok BEN YAHIA

Position: Full Professor at the Technology University of Tallinn (TalTech)

Short Bio: Prof. Sadok BEN YAHIA obtained his HDR in Computer Sciences from the University of Montpellier (France) in April 2009 and since January 2019. He is the head of the Data Science Group in the IT School, and his research interests mainly focus on data-driven approaches for near-real-time Big Data analytics, e.g., urban mobility in smart cities (e.g., information aggregation and dissemination, traffic congestion prediction), Recommendation System, and fake content fighting.

Title: Data-Driven Approaches for Resilient and Sustainable Urban Mobility

Abstract: The transportation sector is responsible for 23% of energy-related CO2 emissions. Decarbonizing transportation is challenging, as it is still 92% dependent on non-renewable resources. However, current transport decarbonization-related policies are insufficient to decrease CO2 emissions to the expected level. Therefore, strategic approaches to reducing emissions from urban transport are critical to addressing the challenges of climate change. In this talk, we present our recent research activities on a framework to build the next level of innovative data-driven traffic light strategies as the most impactful action to reduce CO2 emissions within the context of urban mobility for Connected and Autonomous Cars. This Framework is committed to embracing the next generation of Edge-AI, benefiting from the ease of implementation and increased computation power toward more composable, distributed, and federated intelligence, as well as security by design frameworks. Powerful eye-bird-view multimodal data fusion approaches feed AI models for accurate CO2 and urban noise level predictions, that feed to dashboards for awareness purposes. Advanced reinforcement learning techniques make use of urban noise predictions to implement the best traffic light strategy in real time. We will also discuss the challenges to achieve resilience by proactively detecting misbehaving entities within Vehicle-to-Everything settings

Prof. Kadi BOUATOUCH

Position: Emeritus Professor IRISA, University of Rennes 1 PERCEPT group

Short Bio: Prof. Kadi BOUATOUCH is an electronics and automatic systems engineer (ENSEM 1974, France). He was awarded a PhD in 1977 (University of Nancy 1, France) and a higher doctorate in computer science in the field of computer graphics in 1989 (University of Rennes 1, France). He is working on global illumination, lighting simulation for complex environments, GPU based rendering and computer vision. He is currently Emeritus Professor at the university of Rennes 1 (France) and researcher at IRISA Rennes (Institut de Recherche en Informatique et Systèmes Aléatoires). He was the head of the FRVSense team within IRISA until September 2017. He is member of Eurographics and was member of ACM and IEEE. He was/is member of the program committee of several conferences and workshops and referee for several Computer Graphics journals such as: The Visual Computer, ACM Trans. On Graphics, IEEE Computer Graphics and Applications, IEEE Trans. On Visualization and Computer Graphics, IEEE Trans. On image processing, etc. He acted as a referee for many conferences and workshops. He served as a chair/committee member/reporter for several PhD theses or higher doctorates in France and abroad (USA, UK, Belgium, Cyprus, The Netherlands, Spain, etc.). He was associate editor for the Visual Computer Journal. He is now General Chair of the VISIGRAPP Conference

Title: Stochastic Approach to realistic rendering in computer graphics for Virtual Reality (VR)

Abstract: In Virtual Reality, it is important to make the rendering of images displayed on an HMD headset as realistic as possible. In this case, it is a question of taking into account the multiple reflections, refractions and diffusions using stochastic methods (Monte Carlo, Gaussian processes, etc.) or AI (CNN neural networks). These methods can be used in other fields such as vision, crowd simulation, etc. This Keynote Lecture begins by introducing the different processing necessary for obtaining a computer-generated image such as: geometric modeling, camera parameters, color, photometric quantities, etc. Then it presents in detail the various stochastic rendering methods allowing the generation of synthetic images with a high level of realism. Among these methods we can cite: the Monte Carlo method, Bayesian Monte Carlo, Metropolis, spectral Analysis of Quadrature Rules and Fourier Truncation-based Methods Applied to the Shading Integral, etc. This lecture will be illustrated with realistic images generated with different rendering methods.

Prof. Samir OTMANE

Position: Full professor in computer science at the University of Evry, Paris-Saclay

Short Bio: Prof. Samir OTMANE is a full professor in computer science at the University of Evry, Paris- Saclay since 2011. He heads the IRA2 team (Interaction, Virtual & Augmented Reality, Ambient Robotics) of IBISC laboratory. He graduated in computer engineering from the University of Titzi-Ouzou (UMMTO) in 1992. Fascinated by research in virtual reality and robotics, he completed a M.S. degree in Robotics at the Université Pierre et Marie Curie (Paris VI) in 1996 and the Ph.D. degree in robotics from the University of Evry Val d'Essonne in 2000. This Ph.D. research gave rise to the first French system for augmented reality teleoperation via the Internet (ARITI project in 1999, referenced by the NASA Space Telerobotics Program until 2010). He was Vice-President of the Evry University in charge of enterprise relations from 2014 to 2023. He was a director of AFRV (Association Française de Réalité Virtuelle, augmentée et de l'interaction 3D) until 2016 and co-chair of Laval Virtual between 2010 and 2016. He is author/co-author of over 100 scientific publications (including conferences and journals) and has participated in several research projects (regional, national, and European) on virtual/augmented reality (VR/AR) and robotics. His current research focuses on how VR and AR can provide new solutions for healthcare area such as functional rehabilitation, medical and paramedical training, etc.

Title: Virtual & augmented reality for medical training and rehabilitation (VR)

Abstract: Virtual and augmented reality technologies offer opportunities to create training and rehabilitation tools in virtual or augmented environments, giving users a first-person experience. Designing such systems requires defining the most critical components to be simulated, and to what degree they can be successfully simulated, considering the context of their use and the effectiveness of interactions. There are several research questions to which we have provided answers, including: How can the user be represented in the virtual environment, and what is the added value of this representation for medical training purposes? How can interaction fidelity impact user performance in surgical simulation-based training? What is the impact of augmented reality feedback on the performance of a patient's gait rehabilitation process?.

In addition, I will present two rehabilitation assistance systems for improving patient usability and motivation: 1) for upper limb motor rehabilitation after stroke in virtual reality; 2) gait rehabilitation in augmented reality.