Pr. Carlos Tavares Calafate

Bio
Talk title

UAV solutions based on wireless communications

Talk summary

In this talk an introduction to unmanned aerial vehicles will be made, detailing their operation, main uses, and main research challenges. Next, different applications and systems developed in our research group will be discussed, showing how wireless communications can be used to achieve advanced features such as swarm creation and collision avoidance.

Pr. Antonio Skarmeta

Bio
Talk title

Advanced IoT Platform based solution for Smart Infrastructure

Talk summary

This talk will review the basic concepts of how IoT provide advanced solutions for data management based on open platform for data integration and interoperability.  Solution for different scenarios like smart building, smart agriculture and smart cities will be described. This talk will review also the basic concepts of securing communications proposal for Internet of Things (IoT) and impact of new 5G networks.

Pr. Yamine AIT AMEUR

Bio
Talk title

Formal modelling of discrete and continuous behaviours in hybrid systems

Talk summary

Hybrid systems consist of a discrete part interacting with a continuous, physical environment. Due to this dual nature, the verification of such systems is complex; it requires the capability to handle and to reason on continuous objects such as functions and differential equations for modelling the physical part, in addition to the usual discrete objects for the controller part.
This talk discusses a formal modelling approach of such systems. This approach is state based and relies on refinement and proof. We show how the development of hybrid systems can be conducted within the Event-B formal method and its integrated development environment Rodin. Examples of such developments are presented as well. We finally explicit some future research paths targeting better support such developments.

Pr. Smail Niar

Bio
Talk title

Embedded System Architecture Optimizations
for Machine Learning Based Autonomous Vehicles

Talk summary

The transportation industry (automotive, railway and avionics) continues to look for ways to reduce the fatalities and the severity of accidents. Autonomous driving (AD) not only reduces the number of accidents, but offers also a better use of road infrastructures and may protect the environment. However, AD comes with inherent challenges. Specifically, many of the actions taken by the autonomous vehicle are based on increasingly complex algorithms, mainly applied from the artificial intelligence (AI) domain such as deep neural networks (DNN). These algorithms are known for their greed of computing and memory resources.
In this presentation, I will talk about projects we are developing at Université Polytechnique Hauts-de-France in the design of optimized embedded systems for highly complex AD functionalities.  The use of techniques such approximate computing, dynamic and partial reconfiguration and hierarchical cloud/fog/edge platforms will be explored. 

Dr. Soror Sahri

Bio
Talk title

Quality assessment of big datasets

Talk summary

Data quality issues trace back their origin to the early days of computing. Data quality issues include inaccurate, imprecise, incomplete, inconsistent or uncertain data. The existing solutions to assess and improve the quality of data primarily target relational data and data warehouses. The recent emergence of big data and renaissance in machine learning necessitates evaluating the suitability of existing approaches to data quality. In this talk, we review different data quality issues, and their measurement attributes, known as quality dimensions. We review existing solutions and present ours to assess quality while efficiently handling the characteristics of big and distributed datasets. Examples and use cases will highlight the solutions.