The main objective of this research project is to identify recurring patterns related to the spread of false information. Our unique approach is based on French data, by combining different sources of information, namely online press articles and Twitter posts. The first part of the thesis focuses on the creation and validation of this dataset by conducting exhaustive statistical analyses, and comparing these results with those of the Anglo-Saxon literature. This will allow us to provide the decisive elements for Fake News detection via machine learning methods on graphs. This will make it possible to work on early detection, or even the modeling of "generic" misleading information propagation.
The district heating network (DHN) facilitates the integration of renewable heat producers and enables efficient energy transport with an optimal control. To take advantage of these advantages, it is necessary to optimize and simulate the network, which is computationally expensive. Dubon joined the Lab-STICC DECIDE team in October 2022 and is also affiliated to the GEPEA OSE team. From the formulation of the DHN as a connected graph, in his thesis, Dubon studies a new method to reduce this simulation cost by aggregating similar consumer nodes using the latest artificial intelligence architectures. His objective is to develop two complementary models: an unsupervised model to identify similar consumer nodes and a time-dependent supervised model to learn the physical dynamics of these consumer nodes.
Modern ships are much more efficient than their 19th or 20th century ancestors. Like factories, these improvements have been made possible by the high degree of systems automation. These systems, hybrids between computers and mechanics, are called cyber physical systems. Industrial control systems (ICS / SCADA) that drive machines, navigation systems, such as AIS are some examples of these CPS. Like all computer systems, they are vulnerable to cyber attacks, but a malfunction on these systems can lead to a disaster in the real world. In addition, it is very difficult to modify these systems to make them "cyber by design". This is why it is important to be able to detect quickly the occurrence of a cyber attack on these systems. There are several methods to do this: signature databases, expert rules or AI. The research questions identified at this stage are the following: What is the place of AI for the detection of attacks on physical cyber systems of ships? How to evaluate the performance of a cyber attack detection algorithm in a maritime SPC context? How to allow the decision maker to choose the most efficient algorithm or combination of algorithms in this context?
The objective of Antoine Mallégol's thesis work is to propose an optimization method for a coupled energy system, composed of an electrical network and a heat network that can interact with each other. The main challenge of this work is to solve a complex model with a long time horizon. Different modeling and optimization methods are proposed: mixed integer linear programming, heuristics, and metaheuristics. A multi-objective approach allows to improve the costs and the environmental impact of the system.
Incorporated into the DECIDE team at LabSTICC since 2020 and the ECORIZON team at Chantiers de l'Atlantique since 2019, Fred is conducting a thesis focused on reducing energy consumption and the environmental footprint of cruise ships. The scientific challenges of his work include integrating data from various sources (sensors, weather archives, supplier data, etc.), applying machine learning techniques, modeling the systems and subsystems that make up the ship, and developing decision-support tools, from design to operation. His work is carried out under a CIFRE thesis, in partnership with IMT Atlantique and Chantiers de l'Atlantique.
Quentin Perrachon is an industrial PhD student as part of a collaboration between the DECIDE team at Lab-STICC at the University of South Brittany and the company Herakles based in Vannes. Herakles develops and distributes an ERP software and wishes to offer an additional tool to provide solutions to scheduling problems for small to medium-sized manufacturing workshops. A generic modeling approach is proposed to solve problems for a wide variety of industries, this modeling is based on the flexible job shop scheduling problem with the addition of several industrial constraints, such as resource unavailability or the potentially partial necessity of resources for certain operations. The goal is to maintain just one model and tool capable of meeting the demands of different industries. Originating from operations research, exact and metaheuristic approaches based on neighborhood techniques are explored and proposed to solve this problem.