Détection d'anomalies dans les flux de données pour une application dans les réseaux de capteurs
Détection d'anomalies dans les flux de données pour une application dans les réseaux de capteurs
A digital twin testbed for real-time stormwater modeling with online quality control
Real-time monitoring and control of urban drainage systems promises to enable improved management of stormwater hazards like floods and combined sewer overflows. To meet these goals, water managers are increasingly demanding data-driven digital twin models that use streaming sensor data and online models to monitor stormwater dynamics in real-time....
Multi layered Misbehavior Detection for a connected and autonomous vehicle
In recent years, the vehicular field has undergone significant advancements with the development of autonomous vehicles and smart cities. These advancements have brought about a modernization of human life, where everything is interconnected - from individuals through smartphones to infrastructure, cars, and motorcycles. In such a system, informati...
Rare cortical folding patterns detection based on an unsupervised deep learning approach
One of the visual characteristics of the brain is its folded appearance. It is composed of convolutions called gyri, which are delimited by furrows called sulci. Like fingerprints, the patterns of cortical folding, i.e. the arrangement, characteristics and shape of the sulci, are unique to each individual, although they do fit into a general organi...
Predictive analysis of time series in various application contexts
Emergency medical transport in France is triggered by the dispatch of an ambulance, either by the SMUR, SAMU, by a private ambulance company or by the fire department after dialing one of the emergency numbers. Since accidents are related to human activities, which in turn depend on the time of day, season, weather, climate, special events, etc., t...
Computer vision methods for 3d concrete printing process monitoring
Construction based on 3D concrete printing has become an attractive technology, infusing digital technology to the sector. Towards this digitalization, we propose methods based on computer vision for the monitoring of constructions built using contour crafting (a 3D concrete printing method). Our methods can be divided into two types: damage and qu...
Embedded anomaly detection - Machine learning based radiation hardening of space electronics
The miniaturization of electronic components was one of the major improvements that happened during the last decades. Space agencies followed this trend and satellites became more and more complex. However, by reducing the size of their components, satellites became subject to space radiation. Indeed, satellites aren't protected by the atmosphere a...
Web-based data driven network monitoring : from performance estimation to anomaly detection
The goal of this thesis is to leverage passive measurements freely available in the browser and deep learning techniques to infer network performance and detect anomalies. We start by inferring the main properties of the underlying Network from web performance metrics based on passive measurements obtained from within the browser. We use machine le...
Perception de l'environnement de navigation pour un robot autonome en milieu agricole
Les robots agricoles autonomes offrent des moyens d'amélioration de la production par l'automatisation de tâches et l'augmentation des capacités de traitements de données et de planification. La fonctionnalité de navigation autonome est au cœur de la conception de tels systèmes intelligents destinés à l'automatisation des opérations agricoles. Dans...
Functional anomaly detection and robust estimation
Enthusiasm for Machine Learning is spreading to nearly all fields such as transportation, energy, medicine, banking or insurance as the ubiquity of sensors through IoT makes more and more data at disposal with an ever finer granularity. The abundance of new applications for monitoring of complex infrastructures (e.g. aircrafts, energy networks) tog...
