Seminars
ingi |
INGI Lunchtime Seminars take place about twice a month and they address various topics related to computing sciences.
They are open to everyone, no registration is required : come and have a seat! Sandwiches and drinks are usually provided.
If you are not an ICTEAM member, join our mailing list to stay informed about the next seminars!
Coming soon ...
Ethical IT by TBC
May 8 at 10:45 a.m. - BARB 94 Place Ste Barbe - 1348 Louvain-la-Neuve
Any respectable company structures its activities around a certain number of core values, often made concrete in codes of ethics. Concepts such as diversity, inclusion, or mutual respect are often highlighted. But what is it really like in practice? how do societies bring these values to life? what are the recent developments in this area? how can an employee react when he feels that these values are not respected.
Seminar given as part of the LINFO2399 - Industrial Seminar in Computer Science
May 15 at 1:00-2:00 p.m. - Nyquist a.164 Maxwell building - 1348 Louvain-la-Neuve
Développement d'une plateforme de diffusion en continu de vidéos volumétriques exploitant le point de vue des utilisateurs by Olivier Brochu (École de technologie supérieure (ÉTS), Montréal, Québec, Canada
La vidéo volumétrique est une application de la réalité virtuelle qui capture la vidéo en trois dimensions. Les plateformes de visionnement existantes nécessitent de télécharger entièrement la vidéo volumétrique avant de la visionner, ce qui occasionne des délais frustrants pour les utilisateurs. Notre projet vise à permettre un accès instantané et ininterrompu au contenu volumétrique pour en démocratiser l’accès. Pour ce faire, une approche prometteuse consiste à exploiter le comportement des utilisateurs.
Application of the Profile Data Structure on the Cumulative Constraint: case of TimeTabling by Roger Kameugne Post-PhD, UCLouvain
Data structures are the main ingredient in strengthening both the time complexity and the filtering power of filtering algorithms in constraint-based scheduling. The Resource Utilization Profile or simply the Profile, is a well-known data structure introduced by Gingras and Quimper (2016) to store resource utilization over time. This data structure is applied to the TimeTabling filtering algorithm that is usually used as part of the cumulative constraint. The resulting quadratic algorithm of the new filtering algorithm performs competitively with existing solvers and scales effectively to large-scale cumulative scheduling problems.
Pay attention : sandwiches will be provided. Please fill in the form before day D at 09:00 to reserve a sandwich
June 5 at 1:00-2:00 p.m. -Shannon, Maxwell a.105 - 1348 Louvain-la-Neuve
Anomaly detection in CPS and my background in IoT data analysis by Mohsen Shirali ICTEAM, UCLouvain
Anomaly Detection (AD) is the process of identifying patterns in data that significantly deviate from expected behaviour. During my PhD, I focused on the Internet of Things (IoT) in healthcare applications, emphasizing systems architecture, privacy, and data analytics. I developed smart sensor systems for modelling human behaviour and assessing the health of the elderly based on physical activity analysis. Additionally, I used Process Mining and proposed techniques to detect gradual changes and anomalies in daily routines, which can indicate potential health risks.
Building on this foundation, my current research extends anomaly detection techniques to Cyber-Physical Systems (CPS). These systems integrate physical and digital components and require advanced monitoring to ensure safe and efficient operation. Anomaly detection allows for the identification of failures and unexpected behaviours. My work explores real-time anomaly detection methods, including time-series analysis, change point detection, and log analysis, as well as the application of Digital Twins to simulate and predict system behaviour. In this presentation, I will share my research background and discuss the challenges of applying anomaly detection to CPS use cases, such as vehicular networks. I will show how we are going to use the observed high redundancy in the metrics exported by vehicles to detect anomalies based on correlations.
June 19 at 1:00-2:00 p.m. -Shannon, Maxwell a.105- 1348 Louvain-la-Neuve INGI lunchtime seminar
Title TBC by Cristel Pelsser ICTEAM, UCLouvain
Abstract
