Hospital Optimizer: Horaire récurrent avec perturbations

Thales développe le Hospital Optimizer, un outil pour gérer l’utilisation des salles d’opérations en les affectant à différentes équipes médicales. Cette allocation tient compte de la demande, des disponibilités médecins, de la disponibilité des salles et des types de chirurgies pouvant être effectuées dans chaque salle. Si la version courante du Hospital Optimizer prend bien […]

Read More
Efficient Learning-based Parameter Configuration of Cellular Networks

Network parameter configuration is crucial for optimizing performance in a cellular network. Often, such parameters are too numerous and their interdependence too complicated for them to be efficiently configured by human experts. Therefore, it is of great interest to study network parameter configuration as a machine learning problem. We aim to expand on the machine […]

Read More
Visual Analytics for Financial Risk

Project 1: The objective of this project is to design a Visual Systemic ‘Risk Map’ as one possible prototype to address some of the issues of risk identification and analysis in the context of global financial systems. We propose the design concept of the ‘Risk Map’ using principles of Cognitive Systems Engineering (instrumental papers in […]

Read More
Anonymity in the context of Data-neighborhoods

The project investigates the transformation of anonymity in times of networked-data by looking into the history of urban neighborhood design and its relation to neighborhood-related machine learning algorithms, such as k-nearest-neighbor (KNN). This method analyzes behavioral patterns to form groups (neighborhoods) of actors with the same characteristics (neighbors). This groupingis then deployed to understand and […]

Read More
Targeted Online Marketing Based on Machine Learning

Online marketing is a popular type of advertising, which utilizes the Internet to deliver advertising information to consumers in the digital era. Despite the advantages of online marketing, there is still much room for efficiency improvement. The major problem with existing online marketing is that there tend to be a mismatch between what are delivered […]

Read More
EarlyDetect: a cloud based mental health screening tool

Mental illness is the leading cause of disability in the world. Diagnosing mental health syndromes have proved challenging for clinicians. This has led to delay in diagnosis or misdiagnosis. Furthermore, the majority of individuals who have mental disorders have more than one condition (co-morbid), which are essential to screen and diagnosis early to achieve symptom […]

Read More
Employing Data Mining and Visualization Strategies for the Analysis of Well-being Indicators: A follow-up

In this project, an online, interactive map visualization tool will be built to illustrate trends of community wellbeing indicators across Nova Scotia using the 2019 Quality of Life survey as the primary source of information. The goal is to empower residents and decision-makers to understand unique well-being trends in communities, providing an invaluable resource for […]

Read More
Système de reconstruction 3D de modèles de villes virtuelles et segmentation sémantique pour l’extraction d’informations géospatiales

Le projet proposé vise à améliorer la reconstruction 3D des villes à partir des photographies aériennes et des données lidar, et plus particulièrement en combinant ces sources d’information. Des algorithmes d’intelligence artificielle, et plus particulièrement les réseaux de neurones convolutifs, seront utilisés pour améliorer la densité des nuages de points lidar pour la reconstruction 3D, […]

Read More
Scaling of IoT Simulation for Verification and Testing

Simulation is a critically important enabler for the scalable verification and testing of Internet-of-Things (IoT) systems. There has been considerable research in recent years on developing IoT simulators. The existing research nevertheless does not adequately address the optimization of simulators for the competing objectives that one typically has to contend with, e.g., in terms of […]

Read More