Projects
Amenable C*-dynamics and their classification KU Leuven
Our understanding of amenable C*-algebras has drastically improved over the past decade due to substantial advances in the Elliott classification program. The proposed research is intended to spearhead the classification and structure theory for C*-dynamics, which encompasses groups acting continuously on C*-algebras and the question to which extent their detailed structure is encoded at the level of computable invariants. The core objective ...
Joint R&D 2023: Wound Classification and treatment recommendation system in a transmural setting Vrije Universiteit Brussel
Classification, symmetries and singularities at the frontiers of algebra, analysis and geometry. KU Leuven
This Methusalem project is a collaboration of all research groups in pure mathematics at KU Leuven. Our research focuses on five main areas of pure mathematics: algebraic geometry, algebraic topology & group theory, classical analysis, differential geometry and functional analysis. Our goal is to make progress on some of the most challenging open problems in these areas, including the monodromy conjecture on motivic zeta functions, ...
Incrementally learning new classes with generative classification KU Leuven
"Learning continually from non-stationary streams of data is a key feature of natural intelligence, but an unsolved problem in deep learning. Particularly challenging for deep neural networks is the problem of ""class-incremental learning"", whereby a network must learn to distinguish classes that are not observed together. In deep learning, the default approach to classification is learning discriminative classifiers. This works great in the ...
Incrementally learning new classes with generative classification KU Leuven
Learning continually from non-stationary streams of data is a key feature of natural intelligence, but an unsolved problem in deep learning. Especially challenging for deep neural networks is “class-incremental learning”, where a network must learn to distinguish classes not observed together.
In deep learning, the default approach to classification is learning discriminative classifiers. This works great in the i.i.d. setting when ...
Better insight into homelessness with counting research based on the ETHOS classification system KU Leuven
With the present project plan we aim - in close collaboration with the Kansfonds and with Prof. Dr. Koen Hermans of KU Leuven - to map the numbers and characteristics of (threatened) homeless people in two medium-sized municipalities by means of a counting study. of the so-called ETHOS-light classification model.
In this way we contribute to the development of a broad definition and census of homeless people based on this in order to ...
cfRRBS: translation of technological advances in methylation profiling of circulating free DNA for minimally invasive classification and relapse detection of high-grade lymphoma Ghent University
Added value for patients. For the diagnosis of high-grade lymphoma, a tissue biopsy currently remains the gold standard, but
Hodgkin lymphoma (HL) and diffuse large B-cell lymphoma (DLBCL) (the most common types) often affect organs that are
difficult to reach. In addition, the differential diagnosis usually includes a wide range of malignant and non-malignant
conditions, which makes that patients would greatly benefit from ...
Semi-supervised edge energy consumption anomaly detection and classification KU Leuven
The researcher will compare energy consumption models based on model and data-driven approaches and noisy run-time state observations. As prediction is in general more difficult than anomaly detection, (1) a first objective will be to determine normal and abnormal energy consumption profiles. Energy consumption anomalies could be hardware failures, as well as abnormal communication environment conditions (such as jammers of signal blockers). ...
Identifying prognostic variables for persistent upper limb dysfunctions after breast cancer treatment: body functions, personal and environmental factors according to the International Classification of Functioning, Disease and Health (ICF) KU Leuven
Decreased upper limb (UL) function is common after breast cancer treatment and has a tremendous impact on a woman's quality of life. Since survival rates are increasing, it is essential to identify these factors during and after breast cancer treatment contributing to persistent UL dysfunctions in terms of identifying targets for prospective evaluation and specific treatment approaches at specific time points. Therefore, this project plans a ...