Projects
Optimization of sportscientific support in sailing: talent identification, -development, performance optimization and injury prevention Ghent University
Sportscientific support contains different sport related themes: biomechanics, morphology, physiology, psychology, nutrition and injury prevention. Within talent development sailors will be supported by different specialists, each on their field. Within talent identification morphological, physiological and psychological profile of the competitive sailor will be made for every boatclass, so that the selection of boatclass will be easier in an ...
Optimization frameworks for deep kernel machines KU Leuven
Reparameterization of ReaxFF force fields using sensitivity analysis and a novel global optimization approach (AutoCheMo) Ghent University
A novel approach to global optimization is introduced for high-dimensional, expensive, and black-box optimization functions (like the reparameterization of ReaxFF force fields). Our method of optimization interference and management is shown to identify more and better minima than traditional approaches. We couple this approach with a state-of-the-art sensitivity analysis to reduce the dimensionality of the problem and speed-up the ...
Taming Nonconvexity in Structured Low-Rank Optimization. KU Leuven
Recent technological advances have led to a dramatic rate of
acquired data in many branches of sciences and engineering. A
natural way of mining valuable features out of these data is to
represent them as lower dimensional objects that allow intuitive
interpretation by domain-specific experts. Nonnegative matrix
factorization (NMF) is a popular dimensionality reduction tool where a
data matrix is decomposed to ...
ROSS (Robust optimization and scenario selection) in the context of proton therapy treatment planning KU Leuven
Newton-type operator splitting methods for real-time optimization of cyberphysical systems KU Leuven
Operator splitting techniques, introduced in the 50's for solving PDEs and optimal control problems, have been successfully used to reduce complex problems into a series of simpler subproblems. They have recently received an enormous renewed interest due to their ability in handling large-scale and embedded convex optimization problems, and thus have found numerous applications in real-time control, machine learning, data mining and signal ...
Efficient Uncertainty quantification for Optimization in Robust design of Industrial Applications Ghent University
The final objective of this project is to develop an efficient methodology for the optimization of industrial processes m.i.v. uncertainties. Uncertainties of the parameters influencing the process, as well as that of the design variables are themselves charged in the optimization cycle. It focuses on a variety of design variables and uncertainties. By adding uncertainty in the design cycle is the exploration of the design space ...