Projects
The role of algorithm aversion and human-automation trust in the use and acceptance of Forecast Support Systems Ghent University
Forecasting is a vital skill needed for remaining competitive in today’s business world. Forecast Support Systems (FSS) have now largely automated the forecasting process. Yet, the role of the forecasters themselves cannot be underestimated. Judgment occurs at various stages of the forecasting process, such as in the selection and evaluation of a forecasting model. But just how good are people at working with formal methods? Two distinct but ...
Extending Automatic Algorithm Selection to the Online Setting KU Leuven
The goal of this PhD is to extend the methodology of automatic algorithm selection to the online setting. The goal of automatic algorithm selection is to automatically select the best algorithm to solve a problem with. This field of research is motivated by the observation that for many problems in artificial intelligence and operations research no clear best algorithm exists. Rather, each algorithm performs well on some of the problem ...
Data Analytics for Algorithm Design KU Leuven
The development of algorithms solving computationally hard optimisation problems has a long history. Several important contributions can be traced back to the mid of the 20th century. Today, state-of-the-art optimisation problems are of high complexity, combining different components developed around a variety of conceptual approaches. The number of concepts as well as alternative implementations of those concepts makes algorithm design an ...
Design and implementation of a low cost attitude determination and control system with novel star tracker algorithm. KU Leuven
The attitude determination and control system determines and controls the orientation of the spacecraft. This system is crucial in the majority of space missions to e.g. point a camera to a star or direct an antenna to a ground station. Increasingly complex missions drive the need for higher accuracy, while the growing number of small spacecraft requires high robustness and low computational cost. This work focusses on the star ...
AutoTime: Automated Algorithm Recommendations for Timetabling Problems Ghent University
From timetabling courses in universities, over assigning nurses in hospitals, to keeping vital logistics running in harbors, timetables are nowadays crucial in keeping our economies and societies running. The construction of these timetables is a complex optimization problem where a multitude of case-specific wishes need to be considered. An important decision is therefore what timetabling algorithm from the literature to choose. This ...
Development of an algorithm for the screening of Non-Alcoholic Fatty Liver Disease. University of Antwerp
A matheuristic routing algorithm in support of a dynamic, integrated mobility system Vrije Universiteit Brussel
providing demand-dependent door-to-door transport tailored to the needs of people with mobility
restrictions. Since it is not efficient to subsidize two systems operating independently in the same
service area, many governments are currently implementing an innovative demand-driven
mobility policy. Private ...
Shared acoustic awareness and algorithm self-configuration in a cooperative audio signal processing context KU Leuven
When cooperative audio processing algorithms are envisaged to run on different audio devices located in the same acoustic environment, a number of crucial questions arises on how this cooperation can be seamlessly organized and managed. First, devices should decide which information on the acoustic scene to share with other devices for increasing the overall acoustic awareness (e.g. room acoustics parameters, sound source models and ...