Projects
Identification of nonlinear continuous-time systems from noisy input – noisy output observations Vrije Universiteit Brussel
An empirical investigation into the acquisition and processing of L2 formulaic sequences through audiovisual input KU Leuven
To achieve high levels of proficiency and fluency in a second language (L2), learners need to acquire a large number of formulaic sequences, or frequently recurring words, phrases and word combinations assumed to be familiar and conventional to native speakers (Siyanova-Chanturia and Pellicer-Sánchez, 2019). In second language acquisition (SLA) research, the term formulaic sequence is commonly used to cover a wide range of multiword ...
Fusion of 2D and 3D Modeling and Recognition Algorithms based on Multi-Modal Sensor Input KU Leuven
Structure from Motion (SfM) is a technique that estimates 3D structure given a 2D image sequence and is well suited to reconstruct the overall shape. It depends on finding feature correspondences in the images, therefor enough texture is necessary.
Photometric Stereo (PS) is a technique for estimating the photometric normals of objects by observing that object under varying lighting conditions. This technique is well suited to recover ...
Potential yield and energy value of biomass from Low Input - High Diversity (LIHiD)-systems in Flanders. KU Leuven
Because of climate change and the finiteness of fossil fuels, the interest in alternative energy strongly increases. Besides wind and solar energy, biomass is an important source of renewable energy. To date, the focus of biomass production for bioenergy lies primarily on woody vegetation and energy crops. However, the sustainability of these systems can often be questioned.
This dissertation examines the possibilities of using biomass ...
Joint State/Input Estimation in Structural Dynamics - State/Force Estimation Using Compressive Sensing within a Multistep Approach KU Leuven
The trend of increasing intelligence in mechatronic systems characterises many products and production lines in our society, aiming at better performances, improved reliability, higher safety, reduced costs and lower emissions. When machines are operational, processes like control and monitoring employ digital computers and sensors to take decisions in response to measured data. Furthermore, during the design phase of a product additional ...
Digital Twins for high-dynamic mechatronic systems -dynamic force, torque and stress estimation KU Leuven
Dynamic Origin-Destination Matrix Estimation in Large-Scale Congested Networks KU Leuven
models are an important tool in the context of traffic planning and traffic
management. An essential input of these models is a dynamicorigin-destination
matrix. The dynamic origin-destination (OD) matrix specifies the number of travelers
from each origin to each destination, and this for each time period. In general, the
OD matrix is not directly ...
Integrating Model-Based and Data-Driven Approaches for Input/State Estimation of Mechanical Systems KU Leuven
Virtual sensing refers to a concept in which measurements or data that are not directly acquired through physical sensors are estimated or ``virtually'' generated using mathematical models, algorithms, or data fusion techniques. Virtual sensing allows the prediction or estimation of certain variables or parameters of interest based on available measurements and the understanding of the underlying system behavior. Current virtual sensing ...