Projects
Performance-Enhancing Techniques for Tucker Tensor Decompositions in Data Processing KU Leuven
As datasets grow in size, so has their dimensionality in many cases. Numerical data in the form of arrays with 3 or more dimensions, i.e. tensors, are commonly found in hyperspectral imaging, diffusion tensor imaging, simulations, X-ray scans, and so on. Even relational databases can be represented using sparse tensors. As a result of this trend, tensor decompositions were developed to process such multidimensional numerical data. Among ...
Agrifood 4.0 = Agri 4.0 + Food 4.0: Use case in potato and vegetable processing sector Inagro vzw
Processing, properties and characteristics of steels used in the electricity sector Ghent University
Objectives
A. To establish a partnership between Mexican and European institutions interested in deepening into the knowledge regarding the processing and improvement of the steel destined to the electrical sector. The alliance will carry out studies on the complete processing route of these steels, from their fusion, to the manufacture of the final products. The participation of academics and industrials during the various stages of the ...
Audio classification with resource-constrained wireless sensor networks KU Leuven
Smart sensing has been subject of significant academic and industrial interest, as these services are becoming more popular due to integrated devices shrinking in size while maintaining their computational power. When designing an integrated solution for a given application, an important choice is to select a proper set of sensor modalities along with the amount of sensors that are needed to cover the environment. In this dissertation, ...
Adaptive Sensor Fusion for Autonomous Driving Ghent University
Thanks to advancements in sensing technology and ICT, autonomous driving is promising to revolutionize transport and mobility. Unfortunately, current systems do not adapt well to unexpectedly complex and/or dynamic situations and environments. This limits the value of autonomous driving at best and causes bodily harm at worst.
The pursuit of improved robustness and overall performance has resulted in a trend towards sensor fusion, ...
Digital signal processing for digital communication, audio- and speech signal processing KU Leuven
Marc Moonen supervises a research team of pre- and postdoctoral researchers performing research in digital signal processing algorithms design and evaluation, for digital communication and audio- and speech signal processing. Digital communication activities are targeted towards physical layer processing (e.g. equalization, multiple-access, interference/crosstalk cancellation and MIMO transmission techniques) and resource allocation, in ...
Sensor fusion and adaptive learning for optimization and control of Wire-Arc Additive Manufacturing – with applications to functionally graded materials KU Leuven
A niche research trend in advanced materials is the creation of materials that are non-isotropic or graded in single or multiple directions of a component, which is referred to as functionally graded materials (FGM). Directional material properties are seen in nature in various forms and this can be utilized in engineering applications where a gradation in thermal, mechanical or tribological properties are required. FGMs can be created with ...
Distributed Spatial Filtering in Wireless Sensor Networks KU Leuven
Wireless sensor networks (WSNs) paved the way for many new technological and scientific advances by accessing information previously unavailable. For example, continuously being able to monitor the brain is crucial for many treatments in the biomedical and healthcare fields, especially for patients suffering from neurological disorders. Using sensor networks, electrical activity of the brain can be measured by sensors placed on the scalp of ...
NIR-Sensitivity-Enhanced Gated Image Sensor for Fluorescence Lifetime Imaging Microscopy (FLIM) KU Leuven
Because of the deep tissue penetration and the lower influence from the autofluorescence background, fluorescence lifetime imaging microscopy (FLIM) in the near-infrared (NIR) range becomes attractive for bioimaging. However, to reconstruct the fluorescence decay profile with the time-resolved technique, repetitive short excitation pulses are required, and a large number of light exposures easily result in the photobleaching of the ...