Projects
Biomedical Data Fusion using Tensor based Blind Source Separation. KU Leuven
The quest for a general functional tensor framework for blind source separation
Our overall objective is the development of a general functional framework for solving tensor based blind source separation (BSS) problems in biomedical data fusion, using tensor decompositions (TDs) as basic core. We claim that TDs will allow the extraction of fairly complicated sources of biomedical activity from fairly complicated sets of uni- and ...
Hyperspectral-hyperspatial data fusion and unimixing techniques to tackle the spectral-spatial resolution trade-off (HYPERMIX). University of Antwerp
Identifying disease genes and mechanisms through nonlinear fusion of omics data KU Leuven
As different types of omics data (genomic variation, gene expression, proteomics, etc.) keep accumulating at ever increasing speed, integratively analyzing such data to facilitate the experimental identification of which genes and variants are associated or causative for disease, better understand pathogenic mechanisms, and predict potential drug target or therapeutic strategies is also growing challenge. Starting from earlier work on gene ...
Data fusion and structured input and output Machine Learning techniques for automated clinical coding. University of Antwerp
Deep learning sensor fusion of images and other data KU Leuven
In this PhD we develop new methods to enable deep learning neural networks to use a combination of data of different nature as input. In contrast to classic image processing CNNs, that only take video data as input, we study the possibilities of adding other sensor data to the same neural network architecture, with the aim to yield an improved accuracy. We will develop and compare novel architectures and fusing methods and evaluate it against ...
Hyperspectral data processing and sensor fusion for scene understanding Ghent University
Hyperspectral data are widely used for various tasks, but often suffer from quality issues. Meanwhile, fusion of information gathered from multiple sources is also important for scene understanding. The goal of the research is joint image quality improvement and scene understanding using a combination of deep learning methods and classical video processing solutions. The result will be a flexible and extensible HSI restoration and sensor ...
Reinforcing Space Situational Awareness Data from Opportunistic Star Trackers Using Advanced Sensor Fusion Techniques KU Leuven
Given the increasing congestion of Earth's orbits, there is a need for improved Space Situational Awareness (SSA). Star Trackers present on active satellites are nowadays earmarked to aid in the mapping of space debris. In this framework the methods to reconcile and combine data from different types of star trackers integrated on diverse platforms positioned in specific orbits need to be investigated. The research focuses on inventing ...
Deep-learning data fusion for patient screening and clustering from genomics liquid biopsies and its application for presymptomatic cancer detection and stratified medicine KU Leuven
My PhD research relates to the design of an Artificial Intelligence (AI) framework for learning complex relations between the DNA profile of a liquid biopsy (i.e., DNA extracted from a blood sample) and the diagnosis, prognosis, or relapse of a tumor. This AI framework will be able to continuously integrate information from DNA profiles from tens of thousands of liquid biopsies. In particular, it will allow building models for the early ...
Privacy preserving data and knowledge fusion in personalized biomedicine KU Leuven
In our research we will investigate privacy preserving data and knowledge fusion methods in personalized medicine, and specifically privacy preservation at both levels: at the level of a single data set containing potentially sensitive, personal samples and in a multi-centric context with distributed, privately owned data sets.