Projects
Machine Learning and Radar Sensors for Monitoring Patients and Elderly People in Healthcare Ghent University
Ecosystem response to climate change: a machine learning approach KU Leuven
The response of ecosystems to climate change is one of the largest uncertainties in future climate projections as the response of ecosystems to disturbances (e.g. wildfire), anomalies and extremes (e.g. droughts, heatwaves,…) remains poorly quantified. Although the frequency and intensity of disturbances, anomalies and extremes are projected to continue to increase with climate change, the ecological impact across ecosystems remains a major ...
A combined framework of machine learning and extreme value theory for anomaly detection and ranking Ghent University
Anomaly detection is frequently encountered in quantitative research in the life sciences. Conventional machine learning methods are not fully adapted to deal with the identification nor the ranking of rare events. In this PhD track, we aim to combine machine learning methods with principles of extreme value theory, a field in statistics especially suited to build models of extremes.
Multivariate time series forecasting and classification using intrinsically explainable machine learning models to solve real-world problems. Hasselt University
Dissecting tissue spatial organization using machine learning and spatial transcriptomics Ghent University
In this project, we aim to better functionally characterize different spatial contexts within tissues. To this end we will develop novel bioinformatics pipelines to process and integrate several “omics” and imaging data types. Novel machine learning methods will be explored that aim to combine the high spatial resolution of imaging techniques with the deep phenotyping capabilities of current scRNAseq methods.
Explainable machine learning, predictive modelling, and causal inference, applied to medical data Hasselt University
Weakly supervised machine learning algorithms for object recognition in-the-wild and entity linking in videos KU Leuven
With the proliferation of video-rich data on the Internet, there is a pressing need for search tools that can retrieve not only relevant videos from a corpus, but also relevant snippets within a video. For retrieving relevant videos, current search technologies hinge on labor-intensive manual annotation of tags, which are subjective and often incomplete. To fully automate search and retrieval systems, we need tools that can understand the ...