Projects
The effects of selection by regularization in high-dimensions - composite estimation, model averaging and dimension reduction KU Leuven
There is a recent awareness of requiring additional efforts for inference when a selection of variables or models has taken place. This can be placed into the larger framework of correct inference and research integrity.
We focus mainly on the high-dimensional setting and consider these valid post-selection issues for composite estimation, model averaging and dimension reduction. Composite estimation involves using a linear ...
Development of a clinical decision support system for diagnosing acute rejection and graft failure after kidney transplantation KU Leuven
After kidney transplantation, several non-invasive biomarkers were proposed for diagnosing acute rejection, as well as predictive models for kidney transplant failure. The diagnostic and predictive value of a single biomarker will probably never be sufficient to accurately diagnose rejection or graft loss, and thus integrated approaches are needed. Moreover, biomarkers are dynamic and their longitudinal evolution is clinically more relevant ...
Unravelling the regulation of secondary metabolite clusters in non-conventional yeasts: sophorolipid biosynthesis by Starmerella bombicola as a case study Ghent University
Fungal secondary metabolites comprise a wide range of bioactive and industrially relevant small molecules. The genes encoding the enzymes for the biosynthesis of such compounds are mostly organised in biosynthetic gene clusters (BGCs). Despite the insights that have been acquired so far, the transcriptional regulation of many BGCs remains enigmatic, thus impeding the valorisation of the respective secondary metabolites. The main cause is ...
Optimum survey design for the study of spatio-temporal data Ghent University
In various life science applications, the acquisition of spatial data can be labor intensive or costly such that in practice one is interested in an efficient design for data collection, e.g. for the acquisition of species observations to model species distribution or for the acquisition of weather observations for the study of climate extremes. Although a rich literature is available on spatial survey designs, less is known on how to develop ...
Data-driven Passenger-seeking Recommendation System for Street-hailing Taxis KU Leuven
Street-hailing taxis provide a primary transport service in modern cities. This service model relies on taxi drivers driving around, arbitrarily picking up passengers on the street. In this dissertation, we aim to develop a passenger-seeking recommendation system called TaxiRec, which directs vacant taxis towards predicted future passengers. The research is motivated by the challenge that passengers do not explicitly request a ride by phone ...
Bayesian networks and kernel methods: algorithms for the development of more accurate clinical decision support systems. KU Leuven
Responsible actuarial and statistical learning KU Leuven
Insurance is a highly data driven business, where reliance on analytics for decision making is key. Actuaries design risk transfers and require appropriate methods to model, to estimate and to predict risks. Insurers collect fine-grained, high-dimensional data, where both the presence of covariates of different types (e.g., continuous, factor, spatial) as well as the volume of the data are challenging. The focus of the PhD research is on ...
Mapping Exposure-Induced Immune Effects: Connecting the Exposome and the Immunome KU Leuven
Immune-mediated, non-communicable diseases, such as autoimmune diseases, allergic diseases and asthma, are chronic disorders in which the interaction between exposome and immune system plays a pivotal role. As prevalence and societal costs of these diseases are rising in the EU, a holistic approach is needed.
The EXIMIOUS consortium—gathering high-level experts in immunology, toxicology, clinical medicine, environmental hygiene, ...