Projects

1 - 10 of 2801 results

Search term:

A thorough study of fuzzy rough sets and their application to data reduction Ghent University

Chris Cornelis
Department of Plant Biotechnology and Bioinformatics, Department of Applied Mathematics, Computer Science and Statistics

The goal of this project is to provide a systematic, theoretical study of the hybridization of fuzzy sets and rough sets, unifying existing proposals and developing new ones, with a view to enhance their suitability for data reduction purposes, as well as to investigate desirable properties that may be inherited from the contributing theories.

Data reduction based on fuzzy rough sets Ghent University

Hans De Meyer
Department of Applied Mathematics, Computer Science and Statistics

As datasets are getting more and more high-dimensional, there is an emerging need for data reduction techniques. This project focuses both on feature selection that selects relevant features and instance selection that removes irrelevant or noisy instances. More specifically, we work on fuzzy rough data reduction, data reduction for imbalanced datasets and robust data reduction.

Sabbatical Joris Vermeesch: Computational analyses of large sequencing data sets KU Leuven

Joris Vermeesch
Department of Human Genetics

Genetics is transforming into genomics, from individual gene analyzes to the analysis of large amounts of genomic data. Where my expertise has been built up in a period of gene research, I want to expand my knowledge of genome research. That will focus on the analysis of large genomic databases and genome assemblies to identify genetic causes of developmental disorders.

Principles of Pattern Set Mining for structured data. University of Antwerp

Bart Goethals
ADReM Data Lab (ADReM)
In this project, we propose to develop and study general techniques to mining sets of patterns directly. Such pattern sets should contain only high quality patterns that are of direct interest to the user and her application.By developing pattern set mining techniques, we hope to to lift pattern mining techniques from the local to the global level, which in turn should contribute to a better understanding of the role of pattern mining techniques ...

Set identification in nonlinear panel data models. KU Leuven

Geert Dhaene
Research Centre of Econometrics, Leuven

Panel data models are used in a wide range of economic applications, but in models with unobserved heterogeneity, estimates of the structural parameters will in general be inconsistent. This is referred to as the incidental parameters problem. Recently, it has been shown that in some models point identification may not even be possible. Given the failure of point identification, it is natural to shift the attention from point estimation to ...

Dealing with Imbalanced and Weakly Labeled Data in Machine Learning using Fuzzy and Rough Set Methods Ghent University

Yvan Saeys
Department of Applied Mathematics, Computer Science and Statistics, Department of Internal medicine

The goal of this project is to tackle two important and challenging problems in machine learning, namely learning from imbalanced and weakly labeled data, using the hybridization of fuzzy sets and rough sets.

A thorough study and explicit enhancement of fuzzy-rough methodologies will allow for the construction of robust new solutions tailored specifically to the problems stated above.

Clinical image quality targets in dental cone-beam CT, set and controlled with anthropomorphic test objects, virtual observers, and big data KU Leuven

Hilde Bosmans
Medical Physics & Quality Assessment, Oral and Maxillo-facial Surgery - Imaging & Pathology (OMFS-IMPATH)
Cone beam computed tomography (CBCT) has evolved into a pivotal imaging modality in dentistry. The wide spread of CBCT has resulted in over 70 different models being used in clinical practice. The wide range in performance (radiation dose and image quality) between these CBCT units calls for new testing methods that are both objective and relevant to the diagnostic task(s) in dental imaging. The current project aims to address this issue in ...

Interactive mining and evaluation of pattern sets. KU Leuven

Luc De Raedt
Informatics Section

We live in the era of data and need tools to reveal valuable information in large amounts of data. The goal of exploratory data mining is to provide as much insight in given data as possible. Within this field, pattern set mining aims at revealing structure in the form of pattern sets. Individual patterns describe subsets of the data; a non-redundant set of patterns provides a global description.

Although pattern set mining is a ...