Here you can find suggestions for Master projects in computer science, information science, and artificial intelligence. If you're interested in one of these topics, I am positive that we can put together a lighter version for a Bachelor project.
Brain-Computer Interfacing (BCI) has as its goal to infer subject intent from brain data using classification. At the FC Donders institute we try to achieve BCI using magnetoencephalography (MEG) and electroencephalography (EEG). One of the problems in BCI is that the optimal classifier structure changes between training sessions. Transfer learning has been implemented as a way to learn from multiple similar tasks and could be useful to find a classifier that performs well over sessions. Furthermore, extensions of transfer learning can help in finding models that generalize well over subjects. This research would focus on testing whether transfer learning can help generalize over sessions and/or subjects.
Contact: Marcel van Gerven or Tom Heskes
Brain-Computer Interfacing (BCI) has as its goal to infer subject intent from brain data using classification. At the FC Donders institute we try to achieve BCI using magnetoencephalography (MEG) and electroencephalography (EEG). It would be useful to examine how the combination of different types of features extracted from MEG/EEG data can help to improve the classification rate.
Contact: Marcel van Gerven or Tom Heskes
Brain-Computer Interfacing (BCI) has as its goal to infer subject intent from brain data using classification. At the FC Donders institute we try to achieve BCI using magnetoencephalography (MEG) and electroencephalography (EEG). We are currently working on a Matlab toolbox for BCI classificiation. It would be useful to implement a number of existing classification algorithms and to compare the performance of these classifiers on an existing BCI dataset.
Contact: Marcel van Gerven or Tom Heskes
Malaria infects between 300 and 500 million people every year and causes between one
and three million deaths annually. Control of malaria is becoming increasingly difficult
as both the parasite and the mosquito vector are developing resistance to anti-malaria
drugs and insecticides. A good understanding of transcriptional regulation of genes in
Plasmodium falciparum, the deadliest species of the parasite that causes malaria in humans,
is important for devising new ways to disrupt the parasite's life cycle. A number of
methods that combine gene expression and genome sequence data to infer transcriptional
regulatory models have been developed, see [1] for a review of some of the existing
methods and some biological background. However, there is one more source of data available
for Plasmodium falciparum, namely, genome sequences of species related to this organism.
Since functionally relevant DNA sequences are conserved among related species, this data
source is expected to be useful for building more accurate transcriptional regulatory models.
The goal of this project is to build and test a classifier that combines Plasmodium falciparum
gene expression and genome sequence data as well as genome sequence data of one or more related parasites.
[1] Gardner, T.S., Faith, J.J. (2005). Reverse-engineering transcription control networks.
Physics of Life Reviews, 2, 65-88.
Contact: Rasa Jurgelenaite or Tom Heskes
Using a dataset of past transactions, classifiers can learn to distinguish fraudulent transactions from legitimate transactions. In a previous project, "simple" binary classifiers have been tested. The goal of this project is to study multi-class classifiers that can make a distinction between different grades of fraudulence (i.e., green/orange/red instead of just green/red).
The project is a collaboration with Digital Security and the company First8. Check out this project description (in Dutch) for more information.Contact: Tom Heskes or Erik Poll
Preliminary results have shown that approximate inference in discrete Bayesian networks can be achieved by replacing large networks potentials with a set of smaller ones while adding hidden nodes. Open questions are which decomposition methods work best and what the optimal decomposition is. This research would focus on improving the existing methods and integrating them within a Matlab toolbox for inference in (dynamic) Bayesian networks.
Contact: Marcel van Gerven
Working Tomorrow is a program of LogicaCMG that aims to test the usefulness of new technological advancements. Several of their suggested Master projects involve artificial intelligence in general and machine learning/data mining in particular.
Contact: Tom Heskes
Several suggestions for bachelor and master projects on the interface between machine learning and bioinformatics can be found on Elena's page. Topics include: fast condensed nearest neighbor with hit miss networks, graph based feature selection, protein function assignment based on shared interacting domain patterns, and predicting protein subcellular localization.
Contact: Elena Marchiori