Student projects
Below follows a list of project descriptions for students. Some of the projects are finished, some are in progress, and some are still available to students that want to do a UG4, MSc or a PhD projects.
If you want to do an MSc or PhD with us, and are not yet a student at the University of Edinburgh, then you need to go through the application procedures set by the School of Informatics. You need to apply under Intelligent Systems & their Applications.
The University of Edinburgh offers a MSc/Diploma in Distributed Scientific Computing.
Directly evolving parameter settings for machine learning models
13 March 2010 - 9:17pm — Jano.van.HemertPrinciple goal: Directly evolving parameter settings for machine learning models
Accelerating Genome-Wide Association Studies with Graphics Processors
22 January 2010 - 1:04pm — Jano.van.HemertPrincipal goal: to substantially improve the performance of the data-intensive analysis for genome-wide association studies (GWAS) by using graphics processing units (GPUs).
Parameter fitting of cosmological models using billions of galaxies
15 January 2010 - 7:45pm — Jano.van.HemertPrincipal goal: to develop, test and make available to the cosmology community a parameter estimation method for models that explain our dark Universe.
Data mining to identify small molecules with bioactivity
15 January 2010 - 7:31pm — Jano.van.HemertPrincipal goal: to apply machines learning to identify small molecues that are likely candidates to have relevant bioactivity for follow-up wet-lab experiments.
Optimising Data-Streaming Elements in Distributed Data Mining
15 January 2010 - 2:59pm — Jano.van.HemertPrinciple goal: To evaluate existing data streaming implementation, formulate model to predict streaming performance corresponding to buffering strategy and then optimise data streaming with dynamical buffering implementation.
Improving Data Placement Strategy in Data-intensive Computations
15 January 2010 - 2:57pm — Jano.van.HemertPrinciple goal: to investigate existing data placement strategies and build a decision model to improve data placement strategies in enacting data-intensive workflow.
Large-scale data mining of chemical-genetic data sets
14 January 2010 - 3:50pm — Jano.van.HemertPrimary objective: to perform data mining on a real-world data set from a biology lab in the School of Biological Sciences with the aim to extract patterns that lead to hypotheses about mode of action of compounds and function of genes.
Detecting Web Spam using Machine Learning
14 January 2010 - 3:10pm — Jano.van.HemertPrimary goal: to develop a classification algorithm to detect Web Spam.
Accelerating data intensive applications using MapReduce
14 January 2010 - 3:08pm — Jano.van.HemertPrincipal goal: by a way of real case study in the Life Science, the goals of this project include: 1) Understanding data-parallel processing using MapReduce model for addressing Performance issues in data intensive applications; 2) Investigating how to adapt data mining algorihtms to the MapReduce model; 3) Prototyping and comparing performance with other frameworks that support data intensive applications.
Detection and elimination of personal data contained in medical images
5 January 2010 - 4:13pm — Jano.van.HemertPrincipal goal: evaluating and implementing different techniques for detecting, recognising and eliminating text containing personal data in medical images.
