Undergraduate Projects - 2009

In 2008 I will be offering projects on three topics:
1) Data Mining, 2) Web Application development

Some of these projects are industry based, this means that most of the supervision might fall in the industry partner, and in some cases it might require that you work on their premises.

1. Data Mining

RAC1. Evaluation of classification algorithms for Brain Computer Interfaces

Electroencephalography is the neurophysiologic measurement of the electrical activity of the brain by recording from electrodes placed on the scalp. Electroencephalograms (EEGs) can be used to recognize specific patterns in brain activity. See Wikipedia
We can currently use brain signals so a subject can move a cursor on a screen, for example to play Pong. You will evaluate a number of machine learning algorithms that can be used to classify the brain signals.

RAC2. Clustering algorithms for web applications

co-supervisor: Jorge Villalon (tbc)
In this project you will integrate document clustering algorithms into a web application.
In the project you will develop skill integrating machine learning algorithms (or developing your own) into web applications such as wikis, blogs and discussion forums. You will be able to use the Weka framework, and Matlab that already contains a number of clustering algorithms.
All the textual data mining and web development projects require Java and web development experience. These projects are perfect if you are also doing ebus5003 or you plan to work as a web developer. You can learn more about them at the ebus5003 page.

RAC3. Managing machine learning models in collaborative web applications

co-supervisor: Jorge Villalon (tbc)
When we develop machine learning models that are trained on the text produced by collaborative web applications, the models produced change frequently. In this project you will study efficient ways for managing these models.
In the project you will develop skill integrating machine learning algorithms (or developing your own) into web applications such as wikis, blogs and discussion forums.
All the textual data mining and web development projects require Java and web development experience. These projects are perfect if you are also doing ebus5003 or you plan to work as a web developer. You can learn more about them at the ebus5003 page.

RAC4. Electrophysiological signals for recognition of emotion

When you fill an emotion your body changes (e.g. if you are scared your heart might accelerate). You will collect and analyse electrocardiogram, electromyogram and skin conductivity recordings to classify emotions. You will evaluate a number of classification algorithms. Experience with signal processing or data mining will be a plus.

RAC5. Recognizing emotions in text.

When you write an emotionally charged document the vocabulary you use might change. In this project you will explore approaches to classifying emotions in text.

2.Web Applications

RAC 10. Integrating google docs with Facebook

co-supervisor: TBC
Develop web servcies to integrate a web based writing tool such as Google doc, with Facebook. This project will require that you use Google's API (Java version) to access documents or spreadsheets, and allow others to read and modify them.
See Sharehomework for an example, where facebook is integrated to Scribd
Google Docs can be accessed using their API

3. Other

RAC11. Business continuity and System recovery in a non-for-profit.
Good Return is a website that engages and connects the Australian
public with low income borrowers in Australia and Asia Pacific that
require microfinance loans to lift themselves out of poverty. The Good
Return initiative has been developed by World Education Australia, an
international not for profit that focuses on literacy, livelihood and
microfinance. Because the Good Return website is currently in beta
mode prior to launch, we need to insure that we can recover the
systems in case of failure .Your role will be to document and test the
recovery procedures which have already been described in the Business
Continuity Manual.