I am mostly interested in Artificial Intelligence problems, and I am happy to supervise projects in (almost) any area of AI. However I am also happy to supervise general CS projects.
I have listed some suggestions below for projects as a starting point, but I am happy to discuss other ideas if there is a project you particularly want to work on.
There is also a list of slightly more advanced projects for students with more programming experience.
There are several existing web-based carbon footprint calculators, e.g., carbontrust.co.uk, carbonfootprint.com. However the personalisation offered by these sites is limited. The aim of this project is to develop a website that allows people to track their carbon footprints and collaborate with other users to reduce them. After registering, users should be able to calculate their carbon footprint (e.g. home energy consumption, commuting, holiday flights etc) and track these against their personal, family or organisational targets. In addition, users should be able to share ideas with others (e.g., via blogs), and participate to reduce their carbon usage, e.g., by car pooling, matchmatking for recycling of building materials etc.
E-learning and coursework submission systems such as WebCT and moodle primarily support the submission of and feedback on text based coursework. However many courses involve graphical coursework, e.g., photography, engineering, architecture etc. The aim of this project is to build a coursework submission and feedback system that supports commenting on graphical coursework. In addition to standard e-learning system features such as user registration, setting courseworks, submission management, notification of submissions and feedback etc, it should provide facilities to allow feedback comments to be placed at particular location on an image (without downloading the image, opening it in acrobat or photoshop, adding the comment and re-uploading it).
There are many energy savings calculators on the web. In general, these give only very approximate indications of the energy that could be saved by various energy saving measures such as adding insulation, double glazing, installing solar collectors etc, as there is no way to provide geometric information about a building. The aim of this project would be to devleop a web-based energy savings calculator that allows users to enter basic geometric information about their home, e.g., shape and size of rooms, size and position of windows, position and heights of surrounding buildings and trees, etc., and use this information to provide more accurate estimates of the impact of energy savings measures.
Valentino Braitenberg's book Vehicles contains a series of thought experiments designed to show how seemingly complex behaviour can result from (very) simple robot architectures. Braitenberg's vehicles use direct, excitatory and inhibitory couplings of sensors to motors: sensors respond to features in the environment, e.g., heat, light etc.; motors move the vehicle in response to signals from the sensors; connections carry signals from the sensors to the motors and either cause the motors to turn or inhibit them from turning. Braitenberg describes a range of vehicles, including those (he) imagined to exhibit: cowardice, aggression, and even love. There are a number of Java and web-based Braitenberg simulators available, e.g., the KOVAN Braitenberg Vehicles applet. However in general these do not allow the vehicles to respond to objects in the simulated environment, such as obstacles and other vehicles. The aim of this project is to implement a Braitenberg vehicles simulator in which the agents can respond to objects and other agents in the environment.
There is growing interest in using rule-based system technology such a CLIPS and JESS to implement business processes. The aim of this project is to explore the practical feasibility of such tools for a non trivial collection of business rules, such as the EU-Car Rent example which forms part (Annex E) of SVBR standard for business rules developed by the OMG. This would involve developing an appropriate way to encode the alethic and deontic modalities found in SVBR rules within the programming formalisms supported by existing rule-base systems.
This file is maintained by Brian Logan Last modified: 22-May-2015, 17:00