Topics for Masterıs Projects and Theses -- Winter 2003 --

	Franz J. Kurfess
	Computer Science Department
	Cal Poly
	Email: fkurfess@csc.calpoly.edu

Areas of Interest

	Artificial Intelligence
		knowledge management
		neural networks for structured knowledge
	Software Engineering
		component-based systems
		process-oriented design
	Educational Systems
		teaching support

Specific Topics

	Knowlets
		Content-Based Spam Filtering
	Ontologies
	Neural Networks for Structured Knowledge
	How Computers Work
	AI Toolbox

Knowlets

	component-based systems for knowledge management
		modular design of more complex systems from simpler components
		similar to components in Software Engineering, but the emphasis is on content, not function
		content-based organization of knowlet collections
	Background: AI, SE, possibly data bases
	Funding: possibly through CAD-RC
		other funding sources under investigation

Content-Based Spam Filtering

	design and implementation of a system that categorizes email messages
		goal: identify as many unsolicited email messages (³spam²) as possible
			avoid false positives (valid messages mis-classified as spam)
	methods
		use content-based and possibly usage-based techniques rather than explicit rules to filter out spam
			Bayesian networks
				http://www.paulgraham.com/spam.html
			Collaborative filtering
	Background: AI, SE; possibly in combination with knowlets
	Funding: None

Ontologies

	design and implementation of ontologies
		(semi-)automatic extension of ontologies
		user interfaces for ontologies
			various perspectives, presentation methods
	Background: AI, SE
	Funding: some through CAD-RC
		other funding sources under investigation

Neural Networks for Structured Knowledge

	processing of complex structures representing knowledge with neural networks
		most NNs are based on vectors, and canıt represent knowledge easily
		recurrent NNs are more powerful, but also more difficult to handle
		experimentation with various types of NNs to evaluate their suitability
			bio-informatics (drug discovery, genome sequencing)
			knowledge management (ontologies, relationships between documents)
	Background: AI, specific domain
	Funding: None now

How Computers Work

	demonstrations and animations of important concepts in computer science
		goal: visualize and animate abstract concepts and methods that may be difficult to understand from static text and diagrams
		hardware
			CPU, memory, hard disk, Š
		OS algorithms
			CPU scheduling, disk scheduling, memory management, deadlock detection, Š
		data structures and algorithms
	Background: Java
	Funding: Would be most welcome :-)

AI Toolbox

	generic educational environment
		agents perform tasks in a simulated or real environment
			search for a goal, explore a room, perform a task, chase other agents, work in teams, Š
		development of search algorithms, games, knowledge representation methods
		modular design
			playground, agents with various capabilities
	Background: AI, SE
	Funding: None