2003 Projects 
							
								
									
									Combining Cognitive Models
								 
								
								Advisor: Dr. Mili
								Cognitive models are created with low level cognitive architectures. These low level architectures often create lengthy models. It would be of great benefit to be able to reuse existing models by composing existing simple models together to create a more complex model. Our project involves creating an algebra to combine models in a parallel fashion.
								Lecture Notes |  
							
								
									
									Finding Symmetry in Boolean Functions
								 
								
								Advisor: Dr. Debnath
								Symmetry detection procedures have applications in circuit verification, technology mapping, and BDD construction. The objective of our project is to develop software tools for symmetry detection of complex logic functions; we are especially interested in functions for which conventional methods are not applicable.
								Lecture Notes |  
							
								
									
									Image Segmentation and Registration
								 
								
								Advisor: Dr. Li
								In medical image analysis, multiple images may want to be overlaid. This requires that the individual images line up. An improvement in computational speed would be to combine the segmentation and registration so that they can be done at the same time instead of sequentially.
								Lecture Notes |  
							
								
									
									Gender and Language Classification for Automatic Speech Recognition
								 
								
								Advisor: Dr. Sethi
								The goal of this project is to experiment with existing methods to identify the gender of the speaker of a recorded telephone quality speech. The project is part of a voice stream analysis system that automatically selects the most appropriate speaker model for speech to text conversion.
								Lecture Notes |  
							
								
									
									Pathfinder Networks for Content Based Image Retrieval Based On Automated Shape Feature Discovery.
								 
								
								Advisor: Dr. Sethi
								The project is a continuation of the 'Perceptual Vector Quantization of Binary Image Blocks' project. The ideas from the previous summer will be extended and used in Content Based Image Retrieval.
								Lecture Notes |