Research Bytes IV

Profs. David Brown, Neil Heffernan, Carolina Ruiz, Elke Rundensteiner, and Matthew Ward
Professors C.S. Dept., WPI

October 10, 2003
11 a.m. - 12 noon
Fuller Labs 320

Abstract:

Professor Brown:: My research is concerned with the application of Artificial Intelligence techniques to aid with, and to help model, design tasks, and interaction at human-computer interfaces.
Professor Heffernan:: Neil Heffernan will talk about the computer science issues he and his graduate students have been tackling at related to building intelligent tutoring systems. These include 1) how to use machine learning to do programming-by-demonstration, 2) computer assisted methods of determining the best fitting cognitive models that matches the data of actual students, and 3) planned work on building "assistments" for the MCAS.
Professor Ruiz:: Intelligent Techniques for Knowledge Discovery in Databases and Data Mining: Knowledge discovery is the process of finding general patterns/principles that summarize/explain a set of "observations". Very large databases have become the standard, making it impossible for human beings to mine the data "by hand" looking for interesting patterns. Automated tools are therefore needed to help discovery these patterns. I'll describe my current research projects with students and colleagues. They include data mining for genetic analysis, exploratory analysis of sleep data, mining of sequential data, and web mining.
Professor Rundensteiner:: As part of the WPI Database Systems Research Group (DSRG), we are exploring anything related to "data" in a broad sense --- how to get it, how to keep it, how to find it, and how to give the right information to the right person at the right time. In this colloquium, I'll, in particular, touch on two of our currently on-going efforts in the DSRG group. One, how to put the database concepts upside down and inside out; where the queries are a-priori designed and standing, while the data is streaming by over time and continuously changing (our stream monitoring engine RAINDROP). Two, how to make a marriage between automata theory, (pattern matching for XML), and database systems (algebraic query optimization techniques) work and even flourish (our XQuery subscription system).
Professor Ward:: Every Picture Tells a Story - exploratory visualization is a process by which data and information are mapped to graphical entities and attributes that can then be interactively investigated by the human analyst. I will describe the process of designing an effective visualization as well as summarize a number of my on-going and potential future projects in the area of visual data mining.

Refreshments will be served.

Maintained by webmaster@wpi.edu
Last modified: Sep 27, 2006, 16:05 EDT